CN111986254A - Target area contour analysis method and device, storage medium and electronic equipment - Google Patents
Target area contour analysis method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN111986254A CN111986254A CN202010853754.7A CN202010853754A CN111986254A CN 111986254 A CN111986254 A CN 111986254A CN 202010853754 A CN202010853754 A CN 202010853754A CN 111986254 A CN111986254 A CN 111986254A
- Authority
- CN
- China
- Prior art keywords
- contour
- target
- target area
- area
- standard
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Abstract
The application provides a target area contour analysis method, a target area contour analysis device, a storage medium and an electronic device, wherein the method is applied to the electronic device and comprises the following steps: acquiring a target area outline sketched by a user aiming at a target area; calculating the coincidence degree of the target area contour and a target area standard contour preset in the target area; evaluating the target region contour by analyzing the degree of coincidence. Through the coincidence degree of electronic equipment automatic calculation user's target region contour that the student sketched promptly and target region standard profile, this coincidence degree of rethread electronic equipment automatic analysis to determine the degree of accuracy of this sketched target region contour, whole process need not artifical the participation, has realized that the efficient carries out the analysis and evaluation to the target region of sketching.
Description
Technical Field
The present application relates to the field of medical technology, and in particular, to a method and an apparatus for analyzing a target region contour, a storage medium, and an electronic device.
Background
Target delineation is a very important skill for oncologists. The target area refers to an area to be irradiated by rays in the tumor radiotherapy process, and the precision is required to be in the millimeter level; under-irradiation will lead to tumor recurrence, and over-irradiation will increase radiation damage, loss of normal organs, etc. Therefore, in the training process of oncologists, the target delineation capacity needs to be emphatically trained and examined. However, the training and examination mode is mainly used for the teacher to subjectively examine the target area drawn by the student, the examination mode is very dependent on the operation of the doctor, and the efficiency is low.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, a storage medium, and an electronic device for analyzing a target contour, so as to efficiently analyze and evaluate a delineated target.
In a first aspect, an embodiment of the present application provides a method for analyzing a target region contour, where the method is applied to an electronic device, and the method includes: acquiring a target area outline sketched by a user aiming at a target area; calculating the coincidence degree of the target area contour and a target area standard contour preset in the target area; evaluating the target region contour by analyzing the degree of coincidence.
In the embodiment of the application, through the coincidence degree of electronic equipment automatic calculation user's target region contour that the student sketched promptly and target region standard profile, this coincidence degree is analyzed to rethread electronic equipment automation to confirm the degree of accuracy of this sketched target region contour, whole process need not artifical the participation, has realized that the efficient carries out analysis and evaluation to the target region of sketching.
With reference to the first aspect, in a first possible implementation manner, calculating a coincidence ratio of the target region contour and a target region standard contour preset in the target region includes: calculating the size of the overlapping part between the target area contour and the target area standard contour; calculating a ratio of the size to a size of the target volume contour, wherein the ratio is indicative of the degree of coincidence.
In the embodiment of the application, the overlapping degree of the contours can be visually reflected due to the size of the overlapping part of the contours, so that the accurate determination of the overlapping degree of the contours is realized.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner, the calculating a size of an overlapping portion between the target volume contour and the target volume standard contour includes: calculating the number of pixel points forming the overlapped part, wherein the number of the pixel points represents the size of the overlapped part; correspondingly, calculating a ratio of the size to the size of the target volume contour includes: and calculating the ratio of the number of the pixels to the number of the pixels forming the target area outline, wherein the number of the pixels forming the target area outline represents the size of the target area outline.
In the embodiment of the application, because the essence of the contour is still formed by the pixel points, the height of the coincidence degree of the contour can be accurately determined by analyzing the number of the pixel points.
With reference to the first aspect, in a third possible implementation manner, calculating a coincidence ratio of the target region contour and a target region standard contour preset in the target region includes: calculating the area enclosed by the target area outline; and calculating the ratio of the area to the area surrounded by the standard outline of the target area, wherein the ratio represents the contact ratio.
In the embodiment of the application, the overlapping degree of the contours can be visually reflected due to the size of the overlapping part of the area enclosed by the contours, so that the accurate determination of the overlapping degree of the contours is realized.
With reference to the first aspect, in a fourth possible implementation manner, calculating a ratio of the area to an area surrounded by the standard contour of the target area includes: calculating the area of an overlapped part between a first graph defined by the target area outline and a second graph defined by the target area standard outline; and calculating the ratio of the area to the sum of the areas, wherein the sum of the areas is the sum of the areas of the first graph and the second graph, and the ratio represents the contact ratio.
In the embodiment of the application, the overlapping degree of the contour can be visually reflected due to the size of the overlapping part between the area enclosed by the contour and the total area, so that the accurate determination of the overlapping degree of the contour is realized.
With reference to the first aspect, in a fifth possible implementation manner, before determining the contact ratio, the method further includes: acquiring a target area reference contour which is sketched by an expert aiming at the target area; and expanding the target area reference contour to obtain the target area standard contour.
