CN112819925A - Method and device for processing focus labeling, electronic equipment and medium - Google Patents
Method and device for processing focus labeling, electronic equipment and medium Download PDFInfo
- Publication number
- CN112819925A CN112819925A CN202110220535.XA CN202110220535A CN112819925A CN 112819925 A CN112819925 A CN 112819925A CN 202110220535 A CN202110220535 A CN 202110220535A CN 112819925 A CN112819925 A CN 112819925A
- Authority
- CN
- China
- Prior art keywords
- image
- labeling
- marking
- focus
- lesion
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000002372 labelling Methods 0.000 title claims abstract description 218
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012545 processing Methods 0.000 title claims abstract description 23
- 230000003902 lesion Effects 0.000 claims abstract description 128
- 238000009877 rendering Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 15
- 230000000007 visual effect Effects 0.000 claims description 12
- 238000012797 qualification Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003672 processing method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002595 magnetic resonance imaging Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Physics & Mathematics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a method and a device for processing focus labeling, electronic equipment and a medium. Wherein, the method comprises the following steps: determining the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a focal region; if the marking information display event is detected, rendering the marking information to a target image to obtain a focus marking image; and determining the labeling result of the lesion labeling image according to the preset labeling image of the lesion labeling image and the target image. The embodiment of the invention can add the marking information of a plurality of people to the original focus image and can carry out marking inspection by combining the preset marking image, thereby effectively improving the marking efficiency of the focus image.
Description
Technical Field
The embodiment of the invention relates to the technical field of image processing, in particular to a method and a device for processing focus marks, electronic equipment and a medium.
Background
With the continuous development of artificial intelligence technology, the application of the artificial intelligence technology in the medical field is gradually increased; currently, the artificial intelligence and medical treatment commonly include eight application scenarios, such as virtual assistant, medical image, and assisted diagnosis and treatment, wherein the medical image is one of the most popular application scenarios. When the medical image is marked with a focus, a marking person mainly searches the medical image to be marked through a marking system, and marks the medical image on the basis of the medical image, such as drawing a circle or marking different shape symbols, so as to mark the focus area in the medical image.
The defects of the scheme are as follows: the marking is directly carried out on the original medical image, the marking of multiple persons cannot be realized, if the marking is carried out on the second person, the marking is carried out on the basis of the first marking, and the marking efficiency of the focus image is reduced.
Disclosure of Invention
The embodiment of the application provides a method and a device for processing focus labeling, electronic equipment and a medium, which can add labeling information of a plurality of people into an original focus image and can perform labeling inspection by combining a preset labeling image, thereby effectively improving the labeling efficiency of the focus image.
In a first aspect, an embodiment of the present invention provides a method for processing a lesion marking, including:
determining the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a lesion region;
if a marking information display event is detected, rendering the marking information to the target image to obtain a focus marking image;
and determining the labeling result of the lesion labeling image according to the lesion labeling image and the preset labeling image of the target image.
Optionally, determining annotation information of at least two annotating persons on the target image includes:
responding to the labeling requests of at least two labeling personnel to a target image, and copying the target image to a visual area;
obtaining labeling information of the target image according to labeling operation of the at least two labeling personnel on the target image in the visual area; wherein the labeling information comprises labeling coordinates and/or a lesion type.
Optionally, rendering the annotation information to the target image to obtain a lesion annotation image, including:
according to the identity of the marking personnel, carrying out color identification on the marking information to obtain marking coordinates and a focus type associated with the marking personnel;
and rendering the marking coordinate and the focus type to the target image to obtain a focus marking image.
Optionally, determining a labeling result of the lesion labeling image according to the lesion labeling image and a preset labeling image of the target image, including:
carrying out image matching on the focus labeling image and a preset labeling image of the target image to obtain a labeling qualified value of the focus labeling image;
and determining the labeling result of the lesion labeling image according to the labeling qualified value of the lesion labeling image.
Optionally, determining the labeling result of the lesion labeling image according to the labeling qualified value of the lesion labeling image includes:
detecting whether the labeling qualified value of the focus labeling image is larger than a qualified threshold value;
if so, determining that the labeling result of the focus labeling image is accurate, and setting the state of the labeling result of the focus labeling image as pass.
Optionally, the method further includes:
acquiring a lesion marking image with a marking result in a passing state;
and training a focus marking model according to the marking coordinates and the focus type displayed in the focus marking image.
Optionally, the method further includes:
and if a marking event of the focus image is detected, inputting the focus image into a focus marking model, and determining a focus area and a focus type of the focus image according to the output of the focus marking model.
In a second aspect, an embodiment of the present invention provides a device for processing lesion marking, including:
the information determining module is used for determining the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a lesion region;
the image determining module is used for rendering the marking information to the target image to obtain a focus marking image if a marking information display event is detected;
and the result determining module is used for determining the labeling result of the focus labeling image according to the focus labeling image and the preset labeling image of the target image.
Optionally, the information determining module is specifically configured to:
responding to the labeling requests of at least two labeling personnel to a target image, and copying the target image to a visual area;
obtaining labeling information of the target image according to labeling operation of the at least two labeling personnel on the target image in the visual area; wherein the labeling information comprises labeling coordinates and/or a lesion type.
Optionally, the image determining module is specifically configured to:
according to the identity of the marking personnel, carrying out color identification on the marking information to obtain marking coordinates and a focus type associated with the marking personnel;
and rendering the marking coordinate and the focus type to the target image to obtain a focus marking image.
Optionally, the result determining module includes: a qualified value determining unit and a labeling result determining unit;
a qualified value determining unit, configured to perform image matching on the lesion marking image and a preset marking image of the target image to obtain a marking qualified value of the lesion marking image;
and the marking result determining unit is used for determining the marking result of the focus marking image according to the marking qualified value of the focus marking image.
Optionally, the labeling result determining unit is specifically configured to:
detecting whether the labeling qualified value of the focus labeling image is larger than a qualified threshold value;
if so, determining that the labeling result of the focus labeling image is accurate, and setting the state of the labeling result of the focus labeling image as pass.
Optionally, the method further includes: the system comprises an image acquisition module and a model training module;
the image acquisition module is used for acquiring a lesion marking image with a marking result in a passing state;
and the model training module is used for training a focus marking model according to the marking coordinates and the focus type displayed in the focus marking image.
Optionally, the method further includes: a lesion marking module;
and the focus marking module is used for inputting the focus image into a focus marking model if a marking event of the focus image is detected, and determining a focus area and a focus type of the focus image according to the output of the focus marking model.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of lesion tagging in accordance with any one of the embodiments of the present invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the method for processing lesion marking according to any of the embodiments of the present invention.
The embodiment of the invention determines the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a focal region; if the marking information display event is detected, rendering the marking information to a target image to obtain a focus marking image; and determining the labeling result of the lesion labeling image according to the preset labeling image of the lesion labeling image and the target image. According to the embodiment of the invention, the marking information of a plurality of persons can be added into the original focus image, and the marking inspection can be carried out by combining the preset marking image, so that the marking efficiency of the focus image is effectively improved.
Drawings
FIG. 1 is a flowchart illustrating a method for processing lesion marking according to a first embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for labeling a lesion according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a processing apparatus for lesion marking according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device in the fourth embodiment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart illustrating a method for processing lesion marking according to a first embodiment of the present invention. The embodiment can be applied to the condition of accurately checking the lesion marking results which are simultaneously carried out by a plurality of people. The method of the present embodiment may be performed by a lesion marking processing apparatus, which may be implemented in hardware and/or software and may be configured in an electronic device. The method for processing lesion marking according to any embodiment of the present application can be realized. As shown in fig. 1, the method specifically includes the following steps:
s110, determining the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a lesion area.
In this embodiment, the target image may be an image with a lesion region, such as CT (Computed Tomography) and MRI (Magnetic Resonance Imaging) of a patient; the annotator may be a medical person, such as a lesion annotation student, for performing lesion annotation on the target image to determine a lesion region in the target image.
Wherein, the marking personnel can mark the focus of the target image on the marking system; specifically, the embodiment can support a plurality of annotating personnel to log in own account numbers in the annotation system for independent annotation at the same time, and the annotation system records the annotation information of different annotating personnel in the information database, so that different annotation data are isolated from each other and do not affect each other.
It should be noted that, in this embodiment, the annotation information of the target image does not include the target image, but is the annotation content other than the target image content; for example, if the annotation person draws a circle on the target image, the annotation information may be the coordinate point distribution of the circle on the target image.
And S120, if the marking information display event is detected, rendering the marking information to the target image to obtain a focus marking image.
In this embodiment, the annotation information display event is an externally triggered information viewing request received by the annotation system, for example, the information viewing request may be an information viewing request initiated by an annotation person on the annotation system through a virtual button; the focus labeling image is a superposition display of a target image and labeling information of the target image by at least two labeling personnel, namely, external labeling information is added on the basis of the target image, and the external labeling information is searched in an information database by a labeling system according to the target image.
Before rendering the annotation information to the target image to obtain the lesion annotation image, the embodiment may further include: responding to the annotation information display event, displaying a target image associated with the event according to the annotation information, and searching annotation information associated with the target image identifier from the information database; wherein, the information database stores the incidence relation between the target image identification and the labeling information; the target image identification may be a name or a custom character of the target image, so that the information database may efficiently manage annotation information associated with a plurality of target images.
And S130, determining a labeling result of the lesion labeling image according to the lesion labeling image and a preset labeling image of the target image.
In this embodiment, the preset labeling image of the target image is an image obtained by accurately labeling a lesion area in the target image, and may be obtained by labeling the lesion area in the target image by a medical lesion related authoritative specialist. Specifically, whether the lesion marking image is accurate or not can be evaluated through the matching result of the lesion marking image and the preset marking image of the target image, so that the marking result of the lesion marking image can be obtained.
The embodiment of the invention determines the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a focal region; if the marking information display event is detected, rendering the marking information to a target image to obtain a focus marking image; and determining the labeling result of the lesion labeling image according to the preset labeling image of the lesion labeling image and the target image. According to the embodiment of the invention, the marking information of a plurality of persons can be added into the original focus image, and the marking inspection can be carried out by combining the preset marking image, so that the marking efficiency of the focus image is effectively improved.
Example two
Fig. 2 is a flowchart illustrating a method for processing lesion marking according to a second embodiment of the present invention. The embodiment is further expanded and optimized on the basis of the embodiment, and can be combined with any optional alternative in the technical scheme. As shown in fig. 2, the method includes:
s210, responding to the labeling requests of at least two labeling personnel to the target image, and copying the target image to a visualization area.
In this embodiment, the target image is pre-stored in an image database of the annotation system, so that the annotation person can perform lesion annotation on the target image in the annotation system. The marking personnel can enter the image marking interface by clicking a virtual button 'focus marking' on the marking system interface and carry out marking operation in a visual area of the image marking interface.
In this embodiment, the target image is copied into the visual area, so as to avoid the problem that the annotation operation of other annotation personnel is affected by the direct annotation of the annotation personnel on the original target image, and the annotation system can support multiple people to perform annotation processing simultaneously.
S220, obtaining annotation information of the target image according to the annotation operation of at least two annotation personnel on the target image in the visual area; wherein the labeling information comprises labeling coordinates and/or a focus type.
In this embodiment, a annotating person can perform a sketching operation, such as marking an arbitrary figure, on a screen interface of an electronic device by using a touch screen or a mouse in the electronic device where the annotation system is located in the annotation system; the marking coordinates can be boundary point coordinates of a graph written by a marking person in a visual area of the marking system; the lesion type may support writing, or may be replaced by a string corresponding to a type preset in the annotation system, such as a character a, b.
S230, if a marking information display event is detected, carrying out color marking on the marking information according to the identity of a marking person to obtain a marking coordinate and a focus type associated with the marking person; and rendering the marking coordinates and the focus types to the target image to obtain a focus marking image.
In this embodiment, the identity of the annotating personnel can be evaluated according to the service level of the annotating personnel, and the color of the annotation information of different annotating personnel is distinguished, so as to accurately distinguish the annotation information of different annotating personnel.
Rendering the labeling coordinate and the lesion type to a target image to obtain a lesion labeling image, wherein the rendering the labeling coordinate and the lesion type to the target image may include: classifying the marking information according to the color identification to obtain marking coordinates and focus types corresponding to different color identifications; and filling the marking coordinates and the focus types into a target image based on the color marks of different marking information to obtain a focus marking image with a plurality of marking information.
S240, carrying out image matching on the focus labeling image and a preset labeling image of the target image to obtain a labeling qualified value of the focus labeling image; and determining the labeling result of the lesion labeling image according to the labeling qualified value of the lesion labeling image.
In this embodiment, the lesion marking image is image-matched with the preset marking image of the target image, so as to obtain whether a lesion area marked in the lesion marking image is matched with a lesion area in the preset marking image, and a marking pass value of the lesion marking image is evaluated according to a matching result. According to the embodiment, the image matching can be performed according to the focus labeling image and the preset labeling image of the target image to determine the labeling qualification degree of the focus labeling image, so that the labeling result of the focus labeling image can be visually reflected.
In this embodiment, optionally, determining a labeling result of the lesion labeling image according to the labeling qualified value of the lesion labeling image includes:
detecting whether the labeling qualified value of the focus labeling image is larger than a qualified threshold value;
if so, determining that the labeling result of the lesion labeling image is accurate, and setting the state of the labeling result of the lesion labeling image as pass.
The qualified threshold may be a similar critical value of a lesion region in the lesion labeling image and a lesion region in the preset labeling image, and may be determined according to a ratio of an area of the lesion region in the lesion labeling image to an area of the lesion region in the preset labeling image. According to the method and the device, the qualification of the lesion marking image can be verified based on the preset qualification threshold, so that the lesion marking image with poor marking is prevented from influencing the marking result of the target image, and the accuracy of lesion marking of the target image is effectively improved.
On the basis of the foregoing embodiment, optionally, the method of this embodiment further includes:
acquiring a lesion marking image with a marking result in a passing state;
and training a focus marking model according to the marking coordinates and the focus type displayed in the focus marking image.
In this embodiment, in the labeling system, a label identifier is recorded for each labeling result of the target image to obtain a lesion labeling image, so as to effectively distinguish the lesion labeling image with qualified identifier, which is used as a basis for later-stage training of an AI (Artificial Intelligence) model.
Training a focus labeling model according to the labeling coordinate and the focus type displayed in the focus labeling image, wherein the training comprises the following steps: training according to labeling coordinates displayed in a lesion labeling image to obtain an initial coordinate model, verifying the initial coordinate model, and if the qualification rate of the initial coordinate model exceeds a first threshold value, taking the initial coordinate model as a lesion coordinate model for outputting lesion area coordinates according to an input image to be labeled; and training according to the type of the focus displayed in the focus labeling image to obtain an initial type model, verifying the initial type model, and if the qualification rate of the initial type model exceeds a first threshold value, taking the initial type model as the focus type model for outputting the type of the focus according to the input image to be labeled.
In the embodiment, the state of the labeling result is used for training the focus labeling model for the passing focus labeling image, so that the problem that the accuracy of the model is reduced by the unqualified focus labeling image of the labeling result can be avoided, and the accuracy of the focus labeling model is enhanced.
On the basis of the foregoing embodiment, optionally, the method of this embodiment further includes:
and if the labeling event of the focus image is detected, inputting the focus image into a focus labeling model, and determining the focus area and the focus type of the focus image according to the output of the focus labeling model.
In this embodiment, the lesion marking model may include a lesion coordinate model and a lesion type model, and by inputting the lesion image into the lesion coordinate model, the lesion area coordinate of the lesion image may be determined according to the output of the lesion coordinate model; the focus image is input into the focus type model, and the focus type of the focus image can be determined according to the output of the focus type model. According to the embodiment, the focus image needing to be subjected to focus labeling can be input into the pre-trained focus labeling model, the problem that the judgment result is inaccurate due to the fact that the focus image needs to be manually judged to be subjected to the judgment of the lesion area and the focus type is solved, and therefore the labeling result of the focus image can be effectively and quickly obtained.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a processing apparatus for lesion marking according to a third embodiment of the present invention, which is applicable to accurately check lesion marking results performed by multiple persons at the same time. The device is configured in electronic equipment, and can realize the processing method of the lesion marking in any embodiment of the application. The device specifically comprises the following steps:
the information determining module 310 is configured to determine labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a lesion region;
an image determining module 320, configured to render the annotation information onto the target image to obtain a lesion annotation image if an annotation information display event is detected;
a result determining module 330, configured to determine a labeling result of the lesion labeling image according to the lesion labeling image and a preset labeling image of the target image.
On the basis of the foregoing embodiment, optionally, the information determining module 310 is specifically configured to:
responding to the labeling requests of at least two labeling personnel to a target image, and copying the target image to a visual area;
obtaining labeling information of the target image according to labeling operation of the at least two labeling personnel on the target image in the visual area; wherein the labeling information comprises labeling coordinates and/or a lesion type.
On the basis of the foregoing embodiment, optionally, the image determining module 320 is specifically configured to:
according to the identity of the marking personnel, carrying out color identification on the marking information to obtain marking coordinates and a focus type associated with the marking personnel;
and rendering the marking coordinate and the focus type to the target image to obtain a focus marking image.
On the basis of the foregoing embodiment, optionally, the result determining module 330 includes: a qualified value determining unit and a labeling result determining unit;
a qualified value determining unit, configured to perform image matching on the lesion marking image and a preset marking image of the target image to obtain a marking qualified value of the lesion marking image;
and the marking result determining unit is used for determining the marking result of the focus marking image according to the marking qualified value of the focus marking image.
On the basis of the foregoing embodiment, optionally, the labeling result determining unit is specifically configured to:
detecting whether the labeling qualified value of the focus labeling image is larger than a qualified threshold value;
if so, determining that the labeling result of the focus labeling image is accurate, and setting the state of the labeling result of the focus labeling image as pass.
On the basis of the foregoing embodiment, optionally, the apparatus of this embodiment further includes: the system comprises an image acquisition module and a model training module;
the image acquisition module is used for acquiring a lesion marking image with a marking result in a passing state;
and the model training module is used for training a focus marking model according to the marking coordinates and the focus type displayed in the focus marking image.
On the basis of the foregoing embodiment, optionally, the apparatus of this embodiment further includes: a lesion marking module;
and the focus marking module is used for inputting the focus image into a focus marking model if a marking event of the focus image is detected, and determining a focus area and a focus type of the focus image according to the output of the focus marking model.
By the processing device for the lesion marking, marking information of a plurality of people can be added into the original lesion image, and marking inspection can be performed by combining the preset marking image, so that marking efficiency of the lesion image is effectively improved.
The processing device for lesion marking provided by the embodiment of the invention can execute the processing method for lesion marking provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention, as shown in fig. 4, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processors 410 in the electronic device may be one or more, and one processor 410 is taken as an example in fig. 4; the processor 410, the memory 420, the input device 430 and the output device 440 in the electronic apparatus may be connected by a bus or other means, and the bus connection is exemplified in fig. 4.
The memory 420 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the processing method of lesion marking in the embodiment of the present invention. The processor 410 executes software programs, instructions and modules stored in the memory 420 to execute various functional applications and data processing of the electronic device, that is, to implement the processing method for lesion marking provided by the embodiment of the present invention.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to an electronic device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic apparatus, and may include a keyboard, a mouse, and the like. The output device 440 may include a display device such as a display screen.
EXAMPLE five
The present embodiments provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are used to implement a method of lesion marking processing provided by the embodiments of the present invention.
Of course, the embodiments of the present invention provide a storage medium containing computer-executable instructions, which are not limited to the method operations described above, but can also perform related operations in the method for processing lesion marking provided in any embodiments of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for processing lesion marking, the method comprising:
determining the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a lesion region;
if a marking information display event is detected, rendering the marking information to the target image to obtain a focus marking image;
and determining the labeling result of the lesion labeling image according to the lesion labeling image and the preset labeling image of the target image.
2. The method of claim 1, wherein determining annotation information of at least two annotating persons for the target image comprises:
responding to the labeling requests of at least two labeling personnel to a target image, and copying the target image to a visual area;
obtaining labeling information of the target image according to labeling operation of the at least two labeling personnel on the target image in the visual area; wherein the labeling information comprises labeling coordinates and/or a lesion type.
3. The method of claim 1, wherein rendering the annotation information onto the target image results in a lesion annotation image, comprising:
according to the identity of the marking personnel, carrying out color identification on the marking information to obtain marking coordinates and a focus type associated with the marking personnel;
and rendering the marking coordinate and the focus type to the target image to obtain a focus marking image.
4. The method according to claim 1, wherein determining the labeling result of the lesion labeling image according to the lesion labeling image and a preset labeling image of the target image comprises:
carrying out image matching on the focus labeling image and a preset labeling image of the target image to obtain a labeling qualified value of the focus labeling image;
and determining the labeling result of the lesion labeling image according to the labeling qualified value of the lesion labeling image.
5. The method according to claim 4, wherein determining the labeling result of the lesion labeling image according to the labeling qualification value of the lesion labeling image comprises:
detecting whether the labeling qualified value of the focus labeling image is larger than a qualified threshold value;
if so, determining that the labeling result of the focus labeling image is accurate, and setting the state of the labeling result of the focus labeling image as pass.
6. The method of claim 5, further comprising:
acquiring a lesion marking image with a marking result in a passing state;
and training a focus marking model according to the marking coordinates and the focus type displayed in the focus marking image.
7. The method of claim 6, further comprising:
and if a marking event of the focus image is detected, inputting the focus image into a focus marking model, and determining a focus area and a focus type of the focus image according to the output of the focus marking model.
8. A device for lesion marking, the device comprising:
the information determining module is used for determining the labeling information of at least two labeling personnel on the target image; wherein the target image comprises an image having a lesion region;
the image determining module is used for rendering the marking information to the target image to obtain a focus marking image if a marking information display event is detected;
and the result determining module is used for determining the labeling result of the focus labeling image according to the focus labeling image and the preset labeling image of the target image.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of lesion tagging as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a method of lesion marking according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110220535.XA CN112819925A (en) | 2021-02-26 | 2021-02-26 | Method and device for processing focus labeling, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110220535.XA CN112819925A (en) | 2021-02-26 | 2021-02-26 | Method and device for processing focus labeling, electronic equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112819925A true CN112819925A (en) | 2021-05-18 |
Family
ID=75864132
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110220535.XA Pending CN112819925A (en) | 2021-02-26 | 2021-02-26 | Method and device for processing focus labeling, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112819925A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115345828A (en) * | 2022-07-12 | 2022-11-15 | 江苏诺鬲生物科技有限公司 | Artificial intelligence algorithm-based immunofluorescence staining picture lesion identification method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
| CN109035187A (en) * | 2018-07-10 | 2018-12-18 | 杭州依图医疗技术有限公司 | A kind of mask method and device of medical image |
| WO2019170060A1 (en) * | 2018-03-05 | 2019-09-12 | 深圳大学 | Image authentication-based medical image labeling method and device, user terminal, and computer readable storage medium |
| CN111986194A (en) * | 2020-09-03 | 2020-11-24 | 平安国际智慧城市科技股份有限公司 | Medical annotation image detection method and device, electronic equipment and storage medium |
-
2021
- 2021-02-26 CN CN202110220535.XA patent/CN112819925A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107563123A (en) * | 2017-09-27 | 2018-01-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for marking medical image |
| WO2019170060A1 (en) * | 2018-03-05 | 2019-09-12 | 深圳大学 | Image authentication-based medical image labeling method and device, user terminal, and computer readable storage medium |
| CN109035187A (en) * | 2018-07-10 | 2018-12-18 | 杭州依图医疗技术有限公司 | A kind of mask method and device of medical image |
| CN111986194A (en) * | 2020-09-03 | 2020-11-24 | 平安国际智慧城市科技股份有限公司 | Medical annotation image detection method and device, electronic equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115345828A (en) * | 2022-07-12 | 2022-11-15 | 江苏诺鬲生物科技有限公司 | Artificial intelligence algorithm-based immunofluorescence staining picture lesion identification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3083606B2 (en) | Medical diagnosis support system | |
| CN110276366A (en) | Carry out test object using Weakly supervised model | |
| JP2018106662A (en) | Information processor, information processing method, and program | |
| CN102365645A (en) | Organizing digital images by correlating faces | |
| JP2004234228A (en) | Image search device, keyword assignment method in image search device, and program | |
| CN111985241B (en) | Medical information query method, device, electronic equipment and medium | |
| Delamaro et al. | Using concepts of content‐based image retrieval to implement graphical testing oracles | |
| JP7320280B2 (en) | Label collection device, label collection method and label collection program | |
| CN111063422A (en) | Medical image labeling method, device, equipment and medium | |
| CN110265122A (en) | Image processing method, device, equipment and storage medium based on endoscopic system | |
| CN114049631A (en) | Data labeling method and device, computer equipment and storage medium | |
| CN111124863B (en) | Intelligent device performance testing method and device and intelligent device | |
| CN111507405A (en) | Picture labeling method and device, electronic equipment and computer readable storage medium | |
| CN112819925A (en) | Method and device for processing focus labeling, electronic equipment and medium | |
| US20140208392A1 (en) | Information providing apparatus, information providing method, and non-transitory computer readable medium | |
| CN112084103B (en) | Interface test method, device, equipment and medium | |
| CN113903433B (en) | Image processing method and device and electronic equipment | |
| CN112949305B (en) | Negative feedback information acquisition method, device, equipment and storage medium | |
| CN114724170A (en) | BOM generation method and device, electronic equipment and storage medium | |
| CN114297720A (en) | Image desensitization method and device, electronic equipment and storage medium | |
| CN114003784A (en) | Request recording method, device, equipment and storage medium | |
| CN113282218A (en) | Multi-dimensional report generation method, device, equipment and storage medium | |
| CN112287738A (en) | Text matching method and device for graphic control, medium and electronic equipment | |
| CN111062977B (en) | Sample data generation method and device, computer equipment and storage medium | |
| CN114004029A (en) | Method and device for generating part detection report, electronic device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |