WO2012102069A1 - 情報処理システム、情報処理方法、情報処理装置およびその制御方法とその制御プログラムを格納した記憶媒体 - Google Patents
情報処理システム、情報処理方法、情報処理装置およびその制御方法とその制御プログラムを格納した記憶媒体 Download PDFInfo
- Publication number
- WO2012102069A1 WO2012102069A1 PCT/JP2012/050249 JP2012050249W WO2012102069A1 WO 2012102069 A1 WO2012102069 A1 WO 2012102069A1 JP 2012050249 W JP2012050249 W JP 2012050249W WO 2012102069 A1 WO2012102069 A1 WO 2012102069A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image data
- image
- analysis
- information
- magnification
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/40—Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/60—Editing figures and text; Combining figures or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/945—User interactive design; Environments; Toolboxes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
Definitions
- the present invention relates to an information processing technology that supports diagnosis based on a tissue specimen image of a living tissue.
- Patent Document 1 describes a diagnosis support system in which a medical image is transmitted from a medical image forming system 12 to a specialist at a remote observation station 26 to receive diagnosis support by the specialist.
- Patent Document 1 when the technique of Patent Document 1 is applied to a diagnosis support system in which a large number of pathologists request diagnosis support for tissue specimen images from a diagnosis center, it takes time to transmit the tissue specimen images due to transmission capacity restrictions. You will have to wait for a long time to reply. For example, when a tissue specimen image for one slide is transmitted using a general public line, it may take several minutes to 10 minutes or more.
- An object of the present invention is to provide a technique for solving the above-described problems.
- an apparatus that supports diagnosis based on a tissue specimen image obtained by staining and imaging a biological tissue, First receiving means for receiving image data having a lower magnification out of a plurality of image data obtained at different magnifications with respect to the area image of the selected area in the tissue specimen image; First analysis means for analyzing the area image and generating first feature information based on the lower magnification image data received by the first reception means; Determination means for determining whether or not analysis based on image data having a higher magnification is necessary for the area image based on the first feature information generated by the first analysis means; A notification means for notifying a transmission request for image data with a higher magnification for the area image, when the determination means determines that an analysis based on the image data with a higher magnification is necessary; Second receiving means for receiving the higher-magnification image data transmitted in response to the transmission request by the notification means; Second analysis means for analyzing the area image and generating second feature information
- the method according to the present invention comprises: A method for controlling an information processing apparatus that supports diagnosis based on a tissue specimen image obtained by staining and imaging a biological tissue, A first receiving step of receiving image data having a lower magnification out of a plurality of image data obtained at different magnifications with respect to the area image of the selected area in the tissue specimen image; A first analysis step of analyzing the area image and generating first feature information based on the lower magnification image data received in the first reception step; A determination step for determining whether or not an analysis based on image data having a higher magnification is necessary for the area image based on the first feature information generated in the first analysis step; A notification step for notifying the transmission request of the image data having a higher magnification for the area image when it is determined that the analysis based on the image data having a higher magnification is necessary in the determination step; A second reception step of receiving the higher-magnification image data transmitted in response to the transmission request in the notification step; A second analysis step of analyzing
- a storage medium storing a control program of an information processing apparatus that supports diagnosis based on a tissue specimen image obtained by staining and imaging a biological tissue, A first receiving step of receiving image data having a lower magnification out of a plurality of image data obtained at different magnifications with respect to the area image of the selected area in the tissue specimen image; A first analysis step of analyzing the area image and generating first feature information based on the lower magnification image data received in the first reception step; A determination step for determining whether or not an analysis based on image data having a higher magnification is necessary for the area image based on the first feature information generated in the first analysis step; A notification step for notifying the transmission request of the image data having a higher magnification for the area image when it is determined that the analysis based on the image data having a higher magnification is necessary in the determination step; A second reception step of receiving the higher-magnification image data transmitted in response to the transmission request in the notification step
- an apparatus that requests diagnosis support based on a tissue specimen image obtained by staining and imaging a living tissue, Of the plurality of pieces of image data obtained at different magnifications with respect to the area image of the selected area in the tissue specimen image, transmission source specifying information for specifying the information processing apparatus and image data having lower magnification
- First transmission means for transmitting data in association with image data specifying information for specifying data;
- the image data having a higher magnification for the area image is transmitted as the transmission source specifying information and the image data.
- Second transmission means for transmitting in association with the specific information; Receiving means for receiving feature amount information of the area image associated with the image data specifying information; Display means for displaying the presence or absence of notification of the transmission request for the area image and the feature amount information of the area image in an identifiable manner by superimposing on the tissue specimen image; It is characterized by providing.
- the method according to the present invention comprises: A method for controlling an information processing apparatus that requests diagnosis support based on a tissue specimen image obtained by staining and imaging a living tissue, Of the plurality of pieces of image data obtained at different magnifications with respect to the area image of the selected area in the tissue specimen image, transmission source specifying information for specifying the information processing apparatus and image data having lower magnification A first transmission step of transmitting data in association with image data specifying information for specifying data; In response to a notification of a transmission request for image data having a higher magnification among the plurality of image data obtained at the different magnifications, the image data having a higher magnification for the area image is transmitted as the transmission source specifying information and the image data.
- a second transmission step of transmitting in association with the specific information A receiving step of receiving feature amount information of the area image associated with the image data specifying information;
- a storage medium storing a control program of an information processing apparatus that requests diagnosis support based on a tissue specimen image obtained by staining and imaging a biological tissue, Of the plurality of pieces of image data obtained at different magnifications with respect to the area image of the selected area in the tissue specimen image, transmission source specifying information for specifying the information processing apparatus and image data having lower magnification A first transmission step of transmitting data in association with image data specifying information for specifying data; In response to a notification of a transmission request for image data having a higher magnification among the plurality of image data obtained at the different magnifications, the image data having a higher magnification for the area image is transmitted as the transmission source specifying information and the image data.
- a second transmission step of transmitting in association with the specific information A receiving step of receiving feature amount information of the area image associated with the image data specifying information; The display step of displaying the presence or absence of notification of the transmission request for the area image and the feature amount information of the area image in an identifiable manner by superimposing on the tissue specimen image; A control program for causing a computer to execute is stored.
- a system provides: An information processing system for supporting diagnosis based on a tissue specimen image obtained by staining and imaging a living tissue, First image information of the area image is generated by analyzing image data having a lower magnification among a plurality of pieces of image data obtained at different magnifications with respect to the area image of the selected area in the tissue specimen image.
- First analysis means Determination means for determining whether or not analysis of image data having a higher magnification with respect to the area image is necessary based on the first feature information generated by the first analysis means; Second analysis means for analyzing the area image based on the image data having a higher magnification and generating second feature information when the determination means determines that analysis of the image data having a higher magnification is necessary.
- Display means for displaying the result of determination by the determination means and the second feature information generated by the second analysis means in an identifiable manner; It is characterized by providing.
- the method according to the present invention comprises: An information processing method for supporting diagnosis based on a tissue specimen image obtained by staining and imaging a living tissue, For the area image of the selected area in the tissue specimen image, image data having a lower magnification is analyzed from among a plurality of image data obtained at different magnifications with respect to the area image, and the first of the area images is analyzed.
- a first analysis step for generating feature information A determination step of determining whether analysis of image data having a higher magnification with respect to the area image is necessary based on the first feature information generated in the first analysis step; A second analysis step of generating second feature information by analyzing the area image based on the image data having a higher magnification when it is determined that the analysis of the image data having a higher magnification is necessary in the determination step; , A display step for displaying the result of determination by the determination step and the second feature information generated in the second analysis step in an identifiable manner; It is characterized by including.
- high-precision diagnosis support can be quickly performed on a tissue specimen image from a pathologist regardless of transmission capacity limitations.
- FIG. 1 It is a figure which shows the display screen of the analysis result to the pathologist terminal which concerns on 2nd Embodiment of this invention. It is a block diagram which shows the hardware constitutions of the information processing apparatus which concerns on 2nd Embodiment of this invention. It is a block diagram which shows the structure of the table for low magnification images concerning 2nd Embodiment of this invention. It is a block diagram which shows the structure of the table for high magnification images concerning 2nd Embodiment of this invention. It is a block diagram which shows the structure of organization structure analysis DB which concerns on 2nd Embodiment of this invention. It is a block diagram which shows the structure of feature-value analysis DB which concerns on 2nd Embodiment of this invention.
- An information processing apparatus 100 as a first embodiment of the present invention will be described with reference to FIG.
- An information processing apparatus 100 in FIG. 1 is an apparatus that supports diagnosis based on a tissue specimen image obtained by staining a biological tissue.
- the information processing apparatus 100 includes a first reception unit 101, a first analysis unit 102, a determination unit 103, a notification unit 104, a second reception unit 105, and a second analysis unit 106. And a transmission unit 107.
- the first receiving unit 101 receives image data 121 having a lower magnification out of a plurality of pieces of image data obtained at different magnifications with respect to the area image 111 of the selected area in the tissue specimen image 110.
- the first analysis unit 102 analyzes the area image 111 based on the lower magnification image data 121 received by the first reception unit 101 and generates first feature information.
- the determination unit 103 determines whether or not the area image 111 needs to be analyzed based on image data with a higher magnification based on the first feature information generated by the first analysis unit 102.
- the notification unit 104 notifies the transmission request 122 for image data with a higher magnification for the area image 111.
- the second receiving unit 105 receives the image data 123 with a higher magnification transmitted in response to the transmission request 122 from the notification unit 104.
- the second analysis unit 106 analyzes the area image 111 based on the image data 123 with a higher magnification received by the second reception unit 105 and generates second feature information.
- the transmission unit 107 transmits the second feature information 124 generated by the second analysis unit 106.
- the second embodiment is a pathological image diagnosis support system in which a plurality of pathological medical terminals and an analysis center are connected via a network, and the analysis center analyzes a tissue specimen image transmitted from the pathological medical terminal and supports diagnosis. is there.
- a low-magnification area image of the selected area is transmitted from the pathological medical terminal.
- the analysis center analyzes the low-magnification area image to determine whether it is necessary to analyze the high-magnification area image. If necessary, the pathological medical terminal is requested to transmit a high-magnification area image.
- the analysis center analyzes the high-magnification area image and notifies the pathological terminal of the analysis result that supports the diagnosis. According to this embodiment, it is possible to quickly and accurately receive support from the analysis center for diagnosis based on a tissue specimen image by a pathologist.
- the diagnosis support service in the analysis center can be realized with fewer resources.
- FIG. 2 is a block diagram showing a configuration of a pathological image diagnosis support system 200 that is an information processing system according to the present embodiment.
- the pathological image diagnosis support system 200 includes an information processing apparatus that functions as an analysis center 210, an information processing apparatus that functions as a plurality of pathological terminals 220, and a network 230 that connects the analysis center 210 and the plurality of pathological terminals 220. With.
- the analysis center 210 includes a communication control unit 215 for communicating with a plurality of pathological medical terminals 220 via the network 230.
- a low-magnification area image of one region of interest (hereinafter referred to as ROI: Region of Interest) transmitted from the pathologist terminal 220 is analyzed, and if necessary, a high-magnification area image of the same ROI is analyzed as a result of the analysis.
- a low-magnification image analysis unit 211 that performs a transmission request is provided.
- the low-magnification image analysis unit 211 includes a low-magnification image table 212 that is used for analysis of a low-magnification area image and a transmission request for a high-magnification area image.
- a high-magnification image analyzing unit 213 that analyzes a high-magnification area image of the same ROI transmitted from the pathological medical terminal 220 and returns the analysis result to the pathological medical terminal 220 as diagnosis support information is provided.
- the high-magnification image analysis unit 213 includes a high-magnification image table 214 used for analyzing a high-magnification area image and transmitting diagnosis support information.
- Each pathological terminal 220 includes a control unit 221 that controls the operation of the pathological terminal 220 and communication with the analysis center 210.
- a scanner 222 that reads a pathological slide obtained by photographing a stained biological tissue at a resolution corresponding to a high magnification is provided.
- a display 223 for displaying the tissue specimen image read by the scanner 222 is provided.
- FIG. 2 does not show a keyboard or pointing device for data input or operation instruction, but it is assumed that necessary input / output devices are connected.
- the low magnification is “X10” and the high magnification is “X40”.
- the low magnification is 3,000 ⁇ 3,000 pixels and 0.21 ⁇ m / pixel
- the high magnification is 12,000 ⁇ 12,000 pixels.
- low magnification for example, a tissue structure including the shape of a gland duct can be analyzed, but individual cells and cell nuclei cannot be analyzed.
- high magnification it is possible to accurately analyze individual cells and cell nuclei.
- FIG. 3 is a sequence diagram showing an operation sequence 300 of the pathological image diagnosis support system 200 which is the information processing system of the present embodiment.
- FIG. 3 operations from reading a pathological slide by the scanner 222 of the pathological medical terminal 220 to displaying the diagnosis support information on the screen will be described.
- the pathological medical terminal 220 reads a tissue specimen image from the pathological slide by the scanner 222.
- the resolution of the scanner 222 corresponds to the high-magnification image data of the tissue specimen image, but there is no upper limit on the resolution.
- the read tissue specimen image is displayed on the display 223.
- a tissue region used for diagnosis is selected from a plurality of tissue regions in the tissue specimen image.
- an ROI that requests analysis to the analysis center 210 for diagnosis support is selected from the selected tissue region (see FIG. 4).
- the selection of the tissue region and the selection of the ROI may be instructed by the pathologist from the tissue specimen image on the display 223 screen, or may be determined by existing automatic ROI setting software.
- the automatic ROI setting software determines the target region by calculation with a small load (for example, detection of a region heavily stained with hematoxylin, etc.) compared to the amount of calculation for full-fledged cancer diagnosis performed at the analysis center 210.
- a light software module hereinafter, this software module is referred to as LWA (Light-weight Analyzer) in this specification.
- the pathological medical terminal 220 transmits the low-magnification image data of the selected ROI to the analysis center 210.
- the tissue specimen image read by the scanner 222 corresponds to the high-magnification image data, and therefore, the low-magnification image data is generated by reducing the resolution by, for example, thinning processing.
- the low-magnification image data to be transmitted includes at least the terminal ID of the pathological medical terminal 220, the image number for specifying the image, the site of the taken tissue (stomach, lung, breast, prostate, etc.), and the staining method (HE method, IHC) Method, FISH method, etc.) are attached for analysis and result transmission by the analysis center 210.
- the image number is a number independent of the patient's personal information, and the management of the personal information is converted and assigned so as to be completed in the pathologist terminal 220.
- the allocation method will be described with reference to FIG. 7A.
- only one piece of information is sufficient for selecting an analysis method, only one piece of information is sufficient.
- gender and age information, address and nationality information, etc. may be added for analysis or information storage in a database (hereinafter referred to as DB) or analysis within a range in which the patient's personal information does not leak.
- DB database
- DB database
- a plurality of ROIs are selected in one tissue region, but low-magnification image data may be transmitted collectively for a plurality of ROIs or individually for each ROI.
- step S307 the analysis center 210 that has received the low-magnification image data performs a simple tissue structure analysis using the tissue structure analysis DB that has been learned and registered in advance based on the ROI low-magnification image data.
- this ROI is considered to be a cancer cell candidate, it is determined whether analysis using high-magnification image data is necessary.
- FIG. 8A shows an example of the organization structure analysis DB.
- the next ROI is determined.
- the area image of each ROI is analyzed completely independently without relating to the patient or the pathological medical terminal of the transmission source. Moreover, it may be analyzed independently from other ROI area images in the tissue specimen image from the same pathological slide.
- the analysis center 210 requests the pathological medical terminal 220 to transmit high-magnification image data.
- the transmission request can specify an area image without transmitting patient information, based on the terminal ID and image number of the transmission source.
- the pathologist terminal 220 confirms that the request partner is the own terminal based on the terminal ID of the transmission source, and specifies high-magnification image data to be transmitted based on the image number.
- the ROI information for which high-magnification image data is requested is held for displaying the analysis result.
- the pathological medical terminal 220 transmits the high-magnification image data of the requested ROI to the analysis center 210 together with the transmission source terminal ID and the image number.
- step S317 the analysis center 210 that has received the high-magnification image data performs a fine feature quantity analysis using a feature quantity analysis DB that has been learned and registered in advance based on the ROI high-magnification image data.
- the feature amount analysis may differ depending on the part of the biological tissue or the staining method.
- FIG. 8B shows an example of the feature amount analysis DB.
- step S319 the analysis center 210 transmits the feature amount analyzed based on the high-magnification image data or feature amount information representing the feature amount to the pathological medical terminal 220 as an analysis result.
- step S321 the pathological medical terminal 220 that has received the analysis result superimposes the analysis result on the tissue specimen image read from the pathological slide in step S301 and displays it on the display 223 in step S323 (see FIGS. 5A and 5B).
- the pathologist refers to the analysis result displayed on the display 223 as support information, and diagnoses the tissue specimen image.
- diagnosis prediction based on the feature amount in the feature amount analysis in step S317 has already been realized.
- the diagnosis prediction may be displayed on the display 223 in step S323 to provide diagnosis support.
- FIG. 4 is a diagram showing a screen 400 displayed on the display 223 of the pathologist terminal 220 at the time of transmitting the selected ROI area image to the analysis center 210.
- the screen 400 displays a plurality of selected ROIs 401 to 404 superimposed on the tissue region selected from the tissue specimen image.
- Low-magnification area images in the plurality of ROIs 401 to 404 are transmitted to the analysis center 210 to obtain diagnosis support information.
- the area images of the plurality of ROIs 401 to 404 may be transmitted at once, or one ROI may be transmitted sequentially.
- FIG. 4 shows a case where the ROI is rectangular, it may be another shape such as a circle or an ellipse, or may be a shape that matches the outline of the cell mass.
- 405 in FIG. 4 is management information of the displayed tissue specimen image in the pathologist terminal 220 and information for specifying the analysis center 210 that is a request destination for requesting diagnosis support. Among these, personal information such as name is not transmitted to the analysis center 210. Note that the information shown in 405 is an example, and the present invention is not limited to this.
- FIG. 5A is a diagram showing a first screen 510 in which the analysis result analyzed based on the low-magnification image data in the analysis center 210 is displayed on the display 223 of the pathological terminal 220.
- the analysis results of the plurality of ROIs 401 to 404 in FIG. 4 are represented by differences in the lines of the rectangular frame surrounding the ROI.
- ROI 511 indicates an area without cancer cells that does not need to analyze high-magnification image data by a thin solid line.
- ROIs 512 and 513 indicate areas where the high-magnification image data needs to be analyzed and the cancer cells are clear, with thick solid lines.
- ROI 514 indicates an area without cancer cells, although it requires analysis of high-magnification image data by a thick broken line.
- it is represented by the difference in the lines of the rectangular frame, but may be another identifiable display such as a difference in color.
- 515 in FIG. 5A is management information of the displayed tissue specimen image in the pathologist terminal 220 and information specifying the analysis center 210 of the report source that reported the analysis result of the diagnosis support.
- personal information such as name is managed by the pathologist terminal 220. Note that the information shown in 515 is an example, and the present invention is not limited to this.
- FIG. 5B is a diagram showing a second screen 520 in which the analysis result analyzed based on the high-magnification image data in the analysis center 210 is displayed on the display 223 of the pathologist terminal 220.
- the analysis results of the plurality of ROIs 401 to 404 in FIG. 4 are represented by display of feature amounts analyzed corresponding to each ROI having cancer cells.
- ROIs 521 and 524 indicate that there are no cancer cells because no feature value is displayed.
- the ROIs 522 and 523 are displayed as values of the average nucleus size ( ⁇ m 2), the average deformity, and the texture as feature amounts. Note that the feature amount varies depending on the part of the biological tissue and the staining method, and an example thereof is shown with reference to FIG. 8B. 5B may be displayed in combination with FIG. 5A.
- 5B in FIG. 5B is management information of the displayed tissue specimen image in the pathologist terminal 220 and information for specifying the analysis center 210 that has reported the analysis result of the diagnosis support.
- personal information such as name is managed by the pathologist terminal 220.
- the information indicated by 525 is an example, and the present invention is not limited to this.
- FIG. 6 is a block diagram showing a hardware configuration of the analysis center 210 according to the present embodiment. Although FIG. 6 shows a configuration with one device, it may be configured with a plurality of devices according to function.
- a CPU 610 is a processor for arithmetic control, and realizes a control unit of the analysis center 210 by executing a program.
- the ROM 620 stores fixed data and programs such as initial data and programs.
- the communication control unit 215 controls communication with a plurality of pathological medical terminals 220 via the network 230. Such communication may be wired or wireless.
- the RAM 640 is a random access memory that the CPU 610 uses as a temporary storage work area.
- an area for storing data necessary for realizing the present embodiment is secured.
- received data 641 including image data of an area image received from the pathological medical terminal 220 is stored.
- a low magnification image table 212 for managing low magnification image data received from the pathologist terminal 220 is stored (see FIG. 7A).
- a high magnification image table 214 for managing the high magnification image data received from the pathologist terminal 220 is stored (see FIG. 7B).
- transmission data 642 including an analysis result to be transmitted to the pathological medical terminal 220 is stored.
- the storage 650 is a mass storage device that stores a database, various parameters, and a program executed by the CPU 610 in a nonvolatile manner.
- the storage 650 stores the following data or programs necessary for realizing the present embodiment.
- a tissue structure analysis DB 651 (see FIG. 8A) used for analyzing whether or not high magnification image data needs to be analyzed by performing ROI tissue structure analysis using low magnification image data. Is done.
- a feature amount analysis DB 652 (see FIG. 8B) used for performing ROI feature amount analysis using high-magnification image data is stored.
- the tissue structure analysis DB 651 and feature amount analysis DB 652 are updated by learning using image data received from the pathologist terminal 220, feedback of analysis results, statistical processing of analysis results, and the like. Is desirable.
- a pathological image diagnosis support program 653 for realizing a series of pathological image diagnosis support is stored as a program (see FIG. 9).
- a tissue structure analysis module 654 for performing a tissue structure analysis of ROI using low-magnification image data using the tissue structure analysis DB 651 constituting a part of the pathological image diagnosis support program 653 is stored.
- a feature amount analysis module 655 for performing feature amount analysis of ROI using high-magnification image data using the feature amount analysis DB 652 constituting a part of the pathological image diagnosis support program 653 is stored.
- an analysis result transmission module 656 for transmitting the analysis result as diagnosis support information to the pathological terminal 220 is stored.
- FIG. 6 shows only data and programs essential for the present embodiment, and general-purpose data and programs such as OS are not shown.
- FIG. 7A is a diagram showing a configuration of the low-magnification image table 212 of FIGS. 2 and 6 for managing low-magnification image data.
- this low-magnification image table 212 it is possible to identify the transmission source that transmitted the low-magnification image data and the ROI without personal information, and it is possible to request transmission of high-magnification image data of the same ROI. All the associations between the low-magnification image data and the personal information are held in the pathological medical terminal 220 and do not go outside.
- the terminal ID 701 of the pathologist terminal 220 which is transmission source identification information of the transmission source that transmitted the ROI low-magnification image data
- the image number which is the image data specifying information assigned by the pathological medical terminal 220 is stored as the received image number 702.
- the most significant bit “0” of the image number 702 represents low-magnification image data, but may be represented by other methods.
- the terminal ID 701 and the received image number 702 can specify which ROI image data of which pathological terminal 220 is a transmission request for high-magnification image data without personal information. Therefore, the terminal ID 701 and the received image number 702 may be used as one number for managing image data.
- the received low-magnification image data 703 is stored.
- the low-magnification image data 703 may store a pointer that points to a storage address stored at another position.
- the body tissue portion 704, the staining method 705, and the sex / age 706 are information for selecting the tissue structure analysis method of the low-magnification image data 703. In addition, if the site
- FIG. 7B is a diagram showing a configuration of the high-magnification image table 214 in FIGS. 2 and 6 for managing the high-magnification image data.
- This high-magnification image table 214 makes it possible to identify the transmission source that sent the high-magnification image data and the ROI without personal information, and to transmit and manage analysis results. All the relations between the high-magnification image data and the personal information are held in the pathological medical terminal 220 and do not go outside.
- the high-magnification image table 214 stores the terminal ID 711 of the pathologist terminal 220 that has transmitted the ROI high-magnification image data. Further, the image number assigned by the pathologist terminal 220 is stored as the received image number 712. Here, the most significant bit “1” of the image number 712 represents high-magnification image data, and the number indicated by the lower bits is the same as the image number 702 in FIG. 7A when the ROI is the same. Managed by.
- the terminal ID 711 and the received image number 712 can identify which ROI image data of which pathological terminal 220 the analysis result of the high magnification image data is based on without personal information.
- the received high-magnification image data 713 is stored. Note that the high-magnification image data 713 may store a pointer that points to a storage address stored at another position.
- the body tissue region 714, the staining method 715, and the gender / age 716 are information for selecting a feature amount analysis method of the high-magnification image data 713. In addition, if the site
- FIG. 8A is a diagram showing a configuration of the tissue structure analysis DB 651 of FIG. Note that the parameters used for the organizational structure analysis and the calculation of each feature amount using the parameters are not the feature parts of the present embodiment but are known, and thus the description thereof is omitted (see Japanese Patent Laid-Open No. 2006-153742). ).
- Reference numerals 801 to 805 are determination conditions that are registered in advance for learning in order to determine the necessity 708 of the high-magnification image from the result 707 of the tissue structure analysis in FIG. 7A.
- the determination conditions are different depending on the characteristics of the tissue specimen image itself such as the analysis target biological tissue region 801, the staining method 802, and the other 803.
- the high magnification image data necessary condition 804 of the tissue structure analysis result is a high magnification image data necessary condition parameter obtained in advance from the tissue structure analysis result.
- a value may be a threshold value or a range.
- Such a determination condition is a condition for determining whether or not there is a suspicion that this ROI has cancer. Even if one of the conditions is satisfied, it is determined that the ROI has a cancer. Sometimes it is judged.
- the feature amount analyzed by the tissue structure analysis will be briefly described in the case of the HE staining method, but is not limited to this description.
- a special feature amount may be used depending on the target organ, but the following feature amount is an important feature in almost any cancer.
- FIG. 8B is a diagram showing a configuration of the feature amount analysis DB 652 of FIG. Note that the parameters used in the feature amount analysis and the calculation of each feature amount using the parameters are not the feature portions of the present embodiment, but are known, and thus the description thereof is omitted (see Japanese Patent Application Laid-Open No. 2006-153742). ).
- Reference numerals 811 to 815 are determination criteria that have been registered in advance for generating the analysis result notification data 718 from the result 717 of the feature amount analysis in FIG. 7B.
- the judgment criteria are different judgment criteria depending on the characteristics of the tissue specimen image itself such as the part 811 of the biological tissue to be analyzed, the staining method 812, and the other 813.
- the cancer cell presence / absence determination criterion 814 is a cancer cell presence / absence determination condition parameter obtained in advance from the characteristic amount analysis result. Such a value may be a threshold value or a range.
- Such a judgment condition is a condition for judging whether this ROI was suspected of having cancer but was a cancer as a conclusion, or whether it was suspected of having cancer but was a benign disease as a conclusion. And, even if one condition is satisfied, it may be determined that the cancer is satisfied, or when a plurality of conditions are satisfied, it may be determined that the cancer is detected.
- the feature amount analyzed by the feature amount analysis will be briefly described in the case of the HE staining method, but is not limited to this description.
- a special feature amount may be used depending on the target organ, but the following feature amount is an important feature in almost any cancer.
- F1-F7 described in FIG. 8B F1) the size of the nucleus, F2) the major and minor axis of the nucleus, F3) Circularity (maximum value 1 if close to a circle, smaller value if the degree of deviation from the circle is larger), F4) Texture, F5) Color (RGB), F6) Color (HSV), F7) Ductal area, There is.
- signet ring a signet ring cell
- signet ring a signet ring cell
- the feature quantities of the same name used in the analysis of the low-magnification image data and the analysis of the high-magnification image data are not the same because the resolutions of the images are different.
- the size of the nucleus is roughly analyzed by extracting a region stained with hematoxin and classifying it into a large nucleus and a small nucleus based on the pixel size.
- the outline of the nucleus is accurately extracted, and the size (or circularity or the like) is calculated based on the outline.
- a gland duct region is extracted by analyzing low-magnification image data to generate a duct mask, and the mask information is directly used as a high-magnification image. Pass to data analysis module. Based on this information, the high-magnification image data analysis module checks whether the gland duct contains the nucleus to be analyzed. If it is contained in the gland duct, Do not judge.
- the relationship between the analysis of the low-magnification image data and the analysis of the high-magnification image data is not a simple primary analysis and a secondary analysis, but will be complicated in the present embodiment, and detailed description thereof will be omitted.
- FIG. 9 is a flowchart showing an operation procedure of the analysis center 210. This flowchart is executed by the CPU 610 in FIG. 6 using the RAM 640, and realizes the function of the analysis center 210 in FIG.
- step S901 an image reception from the pathologist terminal 220 is awaited. If there is image reception, the process proceeds to step S903, and information such as the terminal ID of the transmission source of the received image data, the image number, the region, the staining method, and sex / age is stored and held.
- step S905 the transmitted image data is stored and held.
- it is determined whether the image data received from the image number is low magnification image data or high magnification image data it is determined whether the image data received from the image number is low magnification image data or high magnification image data, and the information stored and held in steps S903 and S905 is stored in the low magnification image table 212 in FIG. 7A. Alternatively, it is stored in the high magnification image table 214 of FIG. 7B.
- step S907 the process branches depending on whether the received image data is low magnification image data or high magnification image data. If the received image data is low-magnification image data, the process advances to step S909 to analyze the tissue structure of the low-magnification image data corresponding to the site, staining method, sex / age, and the like. In the tissue structure analysis performed here, for example, in the case of a HE-stained stomach biological tissue, selection of a cancer candidate region is performed based on a disorder of the shape of a gland duct using a known InfoMax algorithm. Next, in step S911, it is determined whether or not it is necessary to analyze high-magnification image data of the same ROI from the result of the tissue structure analysis. If it is necessary to analyze the high-magnification image of the same ROI, the process proceeds to step 913, and the transmission pathological medical terminal 220 is requested to transmit the high-magnification image data of the same ROI.
- step S915 the process advances to step S915 to perform feature quantity analysis of the high-magnification image data corresponding to the site, staining method, sex / age, and the like.
- the feature amount analysis performed here is, for example, a HE-stained stomach biological tissue, and a size and shape analysis of a cell nucleus using a known SVM algorithm is performed.
- step S917 the feature amount analysis result of the high-magnification image data is transmitted with the image number from the transmission source attached to the pathological medical terminal 220 of the transmission source.
- FIG. 10 is a block diagram illustrating a hardware configuration of the pathological medical terminal 220 according to the present embodiment.
- the pathological medical terminal 220 includes a control unit 221, a scanner 222, and a display 223 as a basic configuration.
- a CPU 1010 is a processor for arithmetic control, and realizes a control unit of the pathologist terminal 220 by executing a program.
- the ROM 1020 stores fixed data and programs such as initial data and programs.
- the communication control unit 1030 controls communication with the analysis center 210 via the network 230. Such communication may be wired or wireless.
- the RAM 1040 is a random access memory used by the CPU 1010 as a temporary storage work area.
- the RAM 1040 has an area for storing data necessary for realizing the present embodiment.
- tissue specimen image read data 1041 read from the pathological slide by the scanner 222 is stored.
- the low magnification image data and the high magnification image data transmitted to the analysis center 210 are managed, and an image identification table 1042 for specifying a patient, a region, an ROI, and the like is stored (see FIG. 11).
- transmission / reception data 1043 transmitted / received to / from the analysis center 210 is stored (see FIG. 11).
- display data 1044 to be displayed on the display 223 of the pathologist terminal 220 is stored.
- the storage 1050 is a mass storage device that stores a database, various parameters, and a program executed by the CPU 1010 in a nonvolatile manner.
- the storage 1050 stores the following data or programs necessary for realizing the present embodiment.
- a tissue specimen image DB 1051 read by the scanner 222 that is accumulated locally by a pathologist is stored.
- a patient history DB 1052 that stores a diagnosis history corresponding to a patient is stored.
- the tissue specimen image DB 1051 and the patient history DB 1052 of the pathologist terminal 220 include the pathologist terminal 220.
- the parameters that can access the information of the analysis center 210 are stored.
- a pathological image diagnosis processing program 1053 including a process for requesting the analysis center 210 for pathological image diagnosis support is stored as a program (see FIG. 12). Further, an ROI selection module 1054 that selects a tissue region and ROI to be diagnosed from a tissue specimen image, which constitutes a part of the pathological image diagnosis processing program 1053, is stored. In addition, a transmission / reception control module 1055 that controls data communication with the analysis center 210 that constitutes a part of the pathological image diagnosis processing program 1053 is stored. Further, an analysis result display module 1056 for superimposing and displaying the analysis result received from the analysis center 210 on the tissue specimen image is stored.
- the input interface 1060 is an interface for inputting control signals and data necessary for control by the CPU 1010.
- image data of a tissue specimen image obtained by reading a pathological slide by the scanner 222 is input.
- the output interface 1070 is an interface that outputs control signals and data to the device under the control of the CPU 1010.
- the tissue specimen image, the diagnosis support request information to the analysis center 210, or the analysis result transmitted from the analysis center 210 is output to the display 223.
- FIG. 10 shows only data and programs essential for the present embodiment, and general-purpose data and programs such as OS are not shown.
- FIG. 11 is a diagram showing the configuration of the image identification table 1042 and transmission / reception data 1043 shown in FIG.
- 1101 is a patient ID for identifying a patient
- 1102 is the sex and age of the patient, and information for identifying the patient. Furthermore, although other specific information such as the patient's address is also stored, FIG. 11 shows only information necessary for the processing of this embodiment.
- 1103 is a region of the tissue specimen image to be analyzed
- 1104 is a staining method of the living tissue, and is information related to the analysis method in the analysis center 210.
- 1105 is a slide ID for specifying a pathological slide
- 1106 is a tissue area ID for specifying a tissue area to be analyzed in a tissue specimen image read by the scanner 222 from the pathological slide
- 1107 is an ROI to be analyzed in the tissue area ROI_ID.
- the position addresses of the upper left and lower right of the rectangle indicating the ROI_ID 1107 in the tissue specimen image are stored in 1108. Note that the position storage data differs depending on the shape of the ROI.
- information related to the analysis method in the analysis center 210 is transmitted to the analysis center 210, but information related to personal information of other patients is transmitted to the analysis center 210.
- the image number 1109 uniquely transmitted by the pathologist terminal 220 not related to the personal information of the patient is assigned to the ROI image specified by the data 1101 to 1108.
- 1110 is ROI low magnification image data specified by the image number 1109 to be transmitted
- 1111 is ROI high magnification image data specified by the image number 1109 to be transmitted.
- the analysis result 1112 reported from the analysis center 210 and the diagnosis result 1113 diagnosed by the pathologist with reference to the analysis result 1112 as support information are stored.
- communication of ROI image data and analysis results between the pathological medical terminal 220 and the analysis center 210 is basically a pathology not related to the patient's personal information. This is performed based on the image information assigned by the medical terminal 220.
- FIG. 12 is a flowchart showing an operation procedure of the pathological medical terminal 220 of the present embodiment. This flowchart is executed by the CPU 1010 in FIG. 10 using the RAM 1040, and realizes the function of the pathologist terminal 220 in FIG.
- step S1201 the pathological slide is read at a resolution corresponding to high magnification by the scanner 222, and the read high magnification image data is stored in step S1203.
- step S1205 the tissue specimen image corresponding to the pathological slide is displayed on the display 223.
- step S1207 a tissue region to be analyzed is selected from the tissue specimen image corresponding to the pathological slide, and an ROI is selected from the tissue region, and an image number is assigned to the ROI image.
- the processing in step S1207 may be automatically performed by the LWA installed in the pathologist terminal 220, or may be performed by a touch panel on a display screen in an interactive manner with the pathologist.
- FIG. 4 shows an example in which a plurality of ROIs selected for the analysis request are displayed superimposed on the selected tissue region as a result of the processing in step S1207.
- step S1209 low-magnification image data of the selected ROI is generated.
- the generation method of the low-magnification image data may be an existing method, and for example, the thinning process is simple.
- the generated low-magnification image data is assigned an assigned image number and transmitted to the analysis center 210.
- the terminal ID for identifying the pathologist terminal 220 and information related to the analysis method of the analysis center 210 are also transmitted together.
- step S1213 it is determined whether or not there is a transmission request for high-magnification image data of the same ROI from the analysis center 210. If there is a transmission request for high-magnification image data, the process advances to step S1215 to store and hold the requested ROI for display of the analysis result. In step S1217, the requested ROI high-magnification image data is transmitted to the analysis center 210 with an image number assigned. On the other hand, if there is no transmission request for high-magnification image data, the process advances to step S1219.
- step S1219 reception of an analysis result from the analysis center 210 is awaited. If the analysis result is received, the process proceeds to step S1221, and the analysis result remains as numerical data (see FIG. 5B), or display data such as the color of the ROI frame is generated from the analysis result (see FIG. 5A). A display screen superimposed on the tissue area is generated. In step S1223, the generated display screen is displayed on the display 223, thereby assisting a pathologist in diagnosis.
- the analysis target of the analysis center 210 is limited to the ROI in one tissue region selected from the tissue specimen image of the pathological slide.
- feature amount analysis is performed by referring to ROIs in other tissue regions of the same pathological slide. According to the present embodiment, even when analysis of only the selected tissue region is not sufficient for diagnosis, it is possible to quickly and accurately receive support from the analysis center for diagnosis based on a tissue specimen image by a pathologist.
- the configuration of the information processing system and analysis center of the third embodiment, and the configuration of the pathological terminal are as follows: Since it is similar to the second embodiment and can be estimated, the description will not be repeated.
- FIG. 13 is a sequence diagram showing an operation sequence 300 of the pathological image diagnosis support system 200 which is the information processing system of this embodiment.
- FIG. 13 operations from reading a pathological slide by the scanner 222 of the pathological medical terminal 220 to analyzing the feature amount of the analysis center 210 will be described. Since the operation after the feature amount analysis (S319 to S323) is the same as that in FIG. 3 of the second embodiment, a description thereof will be omitted.
- step S301 to S315 is the same as that in FIG. 3 of the second embodiment, and it is determined whether high-magnification image data is necessary by tissue structure analysis of the ROI low-magnification image data. Request to 220 to transmit.
- step S1309 an image of another tissue region is analyzed for diagnosis support. Whether or not is necessary.
- the high-magnification image data of one region is sent and analyzed, and if the gun determination is made, the sending of the high-magnification image data is terminated at that time, and the final determination is terminated as a gun.
- the next high-magnification image data is requested and analyzed. If the cancer is denied in the analysis of all eight high-magnification image data, the determination will be benign in the end. If this data transfer method is used, the process ends when it is determined that the cancer has occurred. Therefore, it is not necessary to send all eight high-magnification image data, the data transfer amount is reduced, and the total diagnosis time is shortened. It will be. The effect is the same when the eight regions are within the tissue region requested initially.
- step S317 If there is no analysis of the other tissue region and it is sufficient for the analysis, the process proceeds to step S317, and the feature amount analysis is performed using the high-magnification image data. If analysis of another tissue region is necessary, in step S1311, the analysis center 210 requests an image of the other tissue region from the pathological medical terminal 220. In step S1313, the pathological medical terminal 220 selects another tissue region according to the request, holds the selection information, and selects an ROI from the tissue region. In step S1315, the high magnification image data of the ROI of the other selected tissue region is transmitted to the analysis center 210.
- the analysis center 210 in addition to the analysis of the ROI image data selected first in the feature amount analysis in step S317, the analysis center 210 analyzes the ROI image data of other tissue regions that require additional analysis.
- the analysis result is also displayed on the pathologist terminal 220 as diagnosis support information.
- FIG. 13 the request and transmission of the high-magnification image data of the ROI selected first and the request transmission of the ROI high-magnification image data of other tissue regions that require additional analysis are illustrated as separate processes. You may request and send it.
- the analysis center 210 only notifies the analysis result of the ROI image data sent from the pathological medical terminal 220 as diagnosis support information.
- ROI image data that has been analyzed by the analysis center 210 with diagnosis support so far and diagnosis results by a pathologist referring to the analysis results are accumulated as a case DB, and the case DB is notified when the analysis results are notified. Reference data based on is further notified.
- diagnosis based on tissue specimen images by a pathologist based not only on the judgment of a single pathologist but also on the learning results of the relationship between the tissue specimen images of many pathologists, analysis results, and diagnosis results.
- Analytical center support for can be quickly and accurately received. Furthermore, it becomes possible to refer to the diagnosis cases at any time from the pathological medical terminal 220, and the necessity of managing past diagnostic cases at the pathological medical terminal 220 is reduced.
- FIG. 14 is a block diagram illustrating a configuration of a pathological image diagnosis support system 1400 that is an information processing system according to the present embodiment.
- the same reference number is attached
- subjected to the component which performs the function similar to FIG. 14 differs from FIG. 2 only in the configuration of the analysis center 1410, and the same reference numerals are given to the same functional units.
- the pathological image diagnosis support system 1400 includes an information processing apparatus that functions as an analysis center 1410, an information processing apparatus that functions as a plurality of pathological terminals 220, and a network 230 that connects the analysis center 210 and the plurality of pathological terminals 220. With.
- the analysis center 1410 includes a communication control unit 1415 for communicating with a plurality of pathologist terminals 220 via the network 230. Also, a low-magnification image analysis unit 211 that analyzes a low-magnification area image of one ROI transmitted from the pathological medical terminal 220 and requests transmission of a high-magnification area image of the same ROI if necessary as a result of the analysis. Is provided.
- the low-magnification image analysis unit 211 includes a low-magnification image table 212 that is used for analysis of a low-magnification area image and a transmission request for a high-magnification area image.
- a high-magnification image analysis unit 1413 is provided.
- the high-magnification image analyzing unit 1413 analyzes the high-magnification area image of the same ROI transmitted from the pathological medical terminal 220, and returns the analysis result to the pathological medical terminal 220 as diagnosis support information. At the same time, diagnosis auxiliary information referring to the past area images, analysis results, and diagnosis results accumulated in the diagnosis case DB 1416 is returned to the pathologist terminal 220.
- the high-magnification image analysis unit 1413 includes a high-magnification image table 214 used for analyzing a high-magnification area image and transmitting diagnosis support information.
- diagnosis example DB 1416 accumulates the ROI tissue specimen image, the analysis result, and the diagnosis result in association with each other based on the notification of the diagnosis result referring to the analysis result from each pathological medical terminal 220, and stores the diagnosis auxiliary information. Referenced for generation.
- the configuration of the pathologist terminal 220 is the same as that of the second embodiment, and a description thereof will be omitted.
- FIG. 15 is a sequence diagram showing an operation sequence 1500 of the pathological image diagnosis support system 1400 that is the information processing system of this embodiment.
- the sequence in FIG. 3 (or FIG. 13) is executed before the start or in the central omitted part, but this is not shown and only the characteristic part of this embodiment is shown. That is, before the omitted part at the center, operations from the input of the diagnosis result of the pathologist at the pathological medical terminal 220 to the accumulation of the case in the diagnosis case DB 1416 are shown. Further, the operation after the central omitted portion is the operation from the transmission of the requested ROI high-magnification image data in FIG. 3 to the display of the analysis result and diagnosis holding information on the pathological medical terminal 220.
- the pathologist terminal 220 After displaying the analysis result of FIG. 3 or FIG. 13 (S323), the pathologist terminal 220 waits for input of a diagnosis result referring to the analysis result by the pathologist in step S1501. If a diagnosis result is input, the process proceeds to step S1503, and a treatment method corresponding to the input diagnosis result is transmitted to the analysis center 210 (see FIG. 16). The diagnosis result and the treatment method are transmitted with the terminal ID and an image number for specifying the same ROI image as in FIG. 3 (S1505).
- the analysis center 210 receives the diagnosis result and the treatment method, in step S1507, the ROI image is accumulated in the analysis center 210 as data independent of the transmission source, the patient, and the like. Reassign.
- the reassigned image number is notified to the pathological terminal 220.
- the pathological medical terminal 220 holds the notified reassigned image number in association with personal information such as a patient. By doing so, the analysis center 210 can store and manage data independently of personal information, and the pathological medical terminal 220 can read ROI image data requested by the analysis center when necessary.
- the analysis center 210 stores the received diagnosis result and treatment method in the diagnosis example DB 1416 in association with the reassigned image number, image data, and analysis result.
- the information stored in the diagnosis case DB 1416 does not have to be all information, and information useful for future diagnosis assistance may be selected and stored.
- the analysis center 210 is also used as an information storage server by the pathological terminal 220, all information transmitted from the pathological terminal 220 is stored for diagnosis support.
- step S315 the high-magnification image data is transmitted to the analysis center 210.
- diagnosis auxiliary information is generated in step S1519 with reference to the diagnosis case DB 1416.
- step S1521 the diagnostic auxiliary information is reported to the pathological medical terminal 220 together with the diagnosis result.
- step S1523 the pathologist terminal 220 generates a display image by superimposing the received diagnosis result and diagnosis auxiliary information on the selected tissue region of the tissue specimen image.
- step S1525 display is performed on the display 223 to support pathologist diagnosis (see FIG. 17).
- FIG. 16 is a diagram showing a screen 1600 displayed on the display 223 of the pathologist terminal 220 when the diagnosis result and treatment method by the selected ROI are transmitted to the analysis center 210.
- the screen 1600 displays a plurality of selected ROIs 1601 to 1604 superimposed on the tissue region selected from the tissue specimen image.
- the ROI 1601 indicates a state deleted from the ROI by the pathologist.
- An ROI 1604 indicates a state changed from malignant to benign by a pathologist.
- ROI 1602 and 1603 are the analysis results as they are.
- Reference numeral 1605 in FIG. 16 indicates management information of the displayed tissue specimen image in the pathological medical terminal 220, information for specifying the analysis center 210 that reports the diagnosis result, and the diagnosis result and treatment method by the pathologist. . Among these, personal information such as name is not transmitted to the analysis center 210. Note that the information shown in 1605 is an example, and the present invention is not limited to this.
- FIG. 17 is a diagram showing a screen 1700 in which the analysis result analyzed in the analysis center 210 and the diagnostic auxiliary information are displayed on the display 223 of the pathological medical terminal 220.
- the analysis results of the plurality of ROIs 1701 to 1704 are represented by the difference in the lines of the rectangular frame surrounding the ROI.
- the ROI 1701 indicates an area free from cancer cells that did not need to analyze high-magnification image data by a thin solid line.
- the ROIs 1702 and 1703 indicate areas where the high-magnification image data needs to be analyzed and the cancer cells are clear, with thick solid lines.
- the ROI 1704 indicates that it is an area without cancer cells, although it requires analysis of high-magnification image data by a thick broken line.
- the difference between the lines of the rectangular frame is shown, but other identifiable display such as a difference in color may be used.
- FIG. 17 is management information of the displayed tissue specimen image in the pathologist terminal 220 and information for specifying the analysis center 210 that reports the analysis result of diagnosis support. Among these, personal information such as name is managed by the pathologist terminal 220.
- FIG. 17 displays diagnostic auxiliary information 1706 including information on whether the medical condition is malignant or benign, prediction of future medical history, and auxiliary information on treatment plans.
- the diagnostic auxiliary information 1706 is generated by referring to the diagnostic case DB 1416 from the analysis result of the ROI image data in the analysis center 210.
- the diagnostic auxiliary information 1706 shows information on whether the symptom is malignant or benign, the average survival time, and the treatment plan, but may include the presence or absence of relocation, the recurrence rate, and the like.
- FIG. 18 is a block diagram illustrating a hardware configuration of the analysis center 210 according to the present embodiment. Although FIG. 18 shows a configuration with one device, it may be configured with a plurality of devices according to function. In FIG. 18, the same reference numerals are given to the functional units similar to those in FIG. 6.
- a CPU 610 is a processor for arithmetic control, and realizes a control unit of the analysis center 210 by executing a program.
- the ROM 620 stores fixed data and programs such as initial data and programs.
- the communication control unit 1415 controls communication with a plurality of pathological medical terminals 220 via the network 230.
- the communication control unit 1415 receives the diagnosis result and the treatment method from the pathological medical terminal 220 and transfers them to the diagnosis case DB 1416. Such communication may be wired or wireless.
- the RAM 1840 is a random access memory that the CPU 610 uses as a temporary storage work area.
- the RAM 1840 has an area for storing data necessary for realizing the present embodiment.
- received data 1841 including image data of an area image received from the pathological medical terminal 220 is stored.
- the received data 1841 includes diagnostic results and treatment methods in addition to ROI image data.
- a low magnification image table 212 for managing low magnification image data received from the pathologist terminal 220 is stored (see FIG. 7A).
- a high magnification image table 214 for managing the high magnification image data received from the pathologist terminal 220 is stored (see FIG. 7B).
- transmission data 1842 including an analysis result to be transmitted to the pathological medical terminal 220 is stored.
- the transmission data 1842 includes diagnostic auxiliary information in addition to the analysis result.
- the storage 1850 is a mass storage device that stores a database, various parameters, and a program executed by the CPU 610 in a nonvolatile manner.
- the storage 1850 stores the following data or programs necessary for realizing the present embodiment.
- a tissue structure analysis DB 651 used for performing ROI tissue structure analysis using low-magnification image data is stored.
- a feature amount analysis DB 652 used for performing ROI feature amount analysis using high-magnification image data is stored.
- the storage 1850 stores a diagnosis case DB 1416 for storing diagnosis results and treatment methods in association with ROI image data (see FIG. 19).
- a pathological image diagnosis support program 1853 for realizing a series of pathological image diagnosis support is stored as a program (see FIG. 20).
- a tissue structure analysis module 654 for performing ROI tissue structure analysis using low-magnification image data using the tissue structure analysis DB 651 constituting a part of the pathological image diagnosis support program 1853 is stored.
- the feature amount analysis DB 652 that constitutes a part of the pathological image diagnosis support program 1853 is used to perform ROI feature amount analysis using high-magnification image data, and diagnostic assistance information is generated with reference to the diagnosis example DB 1416.
- a feature amount analysis module 1855 is stored.
- an analysis result transmission module 1856 for transmitting the analysis result and the diagnosis auxiliary information to the pathological medical terminal 220 as diagnosis support information is stored.
- FIG. 18 shows only data and programs essential to the present embodiment, and general-purpose data and programs such as OS are not shown.
- FIG. 19 is a diagram illustrating a configuration of data stored in the diagnosis case DB 1416.
- the diagnosis example DB 1416 is managed by image numbers uniquely reassigned by the analysis center 210, and is completely independent from personal information such as a patient and a transmission source, and is managed for each ROI. Since the reassigned image number is notified only to the pathological medical terminal 220 of the transmission source, there is no external leakage of personal information, and access from the transmission source is possible at any time.
- the diagnosis case DB 1416 is managed by the reassigned image number 1901.
- ROI high-magnification image data 1902 is stored.
- the high-magnification image data 1902 may store a pointer that points to a storage address stored in another position.
- image link information 1903 and storage date 1904 are stored so that it can be seen that the symptoms of the same patient are changing.
- a part 1905 of a biological tissue related to an analysis method and a diagnostic method, a staining method 1906, and a sex / age 1907 are stored.
- the analysis result 1908 from the image data in the analysis center 210 and the diagnosis result 1909 and the treatment method 1910 diagnosed by the pathologist of the transmission source are stored using the analysis result 1908 as support information.
- FIG. 20 is a flowchart showing an operation procedure of the analysis center 210. This flowchart is executed by the CPU 610 of FIG. 18 using the RAM 640, and realizes the function of the analysis center 210 of FIG. The same steps as those in FIG. 9 are denoted by the same reference numerals.
- step S901 reception of an image from the pathologist terminal 220 is awaited. If an image has been received, the process proceeds to step S903, and information such as the terminal ID, image number, region, staining method, gender / age, etc., of the transmission source of the received image data is stored and held.
- step S905 the transmitted image data is stored and held.
- it is determined whether the image data received from the image number is low magnification image data or high magnification image data it is determined whether the image data received from the image number is low magnification image data or high magnification image data, and the information stored and held in steps S903 and S905 is stored in the low magnification image table 212 in FIG. 7A. Alternatively, it is stored in the high magnification image table 214 of FIG. 7B.
- step S2001 it is determined in step S2001 whether the diagnosis result and the treatment method are received. If the diagnosis result and the treatment method are received, the process proceeds to step S2003, and an image number unique to the analysis center 210 is reassigned. In step S2005, the reassigned image number is notified only to the pathological medical terminal 220 that is the transmission source. In step S2007, the diagnosis result and the treatment method are added to the image data and analysis result of each ROI and recorded in the diagnosis case DB 1416.
- step S907 the process branches depending on whether the received image data is low magnification image data or high magnification image data. If the received image data is low-magnification image data, the process proceeds to step S2009, and the tissue structure analysis of the low-magnification image data corresponding to the site, staining method, sex / age, etc. is performed. Although not described in detail, the information in the diagnosis case DB 1416 can be used for the tissue structure analysis performed in step S2009.
- step S911 it is determined whether it is necessary to analyze a high-magnification image of the same ROI from the result of the tissue structure analysis. If it is necessary to analyze the high-magnification image of the same ROI, the process proceeds to step 913, and the transmission pathological medical terminal 220 is requested to transmit the high-magnification image data of the same ROI.
- step S2015 if the received image data is high-magnification image data, the process proceeds to step S2015, and feature quantity analysis of the high-magnification image data corresponding to the site, staining method, sex / age, and the like is performed.
- diagnosis auxiliary information is generated with reference to the diagnosis case DB 1416.
- step S2019 the characteristic amount analysis result of the high-magnification image data and the diagnostic auxiliary information are transmitted with the image number from the transmission source attached to the pathological medical terminal 220 of the transmission source.
- FIG. 21 is a diagram showing a configuration of the patient history DB 1052 shown in FIG.
- reference numeral 2101 denotes a patient ID for specifying a patient
- 2102 denotes the sex and age of the patient, which is information for specifying the patient.
- FIG. 21 shows only information necessary for the processing of this embodiment.
- Reference numeral 2103 denotes a region of the tissue specimen image to be analyzed
- 2104 denotes a staining method of the living tissue, which is information related to the analysis method in the analysis center 210.
- Reference numeral 2105 denotes an examination date and time when a target tissue specimen image is obtained.
- the analysis result 2106 from the analysis center 210, the diagnosis auxiliary information 2107 from the analysis center 210, and the diagnosis result 2108 by the pathologist, which are information as the results of the examination, are stored for each examination.
- 21 shows the information for specifying the image data.
- 2111 is a slide ID for specifying a pathological slide
- 2112 is an analysis tissue area indicating a tissue area to be analyzed in a tissue specimen image read from the pathology slide by the scanner 222
- 2113 is an analysis indicating an ROI to be analyzed in the tissue area The target ROI.
- the reassigned image number 2114 is registered for the image data stored in the diagnosis case DB 1416 of the analysis center 210. Therefore, the image data without the reassigned image number 2114 is not stored in the diagnosis case DB 1416 of the analysis center 210.
- the presence / absence of the reassigned image number 2114 also serves as a barometer indicating whether or not the image has been used for diagnosis.
- Information specifying image data is registered as 2110 and 2120 corresponding to each examination.
- FIG. 22 is a flowchart showing an operation procedure of the pathological medical terminal 220 of the present embodiment. This flowchart is executed by the CPU 1010 of FIG. 10 using the RAM 1040, and realizes the function of the pathologist terminal 220 of FIG. Note that steps S1201 to S1217 in FIG. 22 are the same as those in FIG.
- step S2219 reception of analysis results and diagnostic auxiliary information is awaited. If the analysis result and the diagnosis auxiliary information are received, the process proceeds to step S2221, and the display result is generated by superimposing the analysis result and the diagnosis auxiliary information on the tissue region. In step S2223, a superimposed image is displayed (see FIG. 17).
- step S2225 input of a diagnosis result by a pathologist is awaited. If a diagnostic result is input by the pathologist, the process proceeds to step S2227, and the diagnostic result is transmitted to the analysis center 210.
- step S2229 the reassigned image number is received from the analysis center 210 and recorded in the patient history DB 1052 of FIG. As described above, if information related to diagnosis is stored in the analysis center 210 including image data, the accumulated data in the pathological medical terminal 220 is reduced (see FIG. 21).
- the ROI image data is transmitted from the pathologist terminal 220 to the analysis center 210 without passing through the diagnosis of the pathologist.
- processing for requesting diagnosis support from the analysis center 210 for a tissue specimen image that is difficult to diagnose even when a pathologist makes a diagnosis locally or remotely will be described.
- diagnosis support is requested only when diagnosis by a pathologist is difficult without providing diagnosis support for all tissue specimen images. Therefore, tissue by a pathologist is reduced while reducing the load on the analysis center 210.
- the analysis center's support for diagnosis based on specimen images can be received quickly and accurately.
- the configuration of the information processing system and analysis center of the fifth embodiment, and the configuration of the pathological terminal are as follows: Since it is similar to the fourth embodiment and can be estimated, the description will not be repeated.
- FIG. 23 is a sequence diagram showing an operation sequence 2300 of the pathological image diagnosis support system 1400 that is the information processing system of this embodiment.
- step S2301 a pathology slide is read by the scanner 222, and in step S2303, a pathologist's diagnosis process is performed locally or remotely. In step S2305, it is determined whether diagnosis is difficult. If the diagnosis is difficult, the diagnosis result is notified to the patient.
- step S2307 the ROI of the tissue area for which analysis is requested for diagnosis support is selected.
- the selection of the ROI in this case is a selection of a place that is difficult to judge in diagnosis.
- step S2309 the high-magnification image data of the selected ROI is transmitted to the analysis center 210, and the analysis is requested.
- the processing from the analysis process (S1517) of the analysis center 210 to the display (S1525) on the display 223 of the pathologist terminal 220 is the same as in FIG. Even in the case of an analysis request for a place where it is difficult to make a determination to the analysis center 210, the processing of sending low-magnification image data according to the present embodiment and sending high-magnification image data may be applied if necessary.
- the present invention can be further applied to the case of determining positive / negative of a cancer region from a tissue specimen image immunostained by the IHC method.
- the ratio of nuclei stained brown, the ratio of nuclei not stained (blue nuclei), the whole circumference of the film (whether the film is all dyed), etc. are used as characteristic quantities.
- the IHC method determines whether ER / PR or Her2 is positive or negative at a fixed magnification (for example, 20X) for a region known to be cancer, and selects a treatment method based on this result.
- a fixed magnification for example, 20X
- the 20X image of the tissue specimen image stained by the IHC method which is made from continuous sections of the cancer area detected from the tissue specimen image of the HE method, is analyzed.
- a process for sending to the center 210 and receiving a negative / positive result is also conceivable.
- the present invention may be applied to a system composed of a plurality of devices, or may be applied to a single device. Furthermore, the present invention can also be applied to a case where a control program that realizes the functions of the embodiments is supplied directly or remotely to a system or apparatus. Therefore, in order to realize the functions of the present invention with a computer, a control program installed in the computer, a medium storing the control program, and a WWW (World Wide Web) server that downloads the control program are also included in the scope of the present invention. include.
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Epidemiology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Biological Materials (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
Description
生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理装置であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを受信する第1受信手段と、
前記第1受信手段が受信した前記倍率のより低い画像データに基づいて、前記エリア画像を解析して第1特徴情報を生成する第1解析手段と、
前記第1解析手段が生成した第1特徴情報に基づいて、前記エリア画像に対して、倍率のより高い画像データに基づく解析が必要か否かを判定する判定手段と、
前記判定手段が前記倍率のより高い画像データに基づく解析が必要と判定した場合、前記エリア画像に対する前記倍率のより高い画像データの送信要求を通知する通知手段と、
前記通知手段による送信要求に応答して送信された前記倍率のより高い画像データを受信する第2受信手段と、
前記第2受信手段が受信した前記倍率のより高い画像データに基づいて、前記エリア画像を解析して第2特徴情報を生成する第2解析手段と、
前記第2解析手段が生成した前記第2特徴情報を送信する送信手段と、
を備えることを特徴とする。
生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理装置の制御方法であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを受信する第1受信ステップと、
前記第1受信ステップにおいて受信した前記倍率のより低い画像データに基づいて、前記エリア画像を解析して第1特徴情報を生成する第1解析ステップと、
前記第1解析ステップにおいて生成した第1特徴情報に基づいて、前記エリア画像に対して、倍率のより高い画像データに基づく解析が必要か否かを判定する判定ステップと、
前記判定ステップにおいて前記倍率のより高い画像データに基づく解析が必要と判定した場合、前記エリア画像に対する前記倍率のより高い画像データの送信要求を通知する通知ステップと、
前記通知ステップにおける送信要求に応答して送信された前記倍率のより高い画像データを受信する第2受信ステップと、
前記第2受信ステップにおいて受信した前記倍率のより高い画像データに基づいて、前記エリア画像を解析して第2特徴情報を生成する第2解析ステップと、
前記第2解析ステップにおいて生成した前記第2特徴情報を送信する送信ステップと、
を含むことを特徴とする。
生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理装置の制御プログラムを格納した記憶媒体であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを受信する第1受信ステップと、
前記第1受信ステップにおいて受信した前記倍率のより低い画像データに基づいて、前記エリア画像を解析して第1特徴情報を生成する第1解析ステップと、
前記第1解析ステップにおいて生成した第1特徴情報に基づいて、前記エリア画像に対して、倍率のより高い画像データに基づく解析が必要か否かを判定する判定ステップと、
前記判定ステップにおいて前記倍率のより高い画像データに基づく解析が必要と判定した場合、前記エリア画像に対する前記倍率のより高い画像データの送信要求を通知する通知ステップと、
前記通知ステップにおける送信要求に応答して送信された前記倍率のより高い画像データを受信する第2受信ステップと、
前記第2受信ステップにおいて受信した前記倍率のより高い画像データに基づいて、前記エリア画像を解析して第2特徴情報を生成する第2解析ステップと、
前記第2解析ステップにおいて生成した前記第2特徴情報を送信する送信ステップと、
をコンピュータに実行させる制御プログラムを格納したことを特徴とする。
生体組織を染色して撮像した組織標本画像に基づく診断の支援を依頼する情報処理装置であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを、前記情報処理装置を特定する送信元特定情報と前記画像データを特定する画像データ特定情報とに対応付けて送信する第1送信手段と、
前記異なる倍率で得られる複数の画像データのうち、倍率のより高い画像データの送信要求の通知に応答して、前記エリア画像に対する前記倍率のより高い画像データを前記送信元特定情報と前記画像データ特定情報とに対応付けて送信する第2送信手段と、
前記画像データ特定情報に対応付けられた前記エリア画像の特徴量情報を受信する受信手段と、
前記エリア画像に対する前記送信要求の通知の有無と、前記エリア画像の前記特徴量情報とを、前記組織標本画像に重畳して識別可能に表示する表示手段と、
を備えることを特徴とする。
生体組織を染色して撮像した組織標本画像に基づく診断の支援を依頼する情報処理装置の制御方法であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを、前記情報処理装置を特定する送信元特定情報と前記画像データを特定する画像データ特定情報とに対応付けて送信する第1送信ステップと、
前記異なる倍率で得られる複数の画像データのうち、倍率のより高い画像データの送信要求の通知に応答して、前記エリア画像に対する前記倍率のより高い画像データを前記送信元特定情報と前記画像データ特定情報とに対応付けて送信する第2送信ステップと、
前記画像データ特定情報に対応付けられた前記エリア画像の特徴量情報を受信する受信ステップと、
前記エリア画像に対する前記送信要求の通知の有無と、前記エリア画像の前記特徴量情報とを、前記組織標本画像に重畳して識別可能に表示する表示ステップと、
を含むことを特徴とする。
生体組織を染色して撮像した組織標本画像に基づく診断の支援を依頼する情報処理装置の制御プログラムを格納した記憶媒体であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを、前記情報処理装置を特定する送信元特定情報と前記画像データを特定する画像データ特定情報とに対応付けて送信する第1送信ステップと、
前記異なる倍率で得られる複数の画像データのうち、倍率のより高い画像データの送信要求の通知に応答して、前記エリア画像に対する前記倍率のより高い画像データを前記送信元特定情報と前記画像データ特定情報とに対応付けて送信する第2送信ステップと、
前記画像データ特定情報に対応付けられた前記エリア画像の特徴量情報を受信する受信ステップと、
前記エリア画像に対する前記送信要求の通知の有無と、前記エリア画像の前記特徴量情報とを、前記組織標本画像に重畳して識別可能に表示する表示ステップと、
をコンピュータに実行させる制御プログラムを格納したことを特徴とする。
生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理システムであって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを解析して、前記エリア画像の第1特徴情報を生成する第1解析手段と、
前記第1解析手段が生成した第1特徴情報に基づいて、前記エリア画像に対する倍率のより高い画像データの解析が必要か否かを判定する判定手段と、
前記判定手段が前記倍率のより高い画像データの解析が必要と判定した場合に、前記倍率のより高い画像データに基づいて前記エリア画像を解析して第2特徴情報を生成する第2解析手段と、
前記判定手段による判定の結果と、前記第2解析手段が生成した前記第2特徴情報とを、識別可能に表示する表示手段と、
を備えることを特徴とする。
生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理方法であって、
前記組織標本画像内の選択されたエリアのエリア画像について、前記エリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを解析して、前記エリア画像の第1特徴情報を生成する第1解析ステップと、
前記第1解析ステップにおいて生成した第1特徴情報に基づいて、前記エリア画像に対する倍率のより高い画像データの解析が必要か否かを判定する判定ステップと、
前記判定ステップにおいて前記倍率のより高い画像データの解析が必要と判定した場合に、前記倍率のより高い画像データに基づいて前記エリア画像を解析して第2特徴情報を生成する第2解析ステップと、
前記判定ステップによる判定の結果と、前記第2解析ステップにおいて生成した前記第2特徴情報とを、識別可能に表示する表示ステップと、
を含むことを特徴とする。
本発明の第1実施形態としての情報処理装置100について、図1を用いて説明する。図1の情報処理装置100は、生体組織を染色して撮像した組織標本画像に基づく診断を支援する装置である。図1に示すように、情報処理装置100は、第1受信部101と、第1解析部102と、判定部103と、通知部104と、第2受信部105と、第2解析部106と、送信部107と、を含む。
第2実施形態は、ネットワークを介して複数の病理医用端末と解析センターとが接続し、解析センターが病理医用端末から送信された組織標本画像を解析して診断を支援する病理画像診断支援システムである。病理医用端末からはまず選択されたエリアの低倍率のエリア画像が送信される。解析センターは、この低倍率のエリア画像を解析して高倍率のエリア画像を解析する必要があるかを判定する。必要であれば、病理医用端末に要求して高倍率のエリア画像を送信させる。解析センターは、高倍率のエリア画像を解析して診断を支援する解析結果を病理医用端末に報知する。本実施形態によれば、病理医による組織標本画像に基づく診断に対する解析センターの支援を迅速に精度良く受けることができる。また、解析センターにおける診断支援サービスをより少ない資源で実現できる。
図2は、本実施形態に係る情報処理システムである病理画像診断支援システム200の構成を示すブロック図である。
図3は、本実施形態の情報処理システムである病理画像診断支援システム200の動作シーケンス300を示すシーケンス図である。図3においては、病理医用端末220のスキャナ222による病理スライドの読み取りから、診断支援情報の画面表示までの動作を説明する。
以下、本実施形態の処理におけるディスプレイ223の表示画面を、図4、図5A、図5Bに従って説明する。
図4は、選択したROIのエリア画像を解析センター210に送信する時点での、病理医用端末220のディスプレイ223に表示された画面400を示す図である。
図5Aは、解析センター210において、低倍率画像データに基づいて解析された解析結果が、病理医用端末220のディスプレイ223に表示された第1画面510を示す図である。
図6は、本実施形態に係る解析センター210のハードウェア構成を示すブロック図である。なお、図6には、1つの装置による構成を示したが、機能別の複数の装置により構成されてもよい。
図7Aは、低倍率画像データを管理するための図2および図6の低倍率画像用テーブル212の構成を示す図である。この低倍率画像用テーブル212により、低倍率画像データを送信した送信元とROIとの特定が個人情報無しに可能となり、同じROIの高倍率画像データの送信要求が可能になる。そして、低倍率画像データと個人情報との関連はすべて病理医用端末220内に保持され、外部に出ることはない。
図7Bは、高倍率画像データを管理するための図2および図6の高倍率画像用テーブル214の構成を示す図である。この高倍率画像用テーブル214により、高倍率画像データを送信した送信元とROIとの特定が個人情報無しに可能となり、解析結果の送信および管理が可能になる。高倍率画像データと個人情報との関連はすべて病理医用端末220内に保持され、外部に出ることはない。
図8Aは、図6の組織構造解析用DB651の構成を示す図である。なお、組織構造解析に使用されるパラメータ類やそれを使った各特徴量の計算などについては、本実施形態の特徴部分ではなく既知であるので、説明は省略する(特開2006-153742号参照)。
f1) 核のサイズ、
f2) 大きい核の密度 = 大きい核の数 / 全核の数、
f3) 腺管に属する核の密度、
f4) 核の向き、
f5) 核の扁平度、
f6) 腺管の厚さ、
f7) 色(RGB)、
f8) 色(HSV)、
f9) 腺管領域、
f10) Gabor関数でフィルタリングした信号(方位特徴、配列)、
がある。
また、大域的特徴としては、上記特徴量に加えて、粘液、脂肪などの領域に関する情報も使う場合がある。特殊な特徴量としては、例えば胃生検では印環細胞(以下、Signet ring)の疑いなどがある。
これらのいずれかの条件、あるいはその組合せがガンである条件を満たせば、高倍率画像の要否805から“要”を、低倍率画像用テーブル212の高倍率画像の要否708にコピーし、高倍率画像データを要求してさらに詳細な特徴量解析をすることになる。
図8Bは、図6の特徴量解析用DB652の構成を示す図である。なお、特徴量解析に使用されるパラメータ類やそれを使った各特徴量の計算などについては、本実施形態の特徴部分ではなく既知であるので、説明は省略する(特開2006-153742号参照)。
F1) 核のサイズ、
F2) 核の長径および短径、
F3) 円形度(円に近ければ最大値1を取り,円から外れている度合いが大きいほど小さい値)、
F4) テクスチャ、
F5) 色(RGB)、
F6) 色(HSV)、
F7) 腺管領域、
がある。
特殊な特徴量としては、例えば、低倍率画像データによる胃生検では印環細胞(以下、Signet ring)の疑いなどがある場合の、高倍率画像データによるSignet ringの有無の確認がある。
これらのいずれかの条件、あるいはその組合せがガンである条件を満たせば、ガン細胞の有無815にコピーし、組織標本画像の送信元に診断支援のため送信される。
また、腺管などの大域的な情報は低倍率でしか得られないため,まず低倍率画像データの解析で腺管領域を抽出して腺管マスクを生成し、そのマスク情報をそのまま高倍率画像データの解析モジュールに渡す。高倍率画像データの解析モジュールはこの情報に基づいて、解析対象である核が腺管に含まれているかどうかを確認して、もし腺管に含まれているならばたとえサイズが大きくてもガンとは判定しないようにする。
これら低倍率画像データの解析と高倍率画像データの解析との関係は単純な一次解析と二次解析ではないが、本実施形態においては煩雑になるので詳細な説明は省略する。
図9は、解析センター210の動作手順を示すフローチャートである。このフローチャートは、図6のCPU610がRAM640を使用しながら実行して、図2の解析センター210の機能を実現する。
図10は、本実施形態に係る病理医用端末220のハードウェア構成を示すブロック図である。図2に示したように、病理医用端末220は、基本的構成として、制御部221と、スキャナ222と、ディスプレイ223とを有している。
図11は、図10に示した画像識別テーブル1042および送受信データ1043の構成を示す図である。
図12は、本実施形態の病理医用端末220の動作手順を示すフローチャートである。このフローチャートは、図10のCPU1010がRAM1040を使用しながら実行して、図2の病理医用端末220の機能を実現する。
第2実施形態において、解析センター210の解析対象は、病理スライドの組織標本画像から選択された1つの組織領域内のROIに限定されていた。本実施形態では、同じ病理スライドの他の組織領域内のROIについても参照することで、特徴量解析を行なう。本実施形態によれば、選択された組織領域のみの分析では診断に十分でない場合も、病理医による組織標本画像に基づく診断に対する解析センターの支援を迅速に精度良く受けることができる。
第2実施形態と類似であり、推定できる範囲であるので、説明の繰り返しは省略する。
図13は、本実施形態の情報処理システムである病理画像診断支援システム200の動作シーケンス300を示すシーケンス図である。図13においては、病理医用端末220のスキャナ222による病理スライドの読み取りから、解析センター210の特徴量解析までの動作を説明する。特徴量解析後の動作(S319~S323)は第2実施形態の図3と同様であるので省略する。
かかる他の組織領域の画像の解析を遠隔で行なう場合には、8個の領域すべてをネットワークを介して送ることは効率が悪いので、例えば次のような処理を行うのが望ましい。まず、1つ領域の高倍率画像データを送って解析し、ガン判定がでればその時点で高倍率画像データを送るのは終了し、最終判定をガンとして終了する。一方、高倍率画像データの解析でガンでないと判定されれば、次の高倍率画像データを要求して解析をするように続けていく。もし8個すべての高倍率画像データの解析でガンが否定されれば,最終的に判定は良性となる。このデータ転送方式とすれば、ガンと判定した時点で処理は終了となるため、8個すべての高倍率画像データを送らなくともよく、データの転送量が小さくなりトータルの診断時間が短縮されることになる。8個の領域が初期に依頼した組織領域内にある場合も、その効果は同様である。
第2および第3実施形態では、解析センター210は、病理医用端末220から送られたROIの画像データの解析結果を診断支援情報として報知するのみであった。本実施形態においては、解析センター210が今まで診断支援で解析してきたROIの画像データと、解析結果を参照した病理医による診断結果とを、事例DBとして蓄積し、解析結果の報知時に事例DBに基づく参考データをさらに報知する。本実施形態によれば、一人の病理医の判断のみでなく、多数の病理医の組織標本画像と解析結果と診断結果との関係の学習結果を踏まえて、病理医による組織標本画像に基づく診断に対する解析センターの支援を迅速に精度良く受けることができる。さらに、病理医用端末220からいつでも診断事例を参照可能となり、病理医用端末220において過去の診断事例を管理する必要が低減する。
図14は、本実施形態に係る情報処理システムである病理画像診断支援システム1400の構成を示すブロック図である。なお、図2と同様の機能を果たす構成部には、同じ参照番号を付している。図14の図2との相違は、解析センター1410の構成のみであり、同様の機能部には同じ参照番号を付す。
図15は、本実施形態の情報処理システムである病理画像診断支援システム1400の動作シーケンス1500を示すシーケンス図である。図15においては、図3(あるいは図13)におけるシーケンスが開始前あるいは中央の省略部で実行されるが、それは図示せずに本実施形態の特徴部のみを図示している。すなわち、中央の省略部の前は、病理医用端末220における病理医の診断結果の入力から、診断事例DB1416への事例の蓄積までの動作を示す。また、中央の省略部の後は、図3における要求されたROIの高倍率画像データの送信から、解析結果および診断保持情報の病理医用端末220における表示までの動作である。
以下、本実施形態の処理におけるディスプレイ223の表示画面を、図16および図17に従って説明する。
図16は、選択したROIによる診断結果と治療方法とを解析センター210に送信する時点での、病理医用端末220のディスプレイ223に表示された画面1600を示す図である。
図17は、解析センター210において解析された解析結果と診断補助情報とが、病理医用端末220のディスプレイ223に表示された画面1700を示す図である。
図18は、本実施形態に係る解析センター210のハードウェア構成を示すブロック図である。なお、図18には、1つの装置による構成を示したが、機能別の複数の装置により構成されてもよい。なお、図18において、図6と同様の機能部には同じ参照番号が付されている。
図19は、診断事例DB1416に蓄積されるデータの構成を示す図である。この診断事例DB1416は、解析センター210で独自に再割当した画像番号によりデータが管理されており、患者や送信元などの個人情報から完全に独立したデータであり、ROIごとに管理される。そして、再割当した画像番号は、送信元の病理医用端末220のみに通知されるので、個人情報の外部漏れがなく、かつ、送信元からはいつでもアクセスが可能である。
図20は、解析センター210の動作手順を示すフローチャートである。このフローチャートは、図18のCPU610がRAM640を使用しながら実行して、図14の解析センター210の機能を実現する。なお、図9と同様のステップには同じ参照番号が付されている。
病理医用端末のハードウェア構成は、図10と基本的には同様であるので、重複説明は避ける。
図21は、図10に示した患者履歴DB1052の構成を示す図である。
図22は、本実施形態の病理医用端末220の動作手順を示すフローチャートである。このフローチャートは、図10のCPU1010がRAM1040を使用しながら実行して、図14の病理医用端末220の機能を実現する。なお、図22のステップS1201からS1217までは、図12と同様であるので、説明は省略する。
第2乃至第5実施形態においては、病理医の診断を経ずに、ROIの画像データを病理医用端末220から解析センター210に送信していた。本実施形態では、病理医がローカルであるいはリモートで診断をしても診断が難しい組織標本画像について、解析センター210に診断支援を依頼する処理を説明する。本実施形態によれば、すべての組織標本画像について診断支援をせずに、病理医による診断が難しい場合のみに診断支援を依頼するので、解析センター210の負荷を低減しながら、病理医による組織標本画像に基づく診断に対する解析センターの支援を迅速に精度良く受けることができる。
第4実施形態と類似であり、推定できる範囲であるので、説明の繰り返しは省略する。
図23は、本実施形態の情報処理システムである病理画像診断支援システム1400の動作シーケンス2300を示すシーケンス図である。
なお、上記実施形態では、染色法としてHE法を使った組織標本画像からガンを検出する場合を主に説明した。しかしながら、IHC法で免疫染色した組織標本画像からガン領域の陽性/陰性を判定する場合にさらに適用が可能である。例えば、乳腺のIHC法に関しては、茶色に染まった核の割合、染まらなかった核(青い核)の割合、膜の全周性(膜がすべて染まっているかどうか)などを特徴量とする。そして、IHC法は、ガンであることが分かっている領域に対して固定倍率(例えば、20X)でER/PR,あるいはHer2陽性か陰性かを判断し、この結果を受けて治療法を選択する。かかるIHC法による組織標本画像の解析を遠隔で行なう場合には、HE法の組織標本画像から検出したガン領域に対して連続切片で作った、IHC法で染色した組織標本画像の20X画像を解析センター210に送信して、陰性/陽性の結果を受け取る処理も考えられる。
Claims (19)
- 生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理装置であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを受信する第1受信手段と、
前記第1受信手段が受信した前記倍率のより低い画像データに基づいて、前記エリア画像を解析して第1特徴情報を生成する第1解析手段と、
前記第1解析手段が生成した第1特徴情報に基づいて、前記エリア画像に対して、倍率のより高い画像データに基づく解析が必要か否かを判定する判定手段と、
前記判定手段が前記倍率のより高い画像データに基づく解析が必要と判定した場合、前記エリア画像に対する前記倍率のより高い画像データの送信要求を通知する通知手段と、
前記通知手段による送信要求に応答して送信された前記倍率のより高い画像データを受信する第2受信手段と、
前記第2受信手段が受信した前記倍率のより高い画像データに基づいて、前記エリア画像を解析して第2特徴情報を生成する第2解析手段と、
前記第2解析手段が生成した前記第2特徴情報を送信する送信手段と、
を備えることを特徴とする情報処理装置。 - 前記エリア画像の画像データを、前記画像データの送信元を特定する送信元特定情報と前記画像データを特定する画像データ特定情報とに対応付けて管理する管理手段をさらに備え、
前記第1および第2受信手段は、前記エリア画像の画像データを前記送信元特定情報および前記画像データ特定情報と共に受信し、
前記通知手段は、前記倍率のより高い画像データの送信要求を前記送信元特定情報および前記画像データ特定情報と共に通知し、
前記送信手段は、前記第2解析手段が生成した前記第2特徴情報を前記送信元特定情報および前記画像データ特定情報と共に送信することを特徴とする請求項1に記載の情報処理装置。 - 前記画像データ特定情報は前記組織標本画像の生体における部位を特定する情報を含み、
前記第1および第2解析手段による解析と前記判定手段による判定とは、それぞれ前記組織標本画像の生体における部位に対応する解析と判定とであることを特徴とする請求項2に記載の情報処理装置。 - 前記画像データ特定情報は前記組織標本画像の染色法を特定する情報を含み、
前記第1および第2解析手段による解析と前記判定手段による判定とは、それぞれ前記組織標本画像の染色法に対応する解析と判定とであることを特徴とする請求項2または3に記載の情報処理装置。 - 前記染色法は、HE法を含むことを特徴とする請求項4に記載の情報処理装置。
- 前記第1解析手段が生成する第1特徴情報は、前記エリア画像における染色された組織構造を含むことを特徴とする請求項1乃至5のいずれか1項に記載の情報処理装置。
- 前記組織構造は、腺管の形状を含むことを特徴とする請求項6に記載の情報処理装置。
- 前記判定手段は、前記エリア画像における染色された組織構造がガン細胞候補と判断される場合に、前記エリア画像について、前記倍率のより高い画像データに基づく解析が必要であると判定することを特徴とする請求項6または7に記載の情報処理装置。
- 前記第2解析手段が生成する前記第2特徴情報は、前記エリア画像における染色された細胞に関する特徴量を含むことを特徴とする請求項1乃至8のいずれか1項に記載の情報処理装置。
- 前記特徴量は、平均核サイズ、平均異形度、テクスチャを含むことを特徴とする請求項9に記載の情報処理装置。
- 前記エリア画像の画像データに対応付けた診断結果を受信する第3受信手段と、
前記エリア画像の画像データを、前記第3受信手段が受信した前記診断結果に対応付けて診断事例として蓄積する蓄積手段と、
前記第2受信手段が受信した前記エリア画像の画像データから、前記蓄積手段に蓄積された画像データを参照して診断補助情報を生成する生成手段と、
をさらに備え、
前記送信手段は、さらに、前記生成手段により生成された診断補助情報を送信することを特徴とする請求項1乃至10のいずれか1項に記載の情報処理装置。 - 前記生成手段による診断補助情報は、病状が悪性か良性かの情報と、平均生存期間と、移転の有無と、再発率と、治療計画の補助情報との少なくともいずれかを含むことを特徴とする請求項11に記載の情報処理装置。
- 生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理装置の制御方法であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを受信する第1受信ステップと、
前記第1受信ステップにおいて受信した前記倍率のより低い画像データに基づいて、前記エリア画像を解析して第1特徴情報を生成する第1解析ステップと、
前記第1解析ステップにおいて生成した第1特徴情報に基づいて、前記エリア画像に対して、倍率のより高い画像データに基づく解析が必要か否かを判定する判定ステップと、
前記判定ステップにおいて前記倍率のより高い画像データに基づく解析が必要と判定した場合、前記エリア画像に対する前記倍率のより高い画像データの送信要求を通知する通知ステップと、
前記通知ステップにおける送信要求に応答して送信された前記倍率のより高い画像データを受信する第2受信ステップと、
前記第2受信ステップにおいて受信した前記倍率のより高い画像データに基づいて、前記エリア画像を解析して第2特徴情報を生成する第2解析ステップと、
前記第2解析ステップにおいて生成した前記第2特徴情報を送信する送信ステップと、
を含むことを特徴とする情報処理装置の制御方法。 - 生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理装置の制御プログラムを格納した記憶媒体であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを受信する第1受信ステップと、
前記第1受信ステップにおいて受信した前記倍率のより低い画像データに基づいて、前記エリア画像を解析して第1特徴情報を生成する第1解析ステップと、
前記第1解析ステップにおいて生成した第1特徴情報に基づいて、前記エリア画像に対して、倍率のより高い画像データに基づく解析が必要か否かを判定する判定ステップと、
前記判定ステップにおいて前記倍率のより高い画像データに基づく解析が必要と判定した場合、前記エリア画像に対する前記倍率のより高い画像データの送信要求を通知する通知ステップと、
前記通知ステップにおける送信要求に応答して送信された前記倍率のより高い画像データを受信する第2受信ステップと、
前記第2受信ステップにおいて受信した前記倍率のより高い画像データに基づいて、前記エリア画像を解析して第2特徴情報を生成する第2解析ステップと、
前記第2解析ステップにおいて生成した前記第2特徴情報を送信する送信ステップと、
をコンピュータに実行させる制御プログラムを格納したことを特徴とする記憶媒体。 - 生体組織を染色して撮像した組織標本画像に基づく診断の支援を依頼する情報処理装置であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを、前記情報処理装置を特定する送信元特定情報と前記画像データを特定する画像データ特定情報とに対応付けて送信する第1送信手段と、
前記異なる倍率で得られる複数の画像データのうち、倍率のより高い画像データの送信要求の通知に応答して、前記エリア画像に対する前記倍率のより高い画像データを前記送信元特定情報と前記画像データ特定情報とに対応付けて送信する第2送信手段と、
前記画像データ特定情報に対応付けられた前記エリア画像の特徴量情報を受信する受信手段と、
前記エリア画像に対する前記送信要求の通知の有無と、前記エリア画像の前記特徴量情報とを、前記組織標本画像に重畳して識別可能に表示する表示手段と、
を備えることを特徴とする情報処理装置。 - 生体組織を染色して撮像した組織標本画像に基づく診断の支援を依頼する情報処理装置の制御方法であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを、前記情報処理装置を特定する送信元特定情報と前記画像データを特定する画像データ特定情報とに対応付けて送信する第1送信ステップと、
前記異なる倍率で得られる複数の画像データのうち、倍率のより高い画像データの送信要求の通知に応答して、前記エリア画像に対する前記倍率のより高い画像データを前記送信元特定情報と前記画像データ特定情報とに対応付けて送信する第2送信ステップと、
前記画像データ特定情報に対応付けられた前記エリア画像の特徴量情報を受信する受信ステップと、
前記エリア画像に対する前記送信要求の通知の有無と、前記エリア画像の前記特徴量情報とを、前記組織標本画像に重畳して識別可能に表示する表示ステップと、
を含むことを特徴とする情報処理装置の制御方法。 - 生体組織を染色して撮像した組織標本画像に基づく診断の支援を依頼する情報処理装置の制御プログラムを格納した記憶媒体であって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを、前記情報処理装置を特定する送信元特定情報と前記画像データを特定する画像データ特定情報とに対応付けて送信する第1送信ステップと、
前記異なる倍率で得られる複数の画像データのうち、倍率のより高い画像データの送信要求の通知に応答して、前記エリア画像に対する前記倍率のより高い画像データを前記送信元特定情報と前記画像データ特定情報とに対応付けて送信する第2送信ステップと、
前記画像データ特定情報に対応付けられた前記エリア画像の特徴量情報を受信する受信ステップと、
前記エリア画像に対する前記送信要求の通知の有無と、前記エリア画像の前記特徴量情報とを、前記組織標本画像に重畳して識別可能に表示する表示ステップと、
をコンピュータに実行させる制御プログラムを格納したことを特徴とする記憶媒体。 - 生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理システムであって、
前記組織標本画像内の選択されたエリアのエリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを解析して、前記エリア画像の第1特徴情報を生成する第1解析手段と、
前記第1解析手段が生成した第1特徴情報に基づいて、前記エリア画像に対する倍率のより高い画像データの解析が必要か否かを判定する判定手段と、
前記判定手段が前記倍率のより高い画像データの解析が必要と判定した場合に、前記倍率のより高い画像データに基づいて前記エリア画像を解析して第2特徴情報を生成する第2解析手段と、
前記判定手段による判定の結果と、前記第2解析手段が生成した前記第2特徴情報とを、識別可能に表示する表示手段と、
を備えることを特徴とする情報処理システム。 - 生体組織を染色して撮像した組織標本画像に基づく診断を支援する情報処理方法であって、
前記組織標本画像内の選択されたエリアのエリア画像について、前記エリア画像に対して異なる倍率で得られる複数の画像データのうち、倍率のより低い画像データを解析して、前記エリア画像の第1特徴情報を生成する第1解析ステップと、
前記第1解析ステップにおいて生成した第1特徴情報に基づいて、前記エリア画像に対する倍率のより高い画像データの解析が必要か否かを判定する判定ステップと、
前記判定ステップにおいて前記倍率のより高い画像データの解析が必要と判定した場合に、前記倍率のより高い画像データに基づいて前記エリア画像を解析して第2特徴情報を生成する第2解析ステップと、
前記判定ステップによる判定の結果と、前記第2解析ステップにおいて生成した前記第2特徴情報とを、識別可能に表示する表示ステップと、
を含むことを特徴とする情報処理方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012554708A JP5716753B2 (ja) | 2011-01-24 | 2012-01-10 | 情報処理システム、情報処理方法、情報処理装置およびその制御方法とその制御プログラム |
US13/981,275 US9230154B2 (en) | 2011-01-24 | 2012-01-10 | Information processing apparatus, method, and storage medium for assisting with a diagnosis based on a tissue sample |
US14/818,717 US9361508B2 (en) | 2011-01-24 | 2015-08-05 | Information processing system, information processing method, information processing apparatus, control method therefor, and storage medium storing control program therefor |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2011-012425 | 2011-01-24 | ||
JP2011012425 | 2011-01-24 |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/981,275 A-371-Of-International US9230154B2 (en) | 2011-01-24 | 2012-01-10 | Information processing apparatus, method, and storage medium for assisting with a diagnosis based on a tissue sample |
US14/818,717 Division US9361508B2 (en) | 2011-01-24 | 2015-08-05 | Information processing system, information processing method, information processing apparatus, control method therefor, and storage medium storing control program therefor |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2012102069A1 true WO2012102069A1 (ja) | 2012-08-02 |
Family
ID=46580642
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2012/050249 WO2012102069A1 (ja) | 2011-01-24 | 2012-01-10 | 情報処理システム、情報処理方法、情報処理装置およびその制御方法とその制御プログラムを格納した記憶媒体 |
Country Status (3)
Country | Link |
---|---|
US (2) | US9230154B2 (ja) |
JP (1) | JP5716753B2 (ja) |
WO (1) | WO2012102069A1 (ja) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050611A (zh) * | 2013-03-14 | 2014-09-17 | 索尼公司 | 信息处理装置、信息处理方法和程序 |
JP2015038467A (ja) * | 2013-07-18 | 2015-02-26 | パナソニックIpマネジメント株式会社 | 病理診断支援装置及び病理診断支援方法 |
CN107046608A (zh) * | 2016-02-08 | 2017-08-15 | 富士施乐株式会社 | 终端装置、诊断***和诊断方法 |
CN109872782A (zh) * | 2019-02-20 | 2019-06-11 | 程俊美 | 一种用于处理用于组织病理学的组织样本的***及方法 |
WO2019159741A1 (ja) * | 2018-02-19 | 2019-08-22 | 日本メジフィジックス株式会社 | 医用画像検査支援装置及び医用画像検査支援方法 |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012157201A1 (ja) * | 2011-05-18 | 2012-11-22 | 日本電気株式会社 | 情報処理システム、情報処理方法、情報処理装置およびその制御方法と制御プログラム |
US10451554B2 (en) | 2015-02-23 | 2019-10-22 | Konica Minolta, Inc. | Image processing device, image processing method, and recording medium storing computer readable image processing program |
JP6333871B2 (ja) * | 2016-02-25 | 2018-05-30 | ファナック株式会社 | 入力画像から検出した対象物を表示する画像処理装置 |
US11449991B2 (en) * | 2018-03-08 | 2022-09-20 | Konica Minolta, Inc. | Image processing method, image processing apparatus, and storage medium |
JP7431592B2 (ja) * | 2020-01-29 | 2024-02-15 | 株式会社Screenホールディングス | 画像処理装置、画像処理システムおよび画像処理方法 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000287955A (ja) * | 1999-04-03 | 2000-10-17 | Konica Corp | 画像診断支援装置 |
JP2001005950A (ja) * | 1999-06-21 | 2001-01-12 | Fuji Photo Film Co Ltd | 画像サーバ装置および画像転送方法 |
JP2006326287A (ja) * | 2005-04-26 | 2006-12-07 | Toshiba Corp | 医用画像ファイリング装置 |
JP2010097482A (ja) * | 2008-10-17 | 2010-04-30 | Tokyo Institute Of Technology | 画像表示システム、画像情報管理装置、表示制御装置、画像表示制御方法 |
WO2010140588A1 (ja) * | 2009-06-03 | 2010-12-09 | 日本電気株式会社 | 病理画像診断システム、病理画像診断方法、病理画像診断プログラム |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7505614B1 (en) | 2000-04-03 | 2009-03-17 | Carl Zeiss Microimaging Ais, Inc. | Remote interpretation of medical images |
JP4496943B2 (ja) | 2004-11-30 | 2010-07-07 | 日本電気株式会社 | 病理診断支援装置、病理診断支援プログラム、病理診断支援装置の作動方法、及び病理診断支援システム |
JP4591142B2 (ja) * | 2005-03-16 | 2010-12-01 | コニカミノルタエムジー株式会社 | 医用画像システム |
US8140481B2 (en) | 2005-04-26 | 2012-03-20 | Kabushiki Kaisha Toshiba | Medical image filing system and medical image filing method |
-
2012
- 2012-01-10 JP JP2012554708A patent/JP5716753B2/ja active Active
- 2012-01-10 WO PCT/JP2012/050249 patent/WO2012102069A1/ja active Application Filing
- 2012-01-10 US US13/981,275 patent/US9230154B2/en active Active
-
2015
- 2015-08-05 US US14/818,717 patent/US9361508B2/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000287955A (ja) * | 1999-04-03 | 2000-10-17 | Konica Corp | 画像診断支援装置 |
JP2001005950A (ja) * | 1999-06-21 | 2001-01-12 | Fuji Photo Film Co Ltd | 画像サーバ装置および画像転送方法 |
JP2006326287A (ja) * | 2005-04-26 | 2006-12-07 | Toshiba Corp | 医用画像ファイリング装置 |
JP2010097482A (ja) * | 2008-10-17 | 2010-04-30 | Tokyo Institute Of Technology | 画像表示システム、画像情報管理装置、表示制御装置、画像表示制御方法 |
WO2010140588A1 (ja) * | 2009-06-03 | 2010-12-09 | 日本電気株式会社 | 病理画像診断システム、病理画像診断方法、病理画像診断プログラム |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050611A (zh) * | 2013-03-14 | 2014-09-17 | 索尼公司 | 信息处理装置、信息处理方法和程序 |
CN104050611B (zh) * | 2013-03-14 | 2019-01-04 | 索尼公司 | 信息处理装置、信息处理方法和程序 |
JP2015038467A (ja) * | 2013-07-18 | 2015-02-26 | パナソニックIpマネジメント株式会社 | 病理診断支援装置及び病理診断支援方法 |
CN107046608A (zh) * | 2016-02-08 | 2017-08-15 | 富士施乐株式会社 | 终端装置、诊断***和诊断方法 |
JP2017142567A (ja) * | 2016-02-08 | 2017-08-17 | 富士ゼロックス株式会社 | 端末装置、診断システムおよびプログラム |
WO2019159741A1 (ja) * | 2018-02-19 | 2019-08-22 | 日本メジフィジックス株式会社 | 医用画像検査支援装置及び医用画像検査支援方法 |
CN109872782A (zh) * | 2019-02-20 | 2019-06-11 | 程俊美 | 一种用于处理用于组织病理学的组织样本的***及方法 |
Also Published As
Publication number | Publication date |
---|---|
US9230154B2 (en) | 2016-01-05 |
JP5716753B2 (ja) | 2015-05-13 |
JPWO2012102069A1 (ja) | 2014-06-30 |
US20150339514A1 (en) | 2015-11-26 |
US9361508B2 (en) | 2016-06-07 |
US20130301900A1 (en) | 2013-11-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5716753B2 (ja) | 情報処理システム、情報処理方法、情報処理装置およびその制御方法とその制御プログラム | |
US12008764B2 (en) | Systems, devices, and methods for image processing to generate an image having predictive tagging | |
US20220076411A1 (en) | Neural netork based identification of areas of interest in digital pathology images | |
EP2050069B1 (en) | System and method for co-registering multi-channel images of a tissue micro array | |
US10083340B2 (en) | Automated cell segmentation quality control | |
JP2021063819A (ja) | 包括的なマルチアッセイ組織分析のためのシステムおよび方法 | |
US9020304B2 (en) | Method for loading medical image data and device for performing the method | |
US20120327211A1 (en) | Diagnostic information distribution device and pathology diagnosis system | |
JP5645146B2 (ja) | 情報処理システム、情報処理方法、情報処理装置及びその制御方法とその制御プログラム | |
US11373422B2 (en) | Evaluation assistance method, evaluation assistance system, and computer-readable medium | |
Huang et al. | Mask RCNN algorithm for nuclei detection on breast cancer histopathological images | |
Halicek et al. | Cancer detection using hyperspectral imaging and evaluation of the superficial tumor margin variance with depth | |
WO2019171909A1 (ja) | 画像処理方法、画像処理装置及びプログラム | |
KR20230027164A (ko) | 조직 맵 시각화를 생성하기 위해 전자 이미지를 처리하는 시스템 및 방법 | |
Giavina-Bianchi et al. | Accuracy of deep neural network in triaging common skin diseases of primary care attention | |
Lin et al. | Prostate lesion delineation from multiparametric magnetic resonance imaging based on locality alignment discriminant analysis | |
WO2005010206A1 (ja) | 染色体状態の評価方法および評価システム | |
KR102446638B1 (ko) | 유방암 병변 영역을 판별하기 위한 인공 신경망을 학습하기 위한 학습 방법, 및 이를 수행하는 컴퓨팅 시스템 | |
Schönmeyer et al. | Automated whole slide analysis of differently stained and co-registered tissue sections | |
de Haan et al. | Deep learning-based transformation of the H&E stain into special stains improves kidney disease diagnosis | |
Chaudhury et al. | Predicting Ki67% expression from DCE-MR images of breast tumors using textural kinetic features in tumor habitats | |
CN111134735A (zh) | 一种肺部细胞病理快速现场评估***、方法及计算机可读存储介质 | |
de Haan et al. | Deep learning-based transformation of the H&E stain into special stains | |
Majumdar et al. | Machine learning based local recurrence prediction in colorectal cancer using polarized light imaging | |
Li et al. | An interpretable MRI-based radiomics model predicting the prognosis of high-intensity focused ultrasound ablation of uterine fibroids |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 12739346 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2012554708 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13981275 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 12739346 Country of ref document: EP Kind code of ref document: A1 |