In the embodiment of the application, the target area reference contour is expanded, so that the situation that the target area reference contour directly drawn by an expert is too thin to cause inaccurate evaluation is avoided.
With reference to the first aspect, in a sixth possible implementation manner, the analyzing the contact ratio to evaluate the drawn contour includes: and analyzing the contact ratio by using a preset network model to determine an evaluation score of the target area outline, wherein the higher the evaluation score is, the more accurate the target area outline is, and otherwise, the less accurate the target area outline is.
In the embodiment of the application, as the trained network models are high in accuracy, the evaluation scores of the target area contour can be determined accurately by analyzing the contact ratio through the network models.
In a second aspect, the present application provides an apparatus for analyzing a target region contour, the apparatus being applied to an electronic device, the apparatus including: the contour acquisition model is used for acquiring a target area contour which is sketched by a user aiming at the target area; the contour analysis model is used for calculating the coincidence ratio of the target area contour and a target area standard contour preset by the target area; evaluating the target region contour by analyzing the degree of coincidence.
With reference to the second aspect, in a first possible implementation manner, the contour analysis model is configured to calculate a size of an overlapping portion between the target contour and the target standard contour; calculating a ratio of the size to a size of the target volume contour, wherein the ratio is indicative of the degree of coincidence.
With reference to the first possible implementation manner of the second aspect, in a second possible implementation manner, the contour analysis model is configured to calculate the number of pixels forming the overlapping portion, where the number of pixels represents the size of the overlapping portion; correspondingly, calculating a ratio of the size to the size of the target volume contour includes: and calculating the ratio of the number of the pixels to the number of the pixels forming the target area outline, wherein the number of the pixels forming the target area outline represents the size of the target area outline.
With reference to the second aspect, in a third possible implementation manner, the contour analysis model is configured to calculate an area surrounded by the target region contour; and calculating the ratio of the area to the area surrounded by the standard outline of the target area, wherein the ratio represents the contact ratio.
With reference to the second aspect, in a fourth possible implementation manner, the contour analysis model is configured to calculate an area of an overlapping portion between a first graph defined by the target area contour and a second graph defined by the target area standard contour; and calculating the ratio of the area to the sum of the areas, wherein the sum of the areas is the sum of the areas of the first graph and the second graph, and the ratio represents the contact ratio.
With reference to the second aspect, in a fifth possible implementation manner, before the contour analysis model determines the coincidence degree, the contour analysis model is further configured to obtain a target area reference contour that is drawn by an expert for the target area; and expanding the target area reference contour to obtain the target area standard contour.
With reference to the second aspect, in a sixth possible implementation manner, the contour analysis model is configured to analyze the coincidence degree by using a preset network model to determine an evaluation score of the target region contour, where a higher evaluation score indicates that the target region contour is more accurate, and vice versa, the target region contour is less accurate.
In a third aspect, an embodiment of the present application provides an electronic device, including: a memory for storing a program; a bus; a processor connected to the memory via the bus, the processor being configured to execute the program to perform a method of analyzing a target region profile as set forth in the first aspect or any one of the possible implementations of the first aspect.
In a fourth aspect, embodiments of the present application provide a non-transitory computer-readable storage medium storing program code, which, when executed by a computer, performs a method of analyzing a target volume profile according to the first aspect or any one of the possible implementations of the first aspect.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of a method for analyzing a target region profile according to an embodiment of the present disclosure;
fig. 2A is a first application scene diagram of a method for analyzing a target contour according to an embodiment of the present application;
fig. 2B is a second application scenario diagram of a method for analyzing a target region contour according to an embodiment of the present application;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present disclosure;
fig. 4 is a block diagram of an apparatus for analyzing a target region profile according to an embodiment of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
Referring to fig. 1, an embodiment of the present application provides a method for analyzing a target contour, where the method for analyzing the target contour may be performed by an electronic device, and the electronic device may be a mobile terminal, a tablet, a personal computer, or the like with a display interface, and a flow of the method for analyzing the target contour may include:
step S100: and acquiring a target area contour which is sketched by a user aiming at the target area.
Step S200: and calculating the coincidence degree of the contour of the sketched target area and the standard contour of the target area preset by the target area.
Step S300: and evaluating the delineated target area contour by analyzing the contact ratio.
The above flow will be described in detail with reference to the application scenario.
In this embodiment, for each case, there are multiple slice images of the target area, for example, there are 200 slice images of the target area of one case (different target areas, the number of slice images is also different), and therefore, before step S200 is executed for the slice image of each target area of each case, the electronic device needs to acquire a standard contour of the target area, which is drawn in the slice image of the target area by an expert, and the standard contour of the target area is used for evaluating the drawing of the user. In addition, in order to realize more objective and more accurate assessment of the delineation of the user, aiming at the slice image of the same target area, a plurality of experts can delineate the slice image, so that the standard contours of the target areas delineated by the experts are obtained. In other words, it may have a plurality of target standard contours for slice images of the same target. In addition, in order to more clearly illustrate the situation of the case, the electronic device displays the slice image of the target area of the case and also displays some clinical information and pathological information of the case. Such as the sex, age, pathological outcome, etc. of the patient.
It can be understood that, since the principle that the standard contour of the target area is drawn by each expert in the slice image of each target area obtained by the electronic device is substantially the same, the following description will be given by taking the standard contour of the target area drawn by one expert in the slice image of a certain target area obtained by the electronic device as an example.
As an exemplary way to acquire the standard contour of the target region, a way generated by an electronic device can be adopted to acquire the standard contour of the target region.
Specifically, the electronic device may display a slice image of the target area stored in advance on a display interface of the electronic device, and the expert may draw a reference contour of the target area for the target area in the slice image through interaction with the electronic device.
For example, if the display interface of the electronic device is not touchable, the expert may perform contour delineation on the target area in the slice image by operating the mouse, and the electronic device generates a corresponding reference contour of the target area in the slice image by responding to the operation of the expert.
For another example, if the display interface of the electronic device is touch-controllable, the expert may perform contour delineation on the display interface in a touch-control manner, and the electronic device generates a corresponding target reference contour in the slice image by responding to a touch operation of the expert.
Furthermore, the contour lines of the target area reference contour outlined by the expert are thinner, and the accuracy is affected if the target area reference contour outlined by the expert is directly used for evaluation. Therefore, after the target area reference contour is obtained, the electronic device can expand the target area reference contour to a certain extent, for example, the target area reference contour is expanded inwards by a first preset number of pixel points, and the target area reference contour is expanded outwards by a second preset number of pixel points, so that a target area standard contour is obtained.
It should be noted that the first preset number and the second preset number may be set according to actual situations, but one or more numbers, such as one, three, or five, may also not be provided, and too many numbers may also affect the accuracy. In addition, according to the actual situation, the first preset number and the second preset number may be the same or different, for example, if a small number of pixel points need to be expanded, the first preset number may be greater than the second preset number, and if the contour needs to be more accurate, the first preset number may be equal to or less than the second preset number.
For example, as shown in fig. 2A, a target area reference contour L1 outlined by an expert is shown in fig. 2A. The electronics expand on the basis of the target reference contour L1, and a target standard contour L2 as shown in fig. 2B is obtained.
As another exemplary way of obtaining the standard contour of the target region, other device-generated ways may also be adopted to obtain the standard contour of the target region.
Specifically, the expert can draw the target area reference contour through other equipment, and the target area reference contour is sent to the electronic equipment by the other equipment. And the electronic device further expands the target reference contour to obtain the target standard contour.
Or, after obtaining the target reference contour, the other device may continue to expand the target reference contour, and finally send the standard contour of the target obtained by expansion to the electronic device.
It should be noted that the target standard contour obtained by the electronic device may be an image including the target standard contour, and the pixel values of the pixels belonging to the background in the image are uniform, so that the target standard contour can be highlighted in the image; alternatively, it may also be a graphical parameter of the target standard contour and the coordinates of the target standard contour in the slice image.
After describing how the electronic device obtains the standard contour of the target area, the following describes steps S100-S300 in detail, and describes how to evaluate the target area contour drawn by the user by using any one of the standard contours of the target area mentioned above.
Step S100: and acquiring a target area contour which is sketched by a user aiming at the target area.
In this embodiment, for the target region contour, the target region contour may also be obtained by an electronic device or other device.
For example, if a mode generated by the electronic device is adopted, the electronic device may display a slice image of a target area stored in advance on a display interface of the electronic device, and a user (in an application scenario of the present application, the user may be a student who needs to evaluate a delineation) may delineate a target area contour for the target area in the slice image through interaction with the electronic device.
For example, if the display interface of the electronic device is not touchable, the user may also perform contour delineation on the target region in the slice image by operating the mouse, and the electronic device generates a corresponding contour of the target region in the slice image by responding to the operation of the user.
For another example, if the display interface of the electronic device is touch-controllable, the user may perform contour delineation on the display interface by means of touch control, and the electronic device generates a corresponding target area contour in the slice image by responding to the touch operation of the user.
For example, if the target area is generated by other devices, the user may draw the target area contour through the other devices, and the target area contour is sent to the electronic device by the other devices, so that the electronic device obtains the target area contour.
It should be noted that the target area contour obtained by the electronic device may be an image including the target area contour, the size of the image is the same as the size of the image including the standard target area contour, and the pixel values of the pixels belonging to the background in the image are uniform, so that the target area contour can also be highlighted in the image; alternatively, it may also be a graphical parameter of the target contour and the coordinates of the target contour in the slice image.
Step S200: and calculating the coincidence degree of the contour of the sketched target area and the standard contour of the target area preset by the target area.
After the target area contour of the target area is obtained for the same target area, because the target area standard contours of the target area are multiple, the target area contour can be evaluated by utilizing each target area standard contour of the target area. Since the principle of using each target standard contour of the target to evaluate the target contour is substantially the same, the following description will take an example of using one target standard contour of the target to evaluate the target contour.
Specifically, as described above, if the target area contour and the target area standard contour obtained by the electronic device are both images including contours, the electronic device may overlap the two images first, and then analyze the coincidence degree of the target area contour and the target area standard contour.
If the target area contour and the target area standard contour obtained by the electronic device are both the graphic parameters and the coordinates containing the contours, the electronic device can generate the two contours in the same image based on the graphic parameters and the coordinates of the two contours, and then analyze the coincidence degree of the target area contour and the target area standard contour.
If the target contour obtained by the electronic device is an image containing a contour, and the target standard contour obtained is a graphic parameter and a coordinate of the contour, the electronic device may generate the target standard contour in the image containing the target contour based on the graphic parameter and the coordinate, and analyze the coincidence degree of the target contour and the target standard contour.
If the target standard contour obtained by the electronic device is an image containing a contour, and the obtained target contour is a graphic parameter and a coordinate of the contour, the electronic device may generate the target contour in the image containing the target standard contour based on the graphic parameter and the coordinate, and analyze the coincidence degree of the target contour and the target standard contour.
In this embodiment, as a first exemplary way to analyze the coincidence degree, the electronic device may calculate the size of the overlapping portion between the target region contour and the target region standard contour; and calculating the ratio of the size of the overlapped part to the size of the target region contour, wherein the ratio represents the coincidence degree of the two contours.
Specifically, the electronic device can calculate the number of pixels forming the overlapping portion between the target area contour and the target area standard contour by analyzing the target area contour and the target area standard contour, and the number of the pixels can represent the size of the overlapping portion. The electronic equipment compares the calculated number of the pixels with the number of the pixels forming the outline of the target area, and the ratio can be determined. The electronic device may calculate the number of pixels constituting the target area outline in advance, or may calculate the number of pixels in the overlapping portion together.
It will be appreciated that, by the above analysis, the more the target contour falls within the target standard contour, the higher its degree of coincidence. The coincidence degree is highest if the more the target area contour falls into the standard contour of the target area. Therefore, the coincidence degree of the two contours can be objectively and accurately determined by the analysis method.
In this embodiment, as a second exemplary way to analyze the coincidence degree, the electronic device may calculate an area surrounded by the target area contour; and calculating the ratio of the area surrounded by the target area outline to the area surrounded by the target area standard outline, wherein the ratio represents the contact ratio.
Specifically, the electronic device can calculate the number of pixel points contained in the graph surrounded by the target area contour by analyzing the target area contour, and the number of the pixel points can represent the area surrounded by the target area contour. The electronic equipment compares the calculated pixel number with the pixel number contained in the graph surrounded by the standard outline of the target area, and the ratio can be determined. The electronic device may calculate the number of pixels included in the graph surrounded by the target area contour in advance, or calculate the target area contour together when analyzing the target area contour.
It can be understood that whether the target area contour is similar to the target area standard contour can reflect the coincidence condition of the target area contour and the target area standard contour from the side surface, and if the similarity of the target area contour and the target area standard contour is higher, the coincidence degree of the target area contour and the target area standard contour is also higher. Therefore, the coincidence degree of the two contours can be objectively and accurately determined by the analysis method.
In this embodiment, as a third exemplary way of analyzing the coincidence degree, the electronic device may calculate an area of an overlapping portion between a first graph surrounded by the target area outline and a second graph surrounded by the target area standard outline; and calculating the ratio of the area to the sum of the areas, wherein the sum of the areas is the sum of the area of the first graph and the area of the second graph, and the ratio represents the contact ratio.
Specifically, the electronic device may determine an overlapping portion between a first graph defined by the target area contour and a second graph defined by the target area standard contour by analyzing the target area contour and the target area standard contour, and further determine the number of pixels included in the overlapping portion, where the number of pixels included in the overlapping portion indicates an area of the overlapping portion. The electronic equipment adds the number of the pixels contained in the first graph and the number of the pixels contained in the second graph surrounded by the standard outline of the target area, and then determines the sum of the pixels, wherein the sum of the pixels represents the sum of the areas. The electronic device compares the number of pixels contained in the overlapping portion with the total number of pixels and then multiplies the number by 2, so that the ratio can be determined. The electronic device may calculate the number of pixels included in the second graph surrounded by the target area contour in advance, or may calculate the target area contour together when analyzing the target area contour.
It will be appreciated that the more the target contour coincides with the target standard contour, the closer the ratio determined by the above-described manner of calculating the sum of the areas of the overlapping portions and the area is to 1. Therefore, the coincidence degree of the two contours can be objectively and accurately determined by the analysis method.
Step S300: and evaluating the delineated target area contour by analyzing the contact ratio.
In this embodiment, since the scoring standards of each expert for the target area contour may be slightly different, a plurality of set network models are deployed in advance in the electronic device, each network model is set based on the scoring standard of a corresponding expert, and the network model may be a pre-trained multilayer perceptron model or a random forest model, or the network model may be a pre-constructed gaussian regression model. Since the manner of setting each corresponding network model according to the rating standard of each expert is substantially the same, the following description will be given by taking an example of setting one network model according to the rating standard of one expert.
First, the setting method is different for different types of models.
For example, it may be trained on a multi-layer perceptron model or a random forest model. The training parameters of each training input can be at least one of the three ways of determining the contact degree. The at least one degree of coincidence is processed by a multi-layered perceptron model or a random forest model, which may output an evaluation score for the target area profile. The electronic equipment can reversely propagate to optimize the multilayer perceptron model or the random forest model by utilizing the Loss between the evaluation score output by the model and the manual score of the expert corresponding to the model for the target area outline, so that the evaluation score output by the model is closer to the manual score of the expert.
For another example, a gaussian regression model may be used to construct the model. The electronic device can establish a large number of goodness-of-contact degrees and gaussian distributions among manual scores of experts corresponding to the goodness-of-contact degrees respectively, so that a gaussian regression model is constructed according to the gaussian distributions.
For example, if a gaussian regression model is constructed by using 1000 target area contours, each target area contour including the three coincidence degrees, the electronic device may map the three coincidence degrees of each target area contour and the expert score of the target area contour into a three-dimensional coordinate system, so as to obtain 1000 coordinate points, where each coordinate point is the expert score of one target area contour corresponding to the coordinate point, and the coordinate of each coordinate point is the three coincidence degrees of one target area contour corresponding to the coordinate point. Based on the gaussian distribution of the 1000 coordinate points, the electronic device may construct a function to represent the gaussian distribution of the 1000 coordinate points, where the function represents the gaussian regression model.
In this embodiment, based on the trained multiple network models, the electronic device may evaluate the contour of the target area drawn by the user. Wherein, evaluating the contour of the target area of the user's delineation can be applied to the exercise stage of the user performing the delineation exercise, and can also be applied to evaluating the delineation examination stage of the user, which are described below respectively.
Aiming at the exercise stage:
the electronic device may determine at least one coincidence degree in at least one of the three ways of determining the coincidence degree, and input the determined at least one coincidence degree into each network model, and through the processing of each network model, the electronic device may obtain an evaluation score, which is output by each network model and is specific to the target region contour drawn by the user, so as to obtain a plurality of evaluation scores. In this way, the electronic device may average the multiple evaluation scores or take the highest score of the multiple evaluation scores, and use the averaged average score or highest score as the final evaluation score for the target region contour. In other words, the target area contour outlined by the user is evaluated by using the scoring standards of a plurality of experts together, so that the target area contour outlined by the user can be evaluated more accurately and objectively. After the final evaluation score is obtained, the electronic device can display the final evaluation score, so that the user can know the delineation condition of the user on the slice image of the target area.
And, under the condition that needs exist, the user can carry out the operation of showing the standard outline of target area, and electronic equipment obtains this operation through responding to the user and carries out, just corresponding with the standard outline of target area that a certain expert's person sketched or the standard outline of a plurality of target areas that a plurality of expert's personnel sketched show on the slice image of this target area to a plurality of standard outlines of target area that a plurality of expert's personnel sketched with different display colors are on the slice image of target area, so that distinguish.
It can be understood that, at the exercise stage, to the slice image of every target region, the user can all be through showing the target region standard profile of observing each expert's personnel of study delineation to and combine oneself score to the slice image delineation of this target region, compare the target region standard profile of target region profile and each expert's personnel delineation of oneself delineation, thereby realize better learning.
For the examination phase:
the electronic device also obtains the final evaluation score that the user delineates for the slice image of each target area in the aforementioned manner, but the electronic device does not display the final evaluation score. After the user finishes delineating the slice images of all target areas of a case, the electronic device may average all the final evaluation scores of the case or obtain the highest score of all the evaluation scores, and use the average score or the highest score as the final evaluation score for the user examination, and display the final evaluation score.
It should be noted that, in the foregoing, in the examination stage and the exercise stage, the determining the evaluation score of the delineated target area contour directly by using the network model is an exemplary manner of the embodiment, which is not limited, and the embodiment may also determine the evaluation score by using a combined scoring manner.
Specifically, the method comprises the following steps: after obtaining the target area outline that the user sketched to the target area to and before calculating the coincidence degree of this target area outline that sketches and target area predetermined target area standard outline, electronic equipment can analyze this target area outline that sketches earlier whether coincide with target area predetermined target area standard outline, judges promptly whether the same pixel has in this target area outline that sketches and target area predetermined target area standard outline. For example, the electronic device may analyze whether the coordinate of each pixel in the outlined target area contour is the same as the coordinate of a certain pixel in a preset standard contour of the target area; if the pixel points with the same coordinates exist, determining that the pixel point in the outlined target area outline coincides with the position of a corresponding pixel point in a preset standard outline of the target area; and if no pixel point with the same coordinate exists, determining that the position of the pixel point in the outlined target area outline is not coincident with the position of each pixel point in a preset standard outline of the target area.
Further, based on whether the positions of the pixels are overlapped or not, if the electronic device determines that the number of the pixels, which are overlapped with the positions of the pixels in the preset standard contour of the target area, in the outline of the target area is larger than or equal to a preset number, the electronic device determines that the number of the pixels, which are overlapped with the preset standard contour of the target area, in the outline of the target area is overlapped with the preset standard contour of the target area, wherein the preset number can be set according to actual conditions, for example, 1, 5, 10 or 20; if the electronic equipment determines that the number of the pixels coincident with the positions of the pixels in the preset target area standard outline in the outlined target area outline is less than the preset number, it is determined that the outlined target area outline is not coincident with the preset target area standard outline.
Furthermore, when the delineated target area contour is determined to be not coincident with the preset target area standard contour, the electronic equipment does not need to execute subsequent processes. When the determined delineated target area contour coincides with the preset target area standard contour, the electronic device may determine that the delineated target area contour has a basic score, for example, 40 to 50 points, according to a preset rule. Of course, if the delineated target area contour is composed of a plurality of mutually independent sub-contours, the electronic device needs to judge whether each sub-contour is overlapped, and on the basis that each sub-contour is overlapped, it is determined that the delineated target area contour has a basic score, otherwise, it is determined that the delineated target area contour is not overlapped with the preset target area standard contour, thereby terminating the execution of the subsequent flow.
Finally, the electronic device calculates the contact ratio again and analyzes the contact ratio by using the network model to determine a progressive score for the delineated target area contour (the process of determining the progressive score is the process described above, and the process is not described again); and adding the basic score and the progressive score of the sketched target area contour to obtain the final evaluation score of the sketched target area contour.
It should be further noted that, in practical application, after a trained network model is manually scored by a certain expert, other experts can also recognize the manual scoring standard of the expert, so that other experts can directly use the trained network model without training by using their own manual scoring, thereby improving the application efficiency of the network model in practice. For example, after a certain hospital has trained the network model, the network model can be directly popularized to other hospitals for use.
Referring to fig. 3, based on the same inventive concept, the present embodiment provides an electronic device 10, and the electronic device 10 may include a communication interface 11 connected to a network, one or more processors 12 for executing program instructions, a bus 13, and a memory 14 in different forms, such as a disk, a ROM, or a RAM, or any combination thereof. Illustratively, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof.
The memory 14 is used to store a program and the processor 12 is used to call up and run the program in the memory 14 to perform the aforementioned target region contour analysis method.
Referring to fig. 4, based on the same inventive concept, an embodiment of the present application provides an apparatus 100 for analyzing a target profile, where the apparatus 100 for analyzing a target profile is applied to an electronic device, and the apparatus 100 for analyzing a target profile includes:
a contour obtaining model 110, configured to obtain a target area contour that a user outlines for a target area;
a contour analysis model 120 for calculating the coincidence ratio of the target region contour and a target region standard contour preset in the target region; evaluating the target region contour by analyzing the degree of coincidence.
It should be noted that, as those skilled in the art can clearly understand, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
Some embodiments of the present application also provide a computer-readable storage medium of a computer-executable non-volatile program code, which can be a general-purpose storage medium, such as a removable disk, a hard disk, or the like, and the computer-readable storage medium has a program code stored thereon, which when executed by a computer, performs the steps of the method for analyzing a target region profile according to any of the above embodiments.
The program code product of the method for analyzing a target region contour provided in the embodiment of the present application includes a computer-readable storage medium storing program code, where instructions included in the program code may be used to execute the method in the foregoing method embodiment, and specific implementation may refer to the method embodiment, and details are not described herein again.
In conclusion, the coincidence degree of the target area contour drawn by the user, namely the student, and the target area standard contour is automatically calculated through the electronic equipment, and then the coincidence degree is automatically analyzed through the electronic equipment so as to determine the accuracy of the target area contour drawn, the whole process does not need manual participation, and the efficient analysis and evaluation of the target area drawn is realized.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for analyzing a target contour, the method being applied to an electronic device, the method comprising:
acquiring a target area outline sketched by a user aiming at a target area;
calculating the coincidence degree of the target area contour and a target area standard contour preset in the target area;
evaluating the target region contour by analyzing the degree of coincidence.
2. The method for analyzing the target contour according to claim 1, wherein calculating the coincidence of the target contour with a target standard contour preset in the target comprises:
calculating the size of the overlapping part between the target area contour and the target area standard contour;
calculating a ratio of the size to a size of the target volume contour, wherein the ratio is indicative of the degree of coincidence.
3. The method for analyzing the target contour according to claim 2, wherein calculating the size of the overlap between the target contour and the target standard contour comprises:
calculating the number of pixel points forming the overlapped part, wherein the number of the pixel points represents the size of the overlapped part;
correspondingly, calculating a ratio of the size to the size of the target volume contour includes:
and calculating the ratio of the number of the pixels to the number of the pixels forming the target area outline, wherein the number of the pixels forming the target area outline represents the size of the target area outline.
4. The method for analyzing the target contour according to claim 1, wherein calculating the coincidence of the target contour with a target standard contour preset in the target comprises:
calculating the area enclosed by the target area outline;
and calculating the ratio of the area to the area surrounded by the standard outline of the target area, wherein the ratio represents the contact ratio.
5. The method for analyzing a target contour according to claim 1, wherein calculating a ratio of the area to an area surrounded by the target standard contour comprises:
calculating the area of an overlapped part between a first graph defined by the target area outline and a second graph defined by the target area standard outline;
and calculating the ratio of the area to the sum of the areas, wherein the sum of the areas is the sum of the areas of the first graph and the second graph, and the ratio represents the contact ratio.
6. The method of analyzing a target profile of claim 1, further comprising, prior to determining the degree of coincidence:
acquiring a target area reference contour which is sketched by an expert aiming at the target area;
and expanding the target area reference contour to obtain the target area standard contour.
7. The method for analyzing a target region contour according to claim 1, wherein the evaluation of the delineated contour by analyzing the degree of coincidence comprises:
and analyzing the contact ratio by using a preset network model to determine an evaluation score of the target area outline, wherein the higher the evaluation score is, the more accurate the target area outline is, and otherwise, the less accurate the target area outline is.
8. An apparatus for analyzing a contour of a target, the apparatus being applied to an electronic device, the apparatus comprising:
the contour acquisition model is used for acquiring a target area contour which is sketched by a user aiming at the target area;
the contour analysis model is used for calculating the coincidence ratio of the target area contour and a target area standard contour preset by the target area; evaluating the target region contour by analyzing the degree of coincidence.
9. An electronic device, comprising:
a memory for storing a program;
a bus;
a processor connected to the memory via the bus, the processor being configured to run the program to perform a method of analyzing a target profile according to any one of claims 1-7.
10. A non-transitory computer-readable storage medium storing program code which, when executed by a computer, performs a method of analyzing a target profile according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010853754.7A CN111986254B (en) | 2020-08-21 | 2020-08-21 | Target area contour analysis method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010853754.7A CN111986254B (en) | 2020-08-21 | 2020-08-21 | Target area contour analysis method and device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111986254A true CN111986254A (en) | 2020-11-24 |
| CN111986254B CN111986254B (en) | 2022-11-18 |
Family
ID=73443031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010853754.7A Active CN111986254B (en) | 2020-08-21 | 2020-08-21 | Target area contour analysis method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111986254B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113034528A (en) * | 2021-04-01 | 2021-06-25 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Target area and organ-at-risk delineation contour accuracy testing method based on image omics |
| CN115511835A (en) * | 2022-09-28 | 2022-12-23 | 西安航空学院 | Image processing test platform |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080118124A1 (en) * | 2006-10-18 | 2008-05-22 | Anant Madabhushi | Systems and methods for classification of biological datasets |
| CN102509286A (en) * | 2011-09-28 | 2012-06-20 | 清华大学深圳研究生院 | Target region sketching method for medical image |
| CN103339653A (en) * | 2010-12-17 | 2013-10-02 | 奥胡斯大学 | Method for delineation of tissue lesions |
| US20170243399A1 (en) * | 2016-02-19 | 2017-08-24 | The Boeing Company | Methods for Localization Using Geotagged Photographs and Three-Dimensional Visualization |
| CN107622710A (en) * | 2017-08-30 | 2018-01-23 | 中南出版传媒集团股份有限公司湖南教育出版社分公司 | Digitize writing practising method and system |
| WO2018108177A1 (en) * | 2016-12-16 | 2018-06-21 | 北京奇虎科技有限公司 | Method for teaching painting using robot, device and robot therefor |
| CN108447551A (en) * | 2018-02-09 | 2018-08-24 | 北京连心医疗科技有限公司 | A kind of automatic delineation method in target area based on deep learning, equipment and storage medium |
| CN108717866A (en) * | 2018-04-03 | 2018-10-30 | 陈辛元 | A kind of method, apparatus, equipment and the storage medium of the distribution of prediction radiotherapy planning dosage |
| KR101954684B1 (en) * | 2018-10-11 | 2019-03-06 | 주식회사 한국에스지티 | System Forming Image Data Automatically |
| CN109509197A (en) * | 2018-09-26 | 2019-03-22 | 沈阳东软医疗系统有限公司 | A kind of method, apparatus, equipment and storage medium for dividing area-of-interest |
| CN109615642A (en) * | 2018-11-05 | 2019-04-12 | 北京全域医疗技术有限公司 | Jeopardize the automatic delineation method of organ and device in a kind of radiotherapy planning |
| CN110070533A (en) * | 2019-04-23 | 2019-07-30 | 科大讯飞股份有限公司 | A kind of evaluating method of object detection results, device, equipment and storage medium |
| CN110517257A (en) * | 2019-08-30 | 2019-11-29 | 北京推想科技有限公司 | Jeopardize organ markup information processing method and relevant apparatus |
| CN110889848A (en) * | 2019-12-11 | 2020-03-17 | 上海联影医疗科技有限公司 | System and device for processing overlapping region of interest |
-
2020
- 2020-08-21 CN CN202010853754.7A patent/CN111986254B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080118124A1 (en) * | 2006-10-18 | 2008-05-22 | Anant Madabhushi | Systems and methods for classification of biological datasets |
| CN103339653A (en) * | 2010-12-17 | 2013-10-02 | 奥胡斯大学 | Method for delineation of tissue lesions |
| CN102509286A (en) * | 2011-09-28 | 2012-06-20 | 清华大学深圳研究生院 | Target region sketching method for medical image |
| US20170243399A1 (en) * | 2016-02-19 | 2017-08-24 | The Boeing Company | Methods for Localization Using Geotagged Photographs and Three-Dimensional Visualization |
| WO2018108177A1 (en) * | 2016-12-16 | 2018-06-21 | 北京奇虎科技有限公司 | Method for teaching painting using robot, device and robot therefor |
| CN107622710A (en) * | 2017-08-30 | 2018-01-23 | 中南出版传媒集团股份有限公司湖南教育出版社分公司 | Digitize writing practising method and system |
| CN108447551A (en) * | 2018-02-09 | 2018-08-24 | 北京连心医疗科技有限公司 | A kind of automatic delineation method in target area based on deep learning, equipment and storage medium |
| CN108717866A (en) * | 2018-04-03 | 2018-10-30 | 陈辛元 | A kind of method, apparatus, equipment and the storage medium of the distribution of prediction radiotherapy planning dosage |
| CN109509197A (en) * | 2018-09-26 | 2019-03-22 | 沈阳东软医疗系统有限公司 | A kind of method, apparatus, equipment and storage medium for dividing area-of-interest |
| KR101954684B1 (en) * | 2018-10-11 | 2019-03-06 | 주식회사 한국에스지티 | System Forming Image Data Automatically |
| CN109615642A (en) * | 2018-11-05 | 2019-04-12 | 北京全域医疗技术有限公司 | Jeopardize the automatic delineation method of organ and device in a kind of radiotherapy planning |
| CN110070533A (en) * | 2019-04-23 | 2019-07-30 | 科大讯飞股份有限公司 | A kind of evaluating method of object detection results, device, equipment and storage medium |
| CN110517257A (en) * | 2019-08-30 | 2019-11-29 | 北京推想科技有限公司 | Jeopardize organ markup information processing method and relevant apparatus |
| CN110889848A (en) * | 2019-12-11 | 2020-03-17 | 上海联影医疗科技有限公司 | System and device for processing overlapping region of interest |
Non-Patent Citations (1)
| Title |
|---|
| 汪源源等: "利用自适应纹理分布的活动形状分割前列腺磁共振图像", 《光学精密工程》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113034528A (en) * | 2021-04-01 | 2021-06-25 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Target area and organ-at-risk delineation contour accuracy testing method based on image omics |
| CN113034528B (en) * | 2021-04-01 | 2023-07-14 | 福建自贸试验区厦门片区Manteia数据科技有限公司 | Target area and organ-at-risk delineating contour accuracy checking method based on image histology |
| CN115511835A (en) * | 2022-09-28 | 2022-12-23 | 西安航空学院 | Image processing test platform |
| CN115511835B (en) * | 2022-09-28 | 2023-07-25 | 西安航空学院 | Image processing test platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111986254B (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107115111B (en) | Blood flow state analysis system and method | |
| US11883225B2 (en) | Systems and methods for estimating healthy lumen diameter and stenosis quantification in coronary arteries | |
| CN109035187B (en) | Medical image labeling method and device | |
| Shum et al. | Quantitative assessment of abdominal aortic aneurysm geometry | |
| US9510756B2 (en) | Method and system for diagnosis of attention deficit hyperactivity disorder from magnetic resonance images | |
| US8311296B2 (en) | Voting in mammography processing | |
| EP3477589B1 (en) | Method of processing medical image, and medical image processing apparatus performing the method | |
| CN111986254B (en) | Target area contour analysis method and device, storage medium and electronic equipment | |
| JP2007233997A (en) | Facial feature point detecting system and method thereof | |
| CN112561908B (en) | Mammary gland image focus matching method, device and storage medium | |
| CN110956626B (en) | Image-based prognosis evaluation method and device | |
| WO2022247573A1 (en) | Model training method and apparatus, image processing method and apparatus, device, and storage medium | |
| CN116350203A (en) | Physical testing data processing method and system | |
| Nieto-Palomo et al. | Statistical techniques for predicting rupture risk in abdominal aortic aneurysms: A contribution based on bootstrap | |
| US20100202674A1 (en) | Voting in mammography processing | |
| CN115631152A (en) | Ultrasonic image interception method and device, electronic equipment and storage medium | |
| CN111652302B (en) | Method and device for explaining insurance verification classification result | |
| US20210256697A1 (en) | Lymph node detection system and methods for use | |
| Ethier et al. | Using Computer Vision and Artificial Intelligence to Track the Healing of Severe Burns | |
| CN115485717A (en) | Predicting geographic atrophy progression using segmentation and feature assessment | |
| CN114631849A (en) | Abdominal aorta imaging method and related apparatus | |
| Trucco et al. | Validation | |
| CN116504407B (en) | Branch occlusion risk prediction method and system for coronary left trunk bifurcation | |
| US20240013418A1 (en) | Automated Device for Anthropometric Measurements | |
| CN117710358A (en) | Medical image data processing method, medical image equipment and electronic device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |