WO2021081839A1 - 基于vrds 4d的病情分析方法及相关产品 - Google Patents

基于vrds 4d的病情分析方法及相关产品 Download PDF

Info

Publication number
WO2021081839A1
WO2021081839A1 PCT/CN2019/114475 CN2019114475W WO2021081839A1 WO 2021081839 A1 WO2021081839 A1 WO 2021081839A1 CN 2019114475 W CN2019114475 W CN 2019114475W WO 2021081839 A1 WO2021081839 A1 WO 2021081839A1
Authority
WO
WIPO (PCT)
Prior art keywords
target
blood vessel
image data
data
disease
Prior art date
Application number
PCT/CN2019/114475
Other languages
English (en)
French (fr)
Inventor
李戴维伟
李斯图尔特平
Original Assignee
未艾医疗技术(深圳)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 未艾医疗技术(深圳)有限公司 filed Critical 未艾医疗技术(深圳)有限公司
Priority to PCT/CN2019/114475 priority Critical patent/WO2021081839A1/zh
Priority to CN201980099991.4A priority patent/CN114341996A/zh
Publication of WO2021081839A1 publication Critical patent/WO2021081839A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00ICT specially adapted for the handling or processing of medical images
    • G16H30/20ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS

Definitions

  • This application relates to the technical field of medical imaging devices, in particular to a VRDS 4D-based disease analysis method and related products.
  • CT electronic computer tomography
  • MRI magnetic resonance imaging
  • DTI diffusion tensor imaging
  • PET positron emission computed tomography
  • the embodiments of the present application provide a VRDS 4D-based disease analysis method and related products, which are beneficial to improve the efficiency of disease analysis.
  • the embodiments of the present application provide a VRDS 4D-based disease analysis method, including:
  • each human organ corresponds to at least one scanned image
  • the human organ includes at least one of the following: ears, nose, and throat;
  • the disease condition analysis is performed on the diseased part, and the target disease condition analysis result is obtained.
  • an embodiment of the present application provides a VRDS 4D-based disease analysis device, including:
  • the acquiring unit is used to acquire scanned images of multiple human organs of the target user to obtain multiple scanned images, and each human organ corresponds to at least one scanned image;
  • a processing unit configured to process the multiple scanned images to obtain a target 4D image corresponding to the target user, where the target 4D image includes target image data corresponding to the target user;
  • An identification unit configured to identify an onset location corresponding to the target user based on the target image data, where the onset location is one or more of the multiple human organs;
  • an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured by The foregoing processor executes, and the foregoing program includes instructions for executing the steps in the first aspect of the embodiments of the present application.
  • an embodiment of the present application provides a computer-readable storage medium, wherein the above-mentioned computer-readable storage medium stores a computer program for electronic data exchange, wherein the above-mentioned computer program enables a computer to execute Some or all of the steps described in one aspect.
  • the embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute as implemented in this application.
  • the computer program product may be a software installation package.
  • FIG. 1 is a schematic structural diagram of a VRDS 4D-based disease analysis and processing system 100 provided by an embodiment of the present application;
  • FIG. 2 is a schematic flowchart of an embodiment of a VRDS 4D-based disease analysis method provided by an embodiment of the present application
  • FIG. 3 is a schematic structural diagram of a medical imaging device provided by an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of an embodiment of a VRDS 4D-based disease analysis device provided by an embodiment of the present application.
  • the medical imaging devices involved in the embodiments of this application refer to various instruments that use various media as information carriers to reproduce the internal structure of the human body as images.
  • the image information and the actual structure of the human body have spatial and temporal distributions.
  • DICOM data refers to the original image file data that reflects the internal structural characteristics of the human body collected by medical equipment, which can include electronic computed tomography CT, magnetic resonance MRI, diffusion tensor imaging DTI, and positron emission computed tomography PET-
  • image source refers to the Texture2D/3D image volume data generated by analyzing the original DICOM data.
  • VRDS refers to the Virtual Reality Doctor system (VRDS for short).
  • FIG. 1 is a schematic structural diagram of a VRDS 4D-based disease analysis and processing system 100 according to an embodiment of this application.
  • the system 100 includes a medical imaging device 110 and a network database 120.
  • the medical imaging device 110 can Including the local medical imaging device 111 and/or the terminal medical imaging device 112, the local medical imaging device 111 or the terminal medical imaging device 112 is used to base on the original DICOM data, based on the VRDS 4D disease analysis algorithm presented in the embodiment of this application, Perform identification, positioning, four-dimensional volume rendering, and abnormal analysis of human organs to achieve four-dimensional three-dimensional imaging effects (the four-dimensional medical image specifically refers to the medical image including the internal spatial structural features and external spatial structural features of the displayed tissue.
  • the internal space Structural characteristics mean that the slice data inside the tissue is not lost, that is, the medical imaging device can present the internal structure of human organs, blood vessels and other tissues.
  • the external spatial structural characteristics refer to the environmental characteristics between tissues, including tissues and tissues. Spatial location characteristics (including crossing, spacing, fusion), etc., such as the edge structure characteristics of the crossing position between the ears, nose, and throat and blood vessels, etc.), the local medical imaging device 111 is relative to the terminal medical imaging device 112 It can also be used to edit the image source data to form the transfer function result of the four-dimensional human body image.
  • the transfer function result can include the transfer function result of the surface of the human organ and the tissue structure in the human organ, and the transfer function result of the cube space, such as The cube edit box and arc edit array quantity, coordinates, color, transparency and other information required by the transfer function.
  • the network database 120 may be, for example, a cloud server.
  • the network database 120 is used to store the image source generated by analyzing the original DICOM data and the transfer function result of the four-dimensional human body image edited by the local medical imaging device 111.
  • the image source may be from multiple sources.
  • a local medical imaging device 111 to realize interactive diagnosis of multiple doctors.
  • HMDS head mounted Displays Set
  • the operation actions refer to the user’s actions through the medical imaging device.
  • External ingestion devices such as mouse, keyboard, tablet (portable android device, Pad), iPad (internetportable apple device), etc., operate and control the four-dimensional human body image to achieve human-computer interaction.
  • the operation action includes at least one of the following : (1) Change the color and/or transparency of a specific organ/tissue, (2) Position the zoom view, (3) Rotate the view, realize the multi-view 360-degree observation of the four-dimensional human body image, (4) "Enter” the human organ Internal observation of internal structure, real-time cutting effect rendering, (5) Move the view up and down.
  • FIG. 2 is a schematic flowchart of an embodiment of a VRDS 4D-based disease analysis method provided by an embodiment of this application.
  • the VRDS 4D-based disease analysis method described in this embodiment includes the following steps:
  • the medical imaging device obtains scanned images of multiple human organs of a target user, and obtains multiple scanned images. Each human organ corresponds to at least one scanned image.
  • the human organ includes at least one of the following: ears, nose, and Throat
  • the above-mentioned human organs may be at least one of the following: ears, nose, throat, brain, kidneys and other organs, which are not limited here, and the above-mentioned scanned images may include any of the following: CT images, MRI images, DTI images , PET-CT images, etc., are not limited here.
  • the medical imaging device can collect multiple scanned images reflecting the internal structure of multiple human organs of the target user, and each human organ corresponds to at least one scanned image.
  • the medical imaging device processes the multiple scanned images to obtain a target 4D image corresponding to the target user, where the target 4D image includes target image data corresponding to the target user;
  • the target image data may include a human organ data set and a blood vessel data set, and the human organ data set may include data corresponding to multiple human organs.
  • the multiple scanned images are processed to obtain a target 4D image corresponding to the target user, where the target 4D image includes target image data corresponding to the target user, and may include the following steps:
  • the first medical image data includes a human organ data set and a blood vessel data set, and the human organ data set includes the Multiple data corresponding to multiple human organs;
  • the foregoing first preset processing may include at least one of the following operations: VRDS restricted contrast adaptive histogram equalization, hybrid partial differential denoising, VRDS Ai elastic deformation processing, etc., which are not limited here; the medical imaging device may be preset Suppose the VRDS medical network model, the medical imaging device obtains the BMP data source by processing multiple scanned image data, which increases the amount of information of the original data, and increases the depth dimension information, and finally obtains data that meets the requirements of 4D medical image display.
  • the medical imaging device imports the above-mentioned BMP data source into the preset VRDS medical network model, through which each transfer function in the set of pre-stored transfer functions can be called through the VRDS medical network model, and processed by multiple transfer functions in the transfer function set
  • the above-mentioned BMP data source obtains the first medical image data
  • the above-mentioned transfer function set may include the transfer function of the blood vessel and the transfer function of the above-mentioned multiple human organs preset by a reverse editor, wherein the transfer function of the above-mentioned multiple human organs It may include at least one of the following: the transfer function of the ear, the transfer function of the nose, and the transfer function of the larynx. In this way, obtaining the first medical image data through the preset VRDS medical network model can improve the accuracy and efficiency of the obtained data.
  • the medical imaging device may be preset with a cross-vessel network model
  • the preset cross-vessel network model may be a trained neural network model
  • the above-mentioned first medical image data may be imported into the preset cross-vessel network model.
  • the cross blood vessel network model performs data segmentation to obtain ear data set, nose data set, throat data set, and blood vessel data set.
  • the blood vessel data set includes the data associated with the cross positions of the above-mentioned organs and blood vessels.
  • the second medicine can be obtained.
  • Image data in this way, can achieve data segmentation between data corresponding to blood vessels and data corresponding to multiple human organs by crossing the blood vessel network model, so as to obtain data information corresponding to different human organs.
  • the blood vessel centerline data of the blood vessel can be determined from the above-mentioned blood vessel data set.
  • the blood vessel centerline may refer to the line between each center point in the blood vessel section.
  • the method for extracting the blood vessel centerline may include the following At least one: manual calibration, distance transformation, topology refinement, etc., which are not limited here.
  • multiple formation directions corresponding to multiple blood vessels can be determined from the data of the blood vessel intersection part in the blood vessel data set, and based on the multiple The formation direction determines the position and direction of the blood vessel centerline of each blood vessel in the above-mentioned blood vessel in the multiple blood vessels.
  • the blood vessel centerline data set corresponding to each blood vessel can be obtained according to the above-mentioned extraction method, and the blood vessel centerline data set includes multiple The blood vessel centerline of each blood vessel, in this way, the blood vessel centerline can be prepared for the subsequent determination of the location of the disease.
  • the foregoing second preset processing includes at least one of the following methods: 2D boundary optimization processing, 3D boundary optimization processing, data enhancement processing, etc., which are not limited here; the foregoing 2D boundary optimization processing includes: multiple sampling to obtain low resolution Rate information and high-resolution information.
  • the low-resolution information can provide the contextual semantic information of the segmentation target in the entire image, that is, the features that reflect the relationship between the segmentation target and the environment. These features are used for object category judgment, high resolution
  • the rate information is used to provide more refined features for segmentation targets, such as gradients.
  • the segmentation targets may include ear, nose, and throat and blood vessels.
  • the second medical image data can be processed to obtain a 4D image of the target, and the target 4D image may include Target image data.
  • the target image data may include at least one of the following: a blood vessel data set, an ear data set, a nose data set, and a throat data set.
  • the medical imaging device identifies an onset location corresponding to the target user based on the target image data, where the onset location is one or more of the multiple human organs;
  • the above-mentioned disease site may include at least one of the following: nose, ears, throat, etc., which are not limited here.
  • the above-mentioned disease site can be understood as a specific site of disease in multiple human organs, which can be multiple people.
  • the disease type corresponding to the diseased part may be a cyst or a polyp, etc., which is not limited here.
  • identifying the diseased location corresponding to the target user based on the target image data may include the following steps:
  • the blood vessel centerline data set determine the blood vessel distribution data set corresponding to the multiple human organs, wherein each of the human organs corresponds to one blood vessel distribution data;
  • the onset location corresponding to the target user According to the multiple image data, identify the onset location corresponding to the target user.
  • the above-mentioned target image data includes at least a blood vessel data set. Since the scanned image obtained by scanning includes images of multiple blood vessels, multiple target blood vessel data sets associated with multiple human organs can be selected based on the blood vessel data set. The multiple target blood vessels corresponding to the multiple target blood vessel data sets are all connected to multiple human organs, and the blood vessel centerline data sets corresponding to the multiple target blood vessels can be obtained through the multiple target blood vessel data sets.
  • the blood vessel centerline data Concentration includes multiple blood vessel center lines corresponding to multiple target blood vessels. Since each target blood vessel has a width, if the target blood vessel has a disease, the contour will become different, which is not conducive to observing the bifurcation and position of the target blood vessel.
  • the centerline of the blood vessel can be introduced, and then the specific position of the target blood vessel can be obtained through the position of the blood vessel centerline.
  • the corresponding distribution of multiple target blood vessels connected to multiple human organs can be obtained, and
  • a blood vessel distribution data set, the blood vessel distribution data set includes the position of the blood vessel, the shape feature of the blood vessel, and so on.
  • multiple target organs connected to blood vessels can be obtained according to the above-mentioned blood vessel distribution data set.
  • the target organs can include ears, nose, throat, etc., and the multiple target organs can be target organs with disease. In this way, it can be determined The specific location of the lesion in the target organ is conducive to subsequent disease analysis.
  • the identifying the onset location corresponding to the target user based on the multiple image data may include the following steps:
  • the feature information includes at least one of the following: color, shape, position, and size;
  • multiple image data corresponding to multiple target organs can be generated to generate multiple feature information corresponding to the multiple target organs, and the location of the disease can be determined based on the feature information.
  • the feature information may include at least one of the following: Color, shape, position and size, etc., are not limited here.
  • the foregoing step 34 determining multiple target organs according to the blood vessel distribution data set, may include the following steps:
  • A1. Obtain a blood vessel radius data set corresponding to the multiple human organs in the blood vessel data set;
  • A2 according to the blood vessel radius data set, determine a blood vessel distortion distribution data set corresponding to a blood vessel radius in the blood vessel distribution data set that exceeds a preset threshold;
  • A3. Determine the vascular distortion range through the vascular distortion distribution data set
  • A4. Determine the multiple target organs according to the blood vessel distortion distribution data set and the blood vessel distortion range.
  • the above-mentioned blood vessel data set may include data associated with the intersection of blood vessels and blood vessels.
  • the blood vessel data set Through the blood vessel data set, multiple blood vessels connected to multiple human organs can be determined, and images corresponding to the multiple blood vessels can be obtained to determine the above
  • a blood vessel radius data set can be obtained, and the blood vessel radius data set includes the radii of multiple blood vessels corresponding to multiple human organs.
  • the above preset threshold can be set by the user or the system defaults.
  • the preset threshold can be understood as the radius of a normal blood vessel. If a lesion such as hemangioma is formed in the blood vessel, the radius of the blood vessel will be larger than the radius of the normal blood vessel. Then the blood vessel can be classified as a deformed blood vessel, or the contour shape of the blood vessel can be combined to determine whether the blood vessel is a deformed blood vessel.
  • the blood vessel radius exceeding the preset threshold can be filtered from the blood vessel radius data set, and the blood vessel radius can be determined to exceed the preset threshold.
  • a plurality of deformed blood vessels with a threshold value can be obtained, and the deformed blood vessel distribution data set in the above-mentioned blood vessel distribution data set corresponding to the multiple deformed blood vessels can be obtained.
  • the data set includes the distribution data corresponding to each deformed blood vessel.
  • the distribution data includes blood vessel bifurcation information, Position information, etc., to obtain the distribution information corresponding to the above-mentioned multiple distorted blood vessels, and determine the multiple distortion positions of the blood vessel distortion according to the blood vessel distortion distribution data set corresponding to the multiple distorted blood vessels, and according to the multiple distortion positions and the multiple distorted blood vessels
  • the distribution information of multiple target organs with lesions can be determined.
  • the foregoing step 37, identifying the diseased parts in the multiple target organs according to the multiple characteristic information may include the following steps:
  • the aforementioned preset disease location recognition model can be set by the user or the system defaults
  • the preset disease location recognition model can be a convolutional neural network
  • the aforementioned preset probability value can be set by the user or the system defaults
  • the above feature information It may include at least one of the following: morphological features, color features, location features, size features, etc., which are not limited here; specifically, multiple feature probabilities corresponding to the multiple features can be used to determine the excess of the multiple feature probabilities.
  • At least one piece of feature information corresponding to the preset probability value, and the location corresponding to the at least one piece of feature information is the onset location among the multiple onset target organs. In this way, the recognition efficiency can be improved.
  • identifying the onset location corresponding to the target user may further include the following steps:
  • the target image data generate first target image data corresponding to any human organ i among the plurality of human organs, the first target image data includes at least k pieces of spatial position data, and the k pieces
  • the spatial position data corresponds to k first image data, and each of the spatial position data corresponds to one first image data, where k is a positive integer;
  • the medical imaging device can determine the spatial location area corresponding to each human organ data in the multiple human organs according to the human organ data set in the target image data, and determine each human body according to the spatial location area corresponding to each human organ data The position coordinates corresponding to the organ data. In this way, k spatial position data corresponding to any human organ i can be obtained, and each spatial position data can correspond to a first image data in the target image data.
  • the identifying the onset location corresponding to the target user according to the k spatial location data may include the following steps:
  • the site is the site of the disease, where p is an integer less than k.
  • the abnormal first image data can be obtained, and the abnormal part can be obtained from the abnormal first image data, and the abnormal part is the diseased part, where k is positive Integer, p is an integer less than k.
  • the abnormal data corresponding to the onset location can be detected through multiple spatial location data, so that the onset location can be identified, and the recognition accuracy is improved.
  • the medical imaging device performs a disease analysis on the diseased part, and obtains a target disease analysis result.
  • the diseased site after identifying the diseased site, the diseased site can be analyzed to obtain the target diseased analysis result.
  • the medicine can be prescribed according to the obtained diseased analysis result, or the diseased analysis result can be used as an auxiliary treatment plan to help the doctor confirm the diagnosis.
  • step 204 performing disease analysis on the diseased site to obtain the target disease analysis result, may include the following steps:
  • a disease feature database can be preset in the medical imaging device, and multiple disease types can be preset in the preset disease database, and each disease type can correspond to a set of preset disease feature information.
  • the disease types can include at least one of the following : Ear tumors, nose tumors, throat tumors, etc., which are not limited here; specifically, multiple features corresponding to the onset location can be put into the above-mentioned preset disease feature database for matching, and multiple matching values are obtained.
  • a matching value is multiple ratio values obtained by matching multiple preset disease feature information corresponding to each disease in the preset disease feature database, and the disease type corresponding to the largest matching value among the multiple matching values is selected as the target disease type
  • the above-mentioned medical imaging device can also preset the mapping relationship between the disease type and the disease analysis result. According to the mapping relationship, the target disease analysis result corresponding to the target disease type can be determined, and multiple predictions corresponding to each disease type can be determined.
  • Set disease feature information to generate disease analysis data which can obtain multiple disease analysis data for multiple disease types, and preset disease analysis results for each disease analysis data.
  • the preset disease analysis results can correspond to different disease severity. In this way, the target disease analysis result corresponding to the target disease type can be obtained, and the efficiency of disease analysis can be improved, and the efficiency of disease treatment can be improved.
  • the medical imaging device can first obtain scanned images of multiple human organs of the target user, and obtain multiple scanned images, each of which corresponds to at least one
  • the above-mentioned human organs include at least one of the following: ears, nose, and throat.
  • the multiple scanned images are processed to obtain a target 4D image corresponding to the target user, and the target 4D image includes a target image corresponding to the target user Based on the target image data, identify the affected part of the target user.
  • the affected part is one or more parts of multiple human organs.
  • the diseased part is analyzed to obtain the target disease analysis result. In this way, the scanned image
  • the analysis and processing of the target user can obtain the diseased location of the target user, and perform the disease analysis for the diseased location to obtain the disease analysis result, which is beneficial to improve the accuracy and efficiency of the disease analysis.
  • FIG. 3 is a schematic structural diagram of a medical imaging device 300 provided by an embodiment of the application.
  • the medical imaging device 300 includes a processor 310, a memory 320, a communication interface 330, One or more programs 321, wherein the one or more programs 321 are stored in the above-mentioned memory 320 and are configured to be executed by the above-mentioned processor 310, and the one or more programs 321 include: instruction:
  • each human organ corresponds to at least one scanned image
  • the human organ includes at least one of the following: ears, nose, and throat;
  • the disease condition analysis is performed on the diseased part, and the target disease condition analysis result is obtained.
  • scanned images of multiple human organs of the target user can be obtained, and multiple scanned images can be obtained.
  • Each human organ corresponds to at least one scanned image.
  • the aforementioned human organs include At least one of the following: ears, nose, and throat, process multiple scanned images to obtain a target 4D image corresponding to the target user.
  • the target 4D image includes target image data corresponding to the target user. Based on the target image data, identify The diseased part corresponding to the target user, the diseased part is one or more parts of multiple human organs, the diseased part is analyzed for the diseased part, and the target diseased analysis result is obtained.
  • the scanned image can be analyzed and processed to obtain the target user's
  • the location of the disease and the analysis of the disease condition for the location of the disease to obtain the results of the disease analysis, which is beneficial to improve the accuracy and efficiency of the disease analysis.
  • the program further includes a method for performing the following operations The instructions:
  • multiple target organs are determined, and the multiple target organs include at least one of the following: ears, nose, and throat;
  • the onset location corresponding to the target user is identified.
  • the program further includes instructions for performing the following operations:
  • the feature information including at least one of the following: color, shape, position, and size;
  • the onset location corresponding to the target user is identified.
  • the program further includes instructions for performing the following operations:
  • the multiple target organs are determined according to the blood vessel distortion distribution data set and the blood vessel distortion range.
  • the program further includes instructions for performing the following operations:
  • an onset location in the multiple target organs is determined.
  • the program further includes instructions for performing the following operations:
  • the target condition analysis result corresponding to the target user is determined.
  • the program further includes instructions for performing the following operations:
  • first target image data corresponding to any human organ i among the plurality of human organs is generated, the first target image data includes at least k spatial position data, and the k spatial positions The data corresponds to k first image data, and each of the spatial position data corresponds to one first image data, where k is a positive integer;
  • the k pieces of spatial location data identify the onset location corresponding to the target user.
  • the program further includes instructions for performing the following operations:
  • the target 4D image includes target image data corresponding to the target user
  • the program further Include instructions to perform the following actions:
  • the first medical image data includes a human organ data set and a blood vessel data set, and the human organ data set includes the plurality of people Multiple body organ data corresponding to the body organ;
  • FIG. 4 is a schematic structural diagram of an embodiment of a VRDS 4D-based disease analysis device provided by an embodiment of this application.
  • the VRDS 4D-based disease analysis device described in this embodiment includes: an acquisition unit 401, a processing unit 402, an identification unit 403, and an analysis unit 404, which are specifically as follows:
  • the acquiring unit 401 is configured to acquire scanned images of multiple human organs of the target user to obtain multiple scanned images, and each human organ corresponds to at least one scanned image;
  • the processing unit 402 is configured to process the multiple scanned images to obtain a target 4D image corresponding to the target user, and the target 4D image includes target image data corresponding to the target user;
  • the identification unit 403 is configured to identify an onset location corresponding to the target user based on the target image data, where the onset location is one or more of the multiple human organs;
  • the analysis unit 404 is configured to perform a disease analysis on the diseased part to obtain a target disease analysis result.
  • the VRDS 4D-based disease analysis device described in the embodiments of this application can obtain scanned images of multiple human organs of the target user to obtain multiple scanned images, and each human organ corresponds to at least one scanned image.
  • the above-mentioned human organs include at least one of the following: ears, nose, and throat.
  • the multiple scanned images are processed to obtain a target 4D image corresponding to the target user.
  • the target 4D image includes target image data corresponding to the target user.
  • Image data identify the affected part of the target user.
  • the affected part is one or more parts of multiple human organs, and analyze the condition of the affected part to obtain the target condition analysis result.
  • the scanned image can be analyzed and processed.
  • the identification unit 403 is specifically configured to:
  • multiple target organs are determined, and the multiple target organs include at least one of the following: ears, nose, and throat;
  • the onset location corresponding to the target user is identified.
  • the identification unit 403 is specifically further configured to:
  • the feature information including at least one of the following: color, shape, position, and size;
  • the onset location corresponding to the target user is identified.
  • the identification unit 403 is specifically further configured to:
  • the multiple target organs are determined according to the blood vessel distortion distribution data set and the blood vessel distortion range.
  • the identification unit 403 is specifically further configured to:
  • an onset location in the multiple target organs is determined.
  • the above analysis unit 404 is specifically configured to:
  • the target condition analysis result corresponding to the target user is determined.
  • the identification unit 403 is specifically further configured to:
  • first target image data corresponding to any human organ i among the plurality of human organs is generated, the first target image data includes at least k spatial position data, and the k spatial positions The data corresponds to k first image data, and each of the spatial position data corresponds to one first image data, where k is a positive integer;
  • the k pieces of spatial location data identify the onset location corresponding to the target user.
  • the identification unit 403 is specifically further configured to:
  • the target 4D image includes target image data corresponding to the target user, the processing unit 402 Specifically used for:
  • the first medical image data includes a human organ data set and a blood vessel data set, and the human organ data set includes the plurality of people Multiple body organ data corresponding to the body organ;
  • each program module of the VRDS 4D-based disease analysis device of this embodiment can be implemented according to the method in the above method embodiment.
  • An embodiment of the present application also provides a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, and the computer program enables the computer to execute any VRDS 4D-based condition as recorded in the above method embodiment Part or all of the steps of the analytical method.
  • the embodiments of the present application also provide a computer program product.
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program.
  • the computer program is operable to cause a computer to execute the method described in the foregoing method embodiment. Part or all of the steps of any disease analysis method based on VRDS 4D.
  • the disclosed device may be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or may be Integrate into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be realized in the form of hardware or software program module.
  • the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer readable memory.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory.
  • a number of instructions are included to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application.
  • the foregoing memory includes: U disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
  • the program can be stored in a computer-readable memory, and the memory can include: a flash disk , ROM, RAM, magnetic disk or CD, etc.

Landscapes

  • Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Engineering & Computer Science (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Image Analysis (AREA)

Abstract

一种基于VRDS 4D病情分析方法及相关产品,应用于医学成像装置,该方法包括:获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,上述人体器官包括以下至少一种:耳部、鼻部和喉部,对多张扫描图像进行处理,得到目标用户对应的目标4D影像,该目标4D影像包括目标用户对应的目标影像数据,基于目标影像数据识别目标用户对应的发病部位,发病部位为多个人体器官中的一个或者多个部位,针对发病部位进行病情分析,得到目标分析结果。

Description

基于VRDS 4D的病情分析方法及相关产品 技术领域
本申请涉及医学成像装置技术领域,具体涉及一种基于VRDS 4D的病情分析方法及相关产品。
背景技术
目前,医生仍然采用观看阅读连续的二维切片扫描图像,例如,CT(电子计算机断层扫描)、MRI(磁共振成像)、DTI(弥散张量成像)、PET(正电子发射型计算机断层显像)等,以此对患者的病变组织如肿瘤进行判断分析。然而,仅仅通过直接观看两维切片数据无法确定肿瘤与周围血管的关联关系,严重影响到医生对疾病的诊断。
发明内容
本申请实施例提供了一种基于VRDS 4D的病情分析方法及相关产品,有利于提高病情分析的效率。
第一方面,本申请实施例提供了一种基于VRDS 4D的病情分析方法,包括:
获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像,所述人体器官包括以下至少一种:耳部、鼻部和喉部;
对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据;
基于所述目标影像数据,识别所述目标用户对应的发病部位,所述发病部位为所述多个人体器官中的一个或者多个部位;
针对所述发病部位进行病情分析,得到目标病情分析结果。
第二方面,本申请实施例提供了一种基于VRDS 4D的病情分析装置,包括:
获取单元,用于获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像;
处理单元,用于对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据;
识别单元,用于基于所述目标影像数据,识别所述目标用户对应的发病部位,所述发病部位为所述多个人体器官中的一个或者多个部位;
分析单元,用于针对所述发病部位进行病情分析,得到目标病情分析结果。第三方面,本申请实施例提供了一种电子设备,包括处理器、存储器、通信接口,以及一个或多个程序,其中,上述一个或多个程序被存储在上述存储器中,并且被配置由上述处理器执行, 上述程序包括用于执行本申请实施例第一方面中的步骤的指令。
第四方面,本申请实施例提供了一种计算机可读存储介质,其中,上述计算机可读存储介质存储用于电子数据交换的计算机程序,其中,上述计算机程序使得计算机执行如本申请实施例第一方面中所描述的部分或全部步骤。
第五方面,本申请实施例提供了一种计算机程序产品,其中,上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质,上述计算机程序可操作来使计算机执行如本申请实施例第一方面中所描述的部分或全部步骤。该计算机程序产品可以为一个软件安装包。
附图说明
下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍。
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的一种基于VRDS 4D的病情分析处理***100的结构示意图;
图2是本申请实施例提供的一种基于VRDS 4D的病情分析方法的实施例流程示意图;
图3是本申请实施例提供的一种医学成像装置的结构示意图;
图4是本申请实施例提供的一种基于VRDS 4D的病情分析装置的实施例结构示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案,下面将结合本申请实施例中的附图,对本申请实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象,而不是用于描述特定顺序。此外,术语“包括”和“具有”以及它们任何变形,意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、***、产品或设备没有限定于已列出的步骤或单元,而是可选地还包括没有列出的步骤或单元,或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着,结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例,也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是,本文所描述的实施例可以与其它实施例相结合。
本申请实施例所涉及到的医学成像装置是指利用各种不同媒介作为信息载体,将人体内部的结构重现为影像的各种仪器,其影像信息与人体实际结构有着空间和时间分布上的对应关系。“DICOM数据”是指通过医疗设备采集的反映人体内部结构特征的原始图像文件数据,可以包括电子计算机断层扫描CT、核磁共振MRI、弥散张量成像DTI、正电子发射型计算机断层显像PET-CT等信息,“图源”是指解析原始DICOM数据生成的Texture2D/3D图像体数据。“VRDS”是指虚拟现实医用***(Virtual Reality Doctor system,简称为VRDS)。
请参阅图1,为本申请实施例提供的一种基于VRDS 4D的病情分析处理***100的结构示意图,该***100包括该***100包括医学成像装置110和网络数据库120,其中医学成像装置110可以包括本地医学成像装置111和/或终端医学成像装置112,本地医学成像装置111或终端医学成像装置112用于基于原始DICOM数据,以本申请实施例所呈现的VRDS 4D的病情分析算法为基础,进行人体器官的识别、定位、四维体绘制、异常分析,实现四维立体成像效果(该4维医学影像具体是指医学影像包括所显示组织的内部空间结构特征及外部空间结构特征,所述内部空间结构特征是指组织内部的切片数据未丢失,即医学成像装置可以呈现人体器官、血管等组织的内部构造,外部空间结构特性是指组织与组织之间的环境特征,包括组织与组织之间的空间位置特性(包括交叉、间隔、融合)等,如耳部、鼻部和喉部等器官与血管之间的交叉位置的边缘结构特性等),本地医学成像装置111相对于终端医学成像装置112还可以用于对图源数据进行编辑,形成四维人体图像的传递函数结果,该传递函数结果可以包括人体器官表面和人体器官内的组织结构的传递函数结果,以及立方体空间的传递函数结果,如传递函数所需的立方编辑框与弧线编辑的数组数量、坐标、颜色、透明度等信息。网络数据库120例如可以是云服务器等,该网络数据库120用于存储解析原始DICOM数据生成的图源,以及本地医学成像装置111编辑得到的四维人体图像的传递函数结果,图源可以是来自于多个本地医学成像装置111以实现多个医生的交互诊断。
用户通过上述医学成像装置110进行具体的图像显示时,可以选择显示器或者虚拟现实VR的头戴式显示器(Head mounted Displays Set,HMDS)结合操作动作进行显示,操作动作是指用户通过医学成像装置的外部摄入设备,如鼠标、键盘、平板电脑(portable android device,Pad)、iPad(internetportableapple device)等,对四维人体图像进行的操作控制,以实现人机交互,该操作动作包括以下至少一种:(1)改变某个具体器官/组织的颜色和/或透明度,(2)定位缩放视图,(3)旋转视图,实现四维人体图像的多视角360度观察,(4)“进入”人体器官内部观察内部构造,实时剪切效果渲染,(5)上下移动视图。
下面对本申请实施例涉及到的基于VRDS 4D的病情分析方法进行详细介绍。
请参阅图2,为本申请实施例提供的一种基于VRDS 4D的病情分析方法的实施例的流程示意图。本实施例中所描述的基于VRDS 4D的病情分析方法,包括以下步骤:
201、医学成像装置获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像,所述人体器官包括以下至少一种:耳部、鼻部和喉部;
其中,上述人体器官可为以下至少一种:耳部、鼻部、喉、脑部、肾脏等器官,在此不作限定,上述扫描图像可包括以下任意一种:CT图像、MRI图像、DTI图像、PET-CT图像等等,在此不作限定。医学成像装置可采集反应目标用户的多个人体器官内部结构的多张扫描图像,每一人体器官至少对应一张扫描图像。
202、医学成像装置对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据;
其中,可针对多张扫描图像进行处理,得到目标用户对应的目标4D影像,上述目标影像数据可包括人体器官数据集和血管数据集,该人体器官数据集中可包括多个人体器官对应的数据。
可选地,上述步骤202,对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据,可包括如下步骤:
21、针对所述多张扫描图像执行第一预设处理得到位图BMP数据源;
22、将所述BMP数据源导入预设的VRDS医学网络模型,得到第一医学影像数据,所述第一医学影像数据包括人体器官数据集和血管数据集,所述人体器官数据集中包括所述多个人体器官对应的多个数据;
23、将所述第一医学影像数据导入预设的交叉血管网络模型,得到第二医学影像数据,所述第二医学影像数据包括所述人体器官数据集和血管数据集;
24、针对所述第二医学影像数据执行第二预设处理得到所述目标4D影像。
其中,上述第一预设处理可包括以下至少一种操作:VRDS限制对比度自适应直方图均衡、混合偏微分去噪、VRDS Ai弹性变形处理等等,在此不作限定;医学成像装置中可预设VRDS医学网络模型,医学成像装置通过对多张扫描图像数据的处理,得到BMP数据源,提高了原始数据的信息量,且增加了深度维度信息,最终得到符合4D医学影像显示需求的数据。
此外,医学成像装置将上述BMP数据源导入预设的VRDS医学网络模型,可通过该VRDS医学网络模型调用预存的传递函数集合中的每个传递函数,通过传递函数集合中的多个传递函数处理上述BMP数据源,得到第一医学影像数据,上述传递函数集合可包括通过反向编辑器预先设置的血管的传递函数、上述多个人体器官的传递函数,其中,上述多个人体器官的传递函数可包括以下至少一种:耳的传递函数、鼻的传递函数和喉的传递函数,如此,通过预设VRDS医学网络模型得到第一医学影像数据,可提高得到数据的准确性和效率。
进一步地,医学成像装置中可预设交叉血管网络模型,该预设交叉血管网络模型可为训练好的神经网络模型,可将上述第一医学影像数据导入预设的交叉血管网络模型,可通过交叉血管网络模型进行数据分割,得到耳的数据集、鼻的数据集、喉的数据集、血管数据集,该血管数据集中包括上述器官与血管交叉位置关联的数据,最后,可得到第二医学 影像数据,如此,可通过交叉血管网络模型,实现血管对应的数据与多个人体器官对应的数据之间的数据分割,以得到不同的人体器官对应的数据信息。
在一种可能的示例中,可通过上述血管数据集确定血管的血管中心线数据,该血管中心线可指血管剖面中每个中心点之间的连线,血管中心线的提取方法可包括以下至少一种:手动标定、距离变换、拓扑细化等等,在此不作限定,具体地,可通过上述血管数据集中血管交叉部分的数据确定多个血管对应的多个形成方向,并根据多个形成方向确定多个血管中每一血管的血管中心线在上述血管中的位置以及方向,如此,可根据上述提取方法得到每个血管对应的血管中心线数据集,该血管中心线数据集中包括多个血管的血管中心线,如此,该血管中心线可为后续确定发病部位做准备。
进一步地,上述第二预设处理包括以下至少一种方法:2D边界优化处理、3D边界优化处理、数据增强处理等等,在此不作限定;上述2D边界优化处理包括:多次采样获取低分辨率信息和高分辨率信息,其中,低分辨率信息能够提供分割目标在整个图像中上下文语义信息,即反映所述分割目标与环境之间关系的特征,这些特征用于物体类别判断,高分辨率信息用于为分割目标提供更加精细的特征,如梯度等,其中,上述分割目标可包括耳鼻喉和血管,如此,处理上述第二医学影像数据可得到目标4D影像,该目标4D影像可包括目标影像数据,该目标影像数据可包括中可包括以下至少一种:血管数据集、耳数据集、鼻数据集和喉数据集。
203、医学成像装置基于所述目标影像数据,识别所述目标用户对应的发病部位,所述发病部位为所述多个人体器官中的一个或者多个部位;
其中,上述发病部位可包括以下至少一种:鼻部、耳部、喉部等等,在此不作限定,上述发病部位可理解为多个人体器官中具体的发生病变的部位,可为多个人体器官中的一个或者多个部位,该发病部位对应的疾病类型可为肿囊或者息肉等等,在此不作限定。
可选地,上述步骤203,若所述目标影像数据至少包括血管数据集,基于所述目标影像数据,识别所述目标用户对应的发病部位,可包括如下步骤:
31、基于所述血管数据集,选取与所述多个人体器官相关联的多个目标血管数据集;
32、获取所述多个目标血管数据集对应的血管中心线数据集,所述血管中心线为所述目标血管剖面中每个中心点之间的连线;
33、根据所述血管中心线数据集,确定与所述多个人体器官对应的血管分布数据集,其中,每一所述人体器官对应的一个血管分布数据;
34、根据所述血管分布数据集,确定多个目标器官,所述多个目标器官中包括以下至少一种:耳部、鼻部和喉部;
35、获取所述目标影像集中所述多个目标器官对应的多个影像数据,每一目标器官对应一个影像数据;
36、根据所述多个影像数据,识别所述目标用户对应的发病部位。
其中,上述目标影像数据至少包括血管数据集,由于扫描得到的扫描图像中包括多个血管的图像,因此,可基于血管数据集,选取与多个人体器官相关联的多个目标血管数据集,该多个目标血管数据集对应的多个目标血管均与多个人体器官相连,可通过多个目标血管数据集,得到与上述多个目标血管对应的血管中心线数据集,该血管中心线数据集中包括多个目标血管对应的多个血管中心线,由于每个目标血管都是有宽度的,若目标血管产生病变以后,轮廓则会变得不一样,不利于观察目标血管的分叉、位置等信息,因此,可引入血管中心线,然后,可通过血管中心线的位置,可得到目标血管的具***置,如此,可得到与多个人体器官相连接的多个目标血管对应的分布,得到血管分布数据集,该血管分布数据集中包括血管的位置、血管的形状特征等等。
此外,可根据上述血管分布数据集,得到与血管连接的多个目标器官,该目标器官可包括耳、鼻和喉等等,上述多个目标器官可为发生病变的目标器官,如此,可确定目标器官中具体的发生病变的部位,有利于后续的病情分析。
可选地,上述步骤36,所述根据所述多个影像数据,识别所述目标用户对应的发病部位,可包括如下步骤:
361、根据所述多个影像数据,生成所述多个目标器官对应的多个特征信息,所述特征信息包括以下至少一种:颜色、形状、位置、大小;
362、根据所述多个特征信息,识别所述目标用户对应的所述发病部位。
其中,为了确定发病部位,可针对多个目标器官对应多个影像数据,生成多个目标器官对应的多个特征信息,可根据特征信息,确定发病部位,上述特征信息可包括以下至少一种:颜色、形状、位置和大小等等,在此不作限定。
在一种可能的示例中,上述步骤34,根据所述血管分布数据集,确定多个目标器官,可包括以下步骤:
A1、获取所述血管数据集中所述多个人体器官对应的血管半径数据集;
A2、根据所述血管半径数据集,确定所述血管分布数据集中超过预设阈值的血管半径对应的血管畸变分布数据集;
A3、通过所述血管畸变分布数据集,确定所述血管畸变范围;
A4、根据所述血管畸变分布数据集与所述血管畸变范围,确定所述多个目标器官。
其中,上述血管数据集中可包括血管与血管交叉部位相关联的数据,可通过血管数据集,确定与多个人体器官相连接的多个血管,并获取多个血管分别对应的影像,以确定上述多个血管的半径,可得到血管半径数据集,该血管半径数据集中包括与多个人体器官对应的多个血管的半径。
此外,上述预设阈值可为用户自行设置或者***默认,该预设阈值可理解为正常血管对应的半径大小,若该血管中生成血管瘤等病变,该血管的半径会大于正常血管的半径,则可将该血管归为畸变血管,或者,也可结合血管的轮廓形状,确定该血管是否为畸变血 管,该可从血管半径数据集中筛选出超过预设阈值的血管半径,确定血管半径超过预设阈值的多个畸变血管,可得到多个畸变血管对应的上述血管分布数据集中的畸变血管分布数据集,该数据集中包括每一畸变血管对应的分布数据,该分布数据包括血管分叉信息、位置信息等,可得到上述多个畸变血管对应的分布信息,可根据多个畸变血管对应的血管畸变分布数据集确定发生血管畸变的多个畸变位置,并根据多个畸变位置以及多个畸变血管的分布信息,确定多个发生病变的目标器官。
可选地,上述步骤37,根据所述多个特征信息,识别所述多个目标器官中的发病部位,可包括以下步骤:
B1、获取预设发病部位识别模型;
B2、将所述多个特征信息输入所述预设发病部位识别模型,得到所述多个特征信息中每一特征信息对应的特征概率,得到多个特征概率;
B3、计算所述多个特征概率中的超过预设概率值对应的至少一个特征信息;
B4、根据所述至少一个特征信息,确定所述多个目标器官中的发病部位。
其中,上述预设发病部位识别模型可为用户自行设置或者***默认,该预设发病部位识别模型可为一个卷积神经网络,上述预设概率值可为用户自行设置或者***默认,上述特征信息可包括以下至少一种:形态特征、颜色特征、位置特征、大小特征等等,在此不作限定;具体地,可通过上述多个特征对应的多个特征概率,确定多个特征概率中的超过预设概率值对应的至少一个特征信息,该至少一个特征信息对应的部位即为上述多个发病的目标器官中的发病部位,如此,能够提高识别效率。
在一种可能的示例中,上述步骤203,基于所述目标影像数据,识别所述目标用户对应的发病部位,还可包括以下步骤:
C1、根据所述目标影像数据,生成所述多个人体器官中任一人体器官i对应的第一目标影像数据,所述第一目标影像数据中包括至少k个空间位置数据,所述k个空间位置数据对应k个第一影像数据,每个所述空间位置数据对应一个第一影像数据,其中,k为正整数;
C2、根据所述k个空间位置数据,识别所述目标用户对应的发病部位。
其中,医学成像装置可根据目标影像数据中的人体器官数据集,确定多个人体器官中每一人体器官数据对应的空间位置区域,并根据每一人体器官数据对应的空间位置区域确定每一人体器官数据对应的位置坐标,如此,可得到任一人体器官i对应的k个空间位置数据,每一空间位置数据可在目标影像数据中对应一个第一影像数据。
可选地,上述步骤C2,所述根据所述k个空间位置数据,识别所述目标用户对应的发病部位,可包括如下步骤:
C21、依据所述k个空间位置数据对所述人体器官i进行定位;
C22、遍历所述k个空间位置数据对应的所述k个第一影像数据,得到p个异常第一影像数据,所述p个异常第一影像数据对应的所述p个空间位置数据对应的部位即为所述发 病部位,其中,p为小于k的整数。
其中,可通过遍历上述k个空间位置数据对应的k个位置坐标,得到P个异常第一影像数据,可由异常第一影像数据得到异常部位,该异常部位即为发病部位,其中,k为正整数,p为小于k的整数,如此,可通过多个空间位置数据,检测出发病部位对应的异常数据,从而识别出发病部位,提高了识别的准确性。
204、医学成像装置针对所述发病部位进行病情分析,得到目标病情分析结果。
其中,识别出发病部位以后,可对该发病部位进行病情分析,得到目标病情分析结果,如此,可根据得到的病情分析结果对症下药,或者可将该病情分析结果作为辅助治疗方案,帮助医生确诊。
可选地,上述步骤204,针对所述发病部位进行病情分析,得到目标病情分析结果,可包括如下步骤:
41、获取预设疾病特征数据库对应的多组预设疾病特征信息,所述预设疾病特征数据库中包括多个疾病类型,每一疾病类型对应一组预设疾病特征信息;
42、将所述发病部位对应的多个特征信息与所述多组预设疾病特征信息一一匹配,得到多个匹配值,每一匹配值对应一种所述疾病类型;
43、获取所述多个匹配值中最大匹配值对应的疾病类型为目标疾病类型;
44、按照预设的疾病类型与病情分析结果之间的映射关系,确定所述目标用户对应的目标病情分析结果。
其中,医学成像装置中可预设疾病特征数据库,该预设疾病数据库中可预设多个疾病类型,每一疾病类型可对应一组预设疾病特征信息,上述疾病类型可包括以下至少一种:耳肿瘤、鼻肿瘤、喉部肿瘤等等,在此不作限定;具体地,可将发病部位对应的多个特征放入上述预设疾病特征数据库中进行匹配,得到多个匹配值,该多个匹配值为与预设疾病特征数据库中每个疾病对应的多个预设疾病特征信息相匹配得到的多个比例值,选取多个匹配值中的最大匹配值对应的疾病类型为目标疾病类型;上述医学成像装置中还可预设疾病类型与病情分析结果之间的映射关系,可根据该映射关系,确定目标疾病类型对应的目标病情分析结果,可针对每种疾病类型对应的多个预设疾病特征信息生成病情分析数据,可得到针对多个疾病类型的多个病情分析数据,可针对每个病情分析数据预设病情分析结果,该预设病情分析结果可对应有不同的病情程度,如此,可得到目标疾病类型对应的目标病情分析结果,可提高病情分析效率,提高病情处理效率。
可以看出,通过本申请实施例所提供的基于VRDS 4D的病情分析方法,医学成像装置首先可获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像,上述人体器官包括以下至少一种:耳部、鼻部和喉部,对多张扫描图像进行处理,得到目标用户对应的目标4D影像,该目标4D影像包括目标用户对应的目标影像数据,基于目标影像数据,识别目标用户对应的发病部位,发病部位为多个人体器官中 的一个或者多个部位,针对发病部位进行病情分析,得到目标病情分析结果,如此,可通过对扫描图像的分析处理,得到目标用户的发病部位,并针对该发病部位进行病情分析,以得到病情分析结果,有利于提高病情分析的准确性和效率。
与上述一致地,请参阅图3,为本申请实施例提供的一种医学成像装置300的结构示意图,如图所示,所述医学成像装置300包括处理器310、存储器320、通信接口330以及一个或多个程序321,其中,所述一个或多个程序321被存储在上述存储器320中,并且被配置由上述处理器310执行,所述一个或多个程序321包括用于执行以下步骤的指令:
获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像,所述人体器官包括以下至少一种:耳部、鼻部和喉部;
对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据;
基于所述目标影像数据,识别所述目标用户对应的发病部位,所述发病部位为所述多个人体器官中的一个或者多个部位;
针对所述发病部位进行病情分析,得到目标病情分析结果。
可以看出,通过本申请实施例所提供的医学成像装置,可可获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像,上述人体器官包括以下至少一种:耳部、鼻部和喉部,对多张扫描图像进行处理,得到目标用户对应的目标4D影像,该目标4D影像包括目标用户对应的目标影像数据,基于目标影像数据,识别目标用户对应的发病部位,发病部位为多个人体器官中的一个或者多个部位,针对发病部位进行病情分析,得到目标病情分析结果,如此,可通过对扫描图像的分析处理,得到目标用户的发病部位,并针对该发病部位进行病情分析,以得到病情分析结果,有利于提高病情分析的准确性和效率。
在一个可能的示例中,若所述目标影像数据至少包括血管数据集,在所述基于所述目标影像数据,识别所述目标用户对应的发病部位方面,所述程序还包括用于执行以下操作的指令:
基于所述血管数据集,选取与所述多个人体器官相关联的多个目标血管数据集;
获取所述多个目标血管数据集对应的血管中心线数据集,所述血管中心线为所述目标血管剖面中每个中心点之间的连线;
根据所述血管中心线数据集,确定与所述多个人体器官对应的血管分布数据集,其中,每一所述人体器官对应的一个血管分布数据;
根据所述血管分布数据集,确定多个目标器官,所述多个目标器官中包括以下至少一种:耳部、鼻部和喉部;
获取所述目标影像集中所述多个目标器官对应的多个影像数据,每一目标器官对应一 个影像数据;
根据所述多个影像数据,识别所述目标用户对应的发病部位。
在一个可能的示例中,在根据所述多个影像数据,识别所述目标用户对应的发病部位方面,所述程序还包括用于执行以下操作的指令:
根据所述多个影像数据,生成所述多个目标器官对应的多个特征信息,所述特征信息包括以下至少一种:颜色、形状、位置、大小;
根据所述多个特征信息,识别所述目标用户对应的所述发病部位。
在一个可能的示例中,在根据所述血管分布数据集,确定多个目标器官方面,所述程序还包括用于执行以下操作的指令:
获取所述血管数据集中所述多个人体器官对应的血管半径数据集;
根据所述血管半径数据集,确定所述血管分布数据集中超过预设阈值的血管半径对应的血管畸变分布数据集;
通过所述血管畸变分布数据集,确定所述血管畸变范围;
根据所述血管畸变分布数据集与所述血管畸变范围,确定所述多个目标器官。
在一个可能的示例中,在根据所述多个特征信息,识别所述多个目标器官中的发病部位方面,所述程序还包括用于执行以下操作的指令:
获取预设发病部位识别模型;
将所述多个特征信息输入所述预设发病部位识别模型,得到所述多个特征信息中每一特征信息对应的特征概率,得到多个特征概率;
计算所述多个特征概率中的超过预设概率值对应的至少一个特征信息;
根据所述至少一个特征信息,确定所述多个目标器官中的发病部位。
在一个可能的示例中,在针对所述发病部位进行病情分析,得到目标病情分析结果方面,所述程序还包括用于执行以下操作的指令:
获取预设疾病特征数据库对应的多组预设疾病特征信息,所述预设疾病特征数据库中包括多个疾病类型,每一疾病类型对应一组预设疾病特征信息;
将所述发病部位对应的多个特征信息与所述多组预设疾病特征信息一一匹配,得到多个匹配值,每一匹配值对应一种所述疾病类型;
获取所述多个匹配值中最大匹配值对应的疾病类型为目标疾病类型;
按照预设的疾病类型与病情分析结果之间的映射关系,确定所述目标用户对应的目标病情分析结果。
在一个可能的示例中,在基于所述目标影像数据,识别所述目标用户对应的发病部位方面,所述程序还包括用于执行以下操作的指令:
根据所述目标影像数据,生成所述多个人体器官中任一人体器官i对应的第一目标影像数据,所述第一目标影像数据中包括至少k个空间位置数据,所述k个空间位置数据对应k 个第一影像数据,每个所述空间位置数据对应一个第一影像数据,其中,k为正整数;
根据所述k个空间位置数据,识别所述目标用户对应的发病部位。
在一个可能的示例中,在所述根据所述k个空间位置数据,识别所述目标用户对应的发病部位方面,所述程序还包括用于执行以下操作的指令:
依据所述k个空间位置数据对所述人体器官i进行定位;
遍历所述k个空间位置数据对应的所述k个第一影像数据,得到p个异常第一影像数据,所述p个异常第一影像数据对应的所述p个空间位置数据对应的部位即为所述发病部位,其中,p为小于k的整数。
在一个可能的示例中,在对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据方面,所述程序还包括用于执行以下操作的指令:
针对所述多张扫描图像执行第一预设处理得到位图BMP数据源;
将所述BMP数据源导入预设的VRDS医学网络模型,得到第一医学影像数据,所述第一医学影像数据包括人体器官数据集和血管数据集,所述人体器官数据集中包括所述多个人体器官对应的多个人体器官数据;
将所述第一医学影像数据导入预设的交叉血管网络模型,得到第二医学影像数据,所述第二医学影像数据包括所述人体器官数据集和血管数据集;
针对所述第二医学影像数据执行第二预设处理得到所述目标4D影像。
与上述一致地,以下为实施上述基于VRDS 4D的病情分析方法的装置,具体如下:
请参阅图4,为本申请实施例提供的一种基于VRDS 4D的病情分析装置的实施例结构示意图。本实施例中所描述的基于VRDS 4D的病情分析装置,包括:获取单元401、处理单元402、识别单元403和分析单元404,具体如下:
所述获取单元401,用于获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像;
所述处理单元402,用于对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据;
所述识别单元403,用于基于所述目标影像数据,识别所述目标用户对应的发病部位,所述发病部位为所述多个人体器官中的一个或者多个部位;
所述分析单元404,用于针对所述发病部位进行病情分析,得到目标病情分析结果。
可以看出,通过本申请实施例所描述的基于VRDS 4D的病情分析装置,可获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像,上述人体器官包括以下至少一种:耳部、鼻部和喉部,对多张扫描图像进行处理,得到目标用户对应的目标4D影像,该目标4D影像包括目标用户对应的目标影像数据,基于目标影 像数据,识别目标用户对应的发病部位,发病部位为多个人体器官中的一个或者多个部位,针对发病部位进行病情分析,得到目标病情分析结果,如此,可通过对扫描图像的分析处理,得到目标用户的发病部位,并针对该发病部位进行病情分析,以得到病情分析结果,有利于提高病情分析的准确性和效率。
在一个可能的示例中,在基于所述目标影像数据,识别所述目标用户对应的发病部位方面,上述识别单元403具体用于:
基于所述血管数据集,选取与所述多个人体器官相关联的多个目标血管数据集;
获取所述多个目标血管数据集对应的血管中心线数据集,所述血管中心线为所述目标血管剖面中每个中心点之间的连线;
根据所述血管中心线数据集,确定与所述多个人体器官对应的血管分布数据集,其中,每一所述人体器官对应的一个血管分布数据;
根据所述血管分布数据集,确定多个目标器官,所述多个目标器官中包括以下至少一种:耳部、鼻部和喉部;
获取所述目标影像集中所述多个目标器官对应的多个影像数据,每一目标器官对应一个影像数据;
根据所述多个影像数据,识别所述目标用户对应的发病部位。
在一个可能的示例中,在根据所述多个影像数据,识别所述目标用户对应的发病部位方面,上述识别单元403具体还用于:
根据所述多个影像数据,生成所述多个目标器官对应的多个特征信息,所述特征信息包括以下至少一种:颜色、形状、位置、大小;
根据所述多个特征信息,识别所述目标用户对应的所述发病部位。
在一个可能的示例中,在根据所述血管分布数据集,确定多个目标器官方面,上述识别单元403具体还用于:
获取所述血管数据集中所述多个人体器官对应的血管半径数据集;
根据所述血管半径数据集,确定所述血管分布数据集中超过预设阈值的血管半径对应的血管畸变分布数据集;
通过所述血管畸变分布数据集,确定所述血管畸变范围;
根据所述血管畸变分布数据集与所述血管畸变范围,确定所述多个目标器官。
在一个可能的示例中,在根据所述多个特征信息,识别所述多个目标器官中的发病部位方面,上述识别单元403具体还用于:
获取预设发病部位识别模型;
将所述多个特征信息输入所述预设发病部位识别模型,得到所述多个特征信息中每一特征信息对应的特征概率,得到多个特征概率;
计算所述多个特征概率中的超过预设概率值对应的至少一个特征信息;
根据所述至少一个特征信息,确定所述多个目标器官中的发病部位。
在一个可能的示例中,在针对所述发病部位进行病情分析,得到目标病情分析结果方面,上述分析单元404具体用于:
获取预设疾病特征数据库对应的多组预设疾病特征信息,所述预设疾病特征数据库中包括多个疾病类型,每一疾病类型对应一组预设疾病特征信息;
将所述发病部位对应的多个特征信息与所述多组预设疾病特征信息一一匹配,得到多个匹配值,每一匹配值对应一种所述疾病类型;
获取所述多个匹配值中最大匹配值对应的疾病类型为目标疾病类型;
按照预设的疾病类型与病情分析结果之间的映射关系,确定所述目标用户对应的目标病情分析结果。
在一个可能的示例中,在基于所述目标影像数据,识别所述目标用户对应的发病部位方面,上述识别单元403具体还用于:
根据所述目标影像数据,生成所述多个人体器官中任一人体器官i对应的第一目标影像数据,所述第一目标影像数据中包括至少k个空间位置数据,所述k个空间位置数据对应k个第一影像数据,每个所述空间位置数据对应一个第一影像数据,其中,k为正整数;
根据所述k个空间位置数据,识别所述目标用户对应的发病部位。
在一个可能的示例中,在根据所述k个空间位置数据,识别所述目标用户对应的发病部位方面,上述识别单元403具体还用于:
依据所述k个空间位置数据对所述人体器官i进行定位;
遍历所述k个空间位置数据对应的所述k个第一影像数据,得到p个异常第一影像数据,所述p个异常第一影像数据对应的所述p个空间位置数据对应的部位即为所述发病部位,其中,p为小于k的整数。
在一个可能的示例中,在对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据方面,上述处理单元402具体用于:
针对所述多张扫描图像执行第一预设处理得到位图BMP数据源;
将所述BMP数据源导入预设的VRDS医学网络模型,得到第一医学影像数据,所述第一医学影像数据包括人体器官数据集和血管数据集,所述人体器官数据集中包括所述多个人体器官对应的多个人体器官数据;
将所述第一医学影像数据导入预设的交叉血管网络模型,得到第二医学影像数据,所述第二医学影像数据包括所述人体器官数据集和血管数据集;
针对所述第二医学影像数据执行第二预设处理得到所述目标4D影像。
可以理解的是,本实施例的基于VRDS 4D的病情分析装置的各程序模块的功能可根据上述方法实施例中的方法具体实现,其具体实现过程可以参照上述方法实施例的相关描述, 此处不再赘述。
本申请实施例还提供一种计算机存储介质,其中,该计算机存储介质存储用于电子数据交换的计算机程序,该计算机程序使得计算机执行如上述方法实施例中记载的任何一种基于VRDS 4D的病情分析方法的部分或全部步骤。
本申请实施例还提供一种计算机程序产品,所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质,所述计算机程序可操作来使计算机执行如上述方法实施例中记载的任何一种基于VRDS 4D的病情分析方法的部分或全部步骤。
需要说明的是,对于前述的各方法实施例,为了简单描述,故将其都表述为一系列的动作组合,但是本领域技术人员应该知悉,本申请并不受所描述的动作顺序的限制,因为依据本申请,某些步骤可以采用其他顺序或者同时进行。其次,本领域技术人员也应该知悉,说明书中所描述的实施例均属于优选实施例,所涉及的动作和模块并不一定是本申请所必须的。
在上述实施例中,对各个实施例的描述都各有侧重,某个实施例中没有详述的部分,可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中,应该理解到,所揭露的装置,可通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个***,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件程序模块的形式实现。
所述集成的单元如果以软件程序模块的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储器中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储器中,包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储器包括:U盘、只读存储器(read-only memory,ROM)、随机存取存储器(random access memory,RAM)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,该程序可以存储于一计算机可读存储器中,存储器可以包括:闪存盘、ROM、RAM、磁盘或光盘等。
以上对本申请实施例进行了详细介绍,本文中应用了具体个例对本申请的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本申请的方法及其核心思想;同时,对于本领域的一般技术人员,依据本申请的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本申请的限制。

Claims (20)

  1. 一种基于VRDS 4D的病情分析方法,其特征在于,包括:
    获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像,所述人体器官包括以下至少一种:耳部、鼻部和喉部;
    对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据;
    基于所述目标影像数据,识别所述目标用户对应的发病部位,所述发病部位为所述多个人体器官中的一个或者多个部位;
    针对所述发病部位进行病情分析,得到目标病情分析结果。
  2. 根据权利要求1所述的方法,其特征在于,若所述目标影像数据至少包括血管数据集,所述基于所述目标影像数据,识别所述目标用户对应的发病部位,包括:
    基于所述血管数据集,选取与所述多个人体器官相关联的多个目标血管数据集;
    获取所述多个目标血管数据集对应的血管中心线数据集,所述血管中心线为所述目标血管剖面中每个中心点之间的连线;
    根据所述血管中心线数据集,确定与所述多个人体器官对应的血管分布数据集,其中,每一所述人体器官对应的一个血管分布数据;
    根据所述血管分布数据集,确定多个目标器官,所述多个目标器官中包括以下至少一种:耳部、鼻部和喉部;
    获取所述目标影像集中所述多个目标器官对应的多个影像数据,每一目标器官对应一个影像数据;
    根据所述多个影像数据,识别所述目标用户对应的发病部位。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述多个影像数据,识别所述目标用户对应的发病部位,包括:
    根据所述多个影像数据,生成所述多个目标器官对应的多个特征信息,所述特征信息包括以下至少一种:颜色、形状、位置、大小;
    根据所述多个特征信息,识别所述目标用户对应的所述发病部位。
  4. 根据权利要求2所述的方法,其特征在于,所述根据所述血管分布数据集,确定多个目标器官,包括:
    获取所述血管数据集中所述多个人体器官对应的血管半径数据集;
    根据所述血管半径数据集,确定所述血管分布数据集中超过预设阈值的血管半径对应的血管畸变分布数据集;
    通过所述血管畸变分布数据集,确定所述血管畸变范围;
    根据所述血管畸变分布数据集与所述血管畸变范围,确定所述多个目标器官。
  5. 根据权利要求3所述的方法,其特征在于,所述根据所述多个特征信息,识别所述 多个目标器官中的发病部位,包括:
    获取预设发病部位识别模型;
    将所述多个特征信息输入所述预设发病部位识别模型,得到所述多个特征信息中每一特征信息对应的特征概率,得到多个特征概率;
    计算所述多个特征概率中的超过预设概率值对应的至少一个特征信息;
    根据所述至少一个特征信息,确定所述多个目标器官中的发病部位。
  6. 根据权利要求1-5任一项所述的方法,其特征在于,所述针对所述发病部位进行病情分析,得到目标病情分析结果,包括:
    获取预设疾病特征数据库对应的多组预设疾病特征信息,所述预设疾病特征数据库中包括多个疾病类型,每一疾病类型对应一组预设疾病特征信息;
    将所述发病部位对应的多个特征信息与所述多组预设疾病特征信息一一匹配,得到多个匹配值,每一匹配值对应一种所述疾病类型;
    获取所述多个匹配值中最大匹配值对应的疾病类型为目标疾病类型;
    按照预设的疾病类型与病情分析结果之间的映射关系,确定所述目标用户对应的目标病情分析结果。
  7. 根据权利要求1所述的方法,其特征在于,所述基于所述目标影像数据,识别所述目标用户对应的发病部位,所述方法还包括:
    根据所述目标影像数据,生成所述多个人体器官中任一人体器官i对应的第一目标影像数据,所述第一目标影像数据中包括至少k个空间位置数据,所述k个空间位置数据对应k个第一影像数据,每个所述空间位置数据对应一个第一影像数据,其中,k为正整数;
    根据所述k个空间位置数据,识别所述目标用户对应的发病部位。
  8. 根据权利要求7所述的方法,其特征在于,所述根据所述k个空间位置数据,识别所述目标用户对应的发病部位,包括:
    依据所述k个空间位置数据对所述人体器官i进行定位;
    遍历所述k个空间位置数据对应的所述k个第一影像数据,得到p个异常第一影像数据,所述p个异常第一影像数据对应的所述p个空间位置数据对应的部位即为所述发病部位,其中,p为小于k的整数。
  9. 根据权利要求1所述的方法,其特征在于,所述对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据,包括:
    针对所述多张扫描图像执行第一预设处理得到位图BMP数据源;
    将所述BMP数据源导入预设的VRDS医学网络模型,得到第一医学影像数据,所述第一医学影像数据包括人体器官数据集和血管数据集,所述人体器官数据集中包括所述多个人体器官对应的多个人体器官数据;
    将所述第一医学影像数据导入预设的交叉血管网络模型,得到第二医学影像数据,所述第二医学影像数据包括所述人体器官数据集和血管数据集;
    针对所述第二医学影像数据执行第二预设处理得到所述目标4D影像。
  10. 一种基于VRDS 4D的病情分析装置,其特征在于,包括:
    获取单元,用于获取目标用户的多个人体器官的扫描图像,得到多张扫描图像,每一人体器官至少对应一张扫描图像;
    处理单元,用于对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像,所述目标4D影像包括所述目标用户对应的目标影像数据;
    识别单元,用于基于所述目标影像数据,识别所述目标用户对应的发病部位,所述发病部位为所述多个人体器官中的一个或者多个部位;
    分析单元,用于针对所述发病部位进行病情分析,得到目标病情分析结果。
  11. 根据权利要求10所述的装置,其特征在于,若所述目标影像数据至少包括血管数据集,所述基于所述目标影像数据,识别所述目标用户对应的发病部位方面,所述识别单元具体用于:
    基于所述血管数据集,选取与所述多个人体器官相关联的多个目标血管数据集;
    获取所述多个目标血管数据集对应的血管中心线数据集,所述血管中心线为所述目标血管剖面中每个中心点之间的连线;
    根据所述血管中心线数据集,确定与所述多个人体器官对应的血管分布数据集,其中,每一所述人体器官对应的一个血管分布数据;
    根据所述血管分布数据集,确定多个目标器官,所述多个目标器官中包括以下至少一种:耳部、鼻部和喉部;
    获取所述目标影像集中所述多个目标器官对应的多个影像数据,每一目标器官对应一个影像数据;
    根据所述多个影像数据,识别所述目标用户对应的发病部位。
  12. 根据权利要求11所述的装置,其特征在于,在所述根据所述多个影像数据,识别所述目标用户对应的发病部位方面,所述识别单元具体还用于:
    根据所述多个影像数据,生成所述多个目标器官对应的多个特征信息,所述特征信息包括以下至少一种:颜色、形状、位置、大小;
    根据所述多个特征信息,识别所述目标用户对应的所述发病部位。
  13. 根据权利要求11所述的装置,其特征在于,在所述根据所述血管分布数据集,确定多个目标器官方面,所述确定单元具体用于:
    获取所述血管数据集中所述多个人体器官对应的血管半径数据集;
    根据所述血管半径数据集,确定所述血管分布数据集中超过预设阈值的血管半径对应的血管畸变分布数据集;
    通过所述血管畸变分布数据集,确定所述血管畸变范围;
    根据所述血管畸变分布数据集与所述血管畸变范围,确定所述多个目标器官。
  14. 根据权利要求13所述的装置,其特征在于,在所述根据所述多个特征信息,识别所述多个目标器官中的发病部位方面,所述确定单元具体还用于:
    获取预设发病部位识别模型;
    将所述多个特征信息输入所述预设发病部位识别模型,得到所述多个特征信息中每一特征信息对应的特征概率,得到多个特征概率;
    计算所述多个特征概率中的超过预设概率值对应的至少一个特征信息;
    根据所述至少一个特征信息,确定所述多个目标器官中的发病部位。
  15. 根据权利要求10-14任一项所述的装置,其特征在于,在所述针对所述发病部位进行病情分析,得到目标病情分析结果方面,所述分析单元具体还用于:
    获取预设疾病特征数据库对应的多组预设疾病特征信息,所述预设疾病特征数据库中包括多个疾病类型,每一疾病类型对应一组预设疾病特征信息;
    将所述发病部位对应的多个特征信息与所述多组预设疾病特征信息一一匹配,得到多个匹配值,每一匹配值对应一种所述疾病类型;
    获取所述多个匹配值中最大匹配值对应的疾病类型为目标疾病类型;
    按照预设的疾病类型与病情分析结果之间的映射关系,确定所述目标用户对应的目标病情分析结果。
  16. 根据权利要求10所述的装置,其特征在于,在所述基于所述目标影像数据,识别所述目标用户对应的发病部位方面,所述识别单元具体还用于:
    根据所述目标影像数据,生成所述多个人体器官中任一人体器官i对应的第一目标影像数据,所述第一目标影像数据中包括至少k个空间位置数据,所述k个空间位置数据对应k个第一影像数据,每个所述空间位置数据对应一个第一影像数据,其中,k为正整数;
    根据所述k个空间位置数据,识别所述目标用户对应的发病部位。
  17. 根据权利要求16所述的装置,其特征在于,在所述根据所述k个空间位置数据,识别所述目标用户对应的发病部位方面,所述识别单元具体还用于:
    依据所述k个空间位置数据对所述人体器官i进行定位;
    遍历所述k个空间位置数据对应的所述k个第一影像数据,得到p个异常第一影像数据,所述p个异常第一影像数据对应的所述p个空间位置数据对应的部位即为所述发病部位,其中,p为小于k的整数。
  18. 根据权利要求10所述的装置,其特征在于,在所述对所述多张扫描图像进行处理,得到所述目标用户对应的目标4D影像方面,若所述目标4D影像包括所述目标用户对应的目标影像数据,所述处理单元具体用于:
    针对所述多张扫描图像执行第一预设处理得到位图BMP数据源;
    将所述BMP数据源导入预设的VRDS医学网络模型,得到第一医学影像数据,所述第一医学影像数据包括人体器官数据集和血管数据集,所述人体器官数据集中包括所述多个人体器官对应的多个人体器官数据;
    将所述第一医学影像数据导入预设的交叉血管网络模型,得到第二医学影像数据,所述第二医学影像数据包括所述人体器官数据集和血管数据集;
    针对所述第二医学影像数据执行第二预设处理得到所述目标4D影像。
  19. 一种医学成像装置,其特征在于,包括处理器、存储器、通信接口,以及一个或多个程序,所述一个或多个程序被存储在所述存储器中,并且被配置由所述处理器执行,所述程序包括用于执行如权利要求1-9任一项所述的方法中的步骤的指令。
  20. 一种计算机可读存储介质,其特征在于,存储用于电子数据交换的计算机程序,其中,所述计算机程序使得计算机执行如权利要求1-9任一项所述的方法。
PCT/CN2019/114475 2019-10-30 2019-10-30 基于vrds 4d的病情分析方法及相关产品 WO2021081839A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2019/114475 WO2021081839A1 (zh) 2019-10-30 2019-10-30 基于vrds 4d的病情分析方法及相关产品
CN201980099991.4A CN114341996A (zh) 2019-10-30 2019-10-30 基于vrds 4d的病情分析方法及相关产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/114475 WO2021081839A1 (zh) 2019-10-30 2019-10-30 基于vrds 4d的病情分析方法及相关产品

Publications (1)

Publication Number Publication Date
WO2021081839A1 true WO2021081839A1 (zh) 2021-05-06

Family

ID=75715700

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/114475 WO2021081839A1 (zh) 2019-10-30 2019-10-30 基于vrds 4d的病情分析方法及相关产品

Country Status (2)

Country Link
CN (1) CN114341996A (zh)
WO (1) WO2021081839A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11348228B2 (en) 2017-06-26 2022-05-31 The Research Foundation For The State University Of New York System, method, and computer-accessible medium for virtual pancreatography

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160086330A1 (en) * 2014-09-19 2016-03-24 Siemens Aktiengesellschaft Method and apparatus for determining a position of an object from mri images
CN108447046A (zh) * 2018-02-05 2018-08-24 龙马智芯(珠海横琴)科技有限公司 病灶的检测方法和装置、设备、计算机可读存储介质
CN109472780A (zh) * 2018-10-26 2019-03-15 强联智创(北京)科技有限公司 一种颅内动脉瘤图像的形态学参数的测量方法及***
CN109544534A (zh) * 2018-11-26 2019-03-29 上海联影智能医疗科技有限公司 一种病灶图像检测装置、方法和计算机可读存储介质
CN109949899A (zh) * 2019-02-28 2019-06-28 未艾医疗技术(深圳)有限公司 图像三维测量方法、电子设备、存储介质及程序产品
CN110379492A (zh) * 2019-07-24 2019-10-25 复旦大学附属中山医院青浦分院 一种全新的ai+pacs***及其检查报告构建方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160086330A1 (en) * 2014-09-19 2016-03-24 Siemens Aktiengesellschaft Method and apparatus for determining a position of an object from mri images
CN108447046A (zh) * 2018-02-05 2018-08-24 龙马智芯(珠海横琴)科技有限公司 病灶的检测方法和装置、设备、计算机可读存储介质
CN109472780A (zh) * 2018-10-26 2019-03-15 强联智创(北京)科技有限公司 一种颅内动脉瘤图像的形态学参数的测量方法及***
CN109544534A (zh) * 2018-11-26 2019-03-29 上海联影智能医疗科技有限公司 一种病灶图像检测装置、方法和计算机可读存储介质
CN109949899A (zh) * 2019-02-28 2019-06-28 未艾医疗技术(深圳)有限公司 图像三维测量方法、电子设备、存储介质及程序产品
CN110379492A (zh) * 2019-07-24 2019-10-25 复旦大学附属中山医院青浦分院 一种全新的ai+pacs***及其检查报告构建方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11348228B2 (en) 2017-06-26 2022-05-31 The Research Foundation For The State University Of New York System, method, and computer-accessible medium for virtual pancreatography

Also Published As

Publication number Publication date
CN114341996A (zh) 2022-04-12

Similar Documents

Publication Publication Date Title
WO2020119679A1 (zh) 三维左心房分割方法、装置、终端设备及存储介质
AU2019430369B2 (en) VRDS 4D medical image-based vein Ai endoscopic analysis method and product
CN112861961B (zh) 肺血管分类方法及装置、存储介质及电子设备
WO2021081771A1 (zh) 基于vrds ai医学影像的心脏冠脉的分析方法和相关装置
WO2021030995A1 (zh) 基于vrds ai下腔静脉影像的分析方法及产品
WO2020173054A1 (zh) Vrds 4d医学影像处理方法及产品
WO2021081839A1 (zh) 基于vrds 4d的病情分析方法及相关产品
WO2020168695A1 (zh) 基于VRDS 4D医学影像的肿瘤与血管Ai处理方法及产品
WO2020168694A1 (zh) 基于VRDS 4D医学影像的肿瘤Ai处理方法及产品
WO2021081850A1 (zh) 基于vrds 4d医学影像的脊椎疾病识别方法及相关装置
WO2021081846A1 (zh) 静脉血管肿瘤影像处理方法及相关产品
WO2020168697A1 (zh) 基于VRDS 4D医学影像的栓塞的Ai识别方法及产品
WO2021081836A1 (zh) 基于vrds 4d医学影像的胃肿瘤识别方法及相关产品
WO2021081845A1 (zh) 一种基于vrds ai的肝脏肿瘤和血管分析方法及相关产品
WO2021081772A1 (zh) 基于vrds ai脑部影像的分析方法和相关装置
WO2021030994A1 (zh) 基于vrds ai静脉影像的识别方法及产品
CN116630326B (zh) 一种基于鼻颅镜***的颅内肿瘤定位***
WO2021081842A1 (zh) 基于vrds ai医学影像的肠肿瘤与血管分析方法和相关装置

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: 19950961

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19950961

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 19.10.2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19950961

Country of ref document: EP

Kind code of ref document: A1