Form association method and device, storage medium and electronic device

Abstract

The present application provides a form association method and device, a storage medium, and an electronic device, relating to the field of clinical trial research technology. The form association method includes: determining a mask image corresponding to a medical image to be associated that includes M lesion areas, wherein the M lesion areas each correspond to a different pixel category in the mask image; determining N groups of first target lesion annotation data corresponding to the medical image to be associated; based on the mask image, determining the association relationship between the N groups of first target lesion annotation data and the M lesion areas; based on the association relationship, associating the first target lesion annotation data that meets the preset annotation conditions to the film reading form corresponding to the medical image to be associated, thereby avoiding errors caused by manual form filling, and the operation process is convenient and fast, greatly improving the work efficiency of the reader and the accuracy of the content of the film reading form.

Description

Technical Field

[0001] The present application relates to the technical field of clinical trial research, and in particular to a form association method and device, a storage medium, and an electronic device. Background Art

[0002] In current medical image interpretation systems, readers need to analyze various image data, select usable image data from a large amount of image data, perform measurements, and then manually enter the measurement results into the interpretation form. However, this manual entry process is prone to omissions, over-entry, or errors, and manual entry is relatively inefficient. Summary of the Invention

[0003] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a form association method and device, a storage medium and an electronic device.

[0004] In a first aspect, an embodiment of the present application provides a form association method, which is applied to a film reading system, and the method includes: determining a mask image corresponding to a medical image to be associated that includes M lesion areas, wherein, in the mask image, the M lesion areas each correspond to a different pixel category; determining N groups of first target lesion annotation data corresponding to the medical image to be associated; based on the mask image, determining the association relationship between the N groups of first target lesion annotation data and the M lesion areas; based on the association relationship, associating the first target lesion annotation data that meets the preset annotation conditions to the film reading form corresponding to the medical image to be associated.

[0005] In combination with the first aspect, in certain implementations of the first aspect, the first target lesion annotation data corresponds to first-type lesion long and short diameter annotation line segments, and based on the mask image, the association relationship between N groups of first target lesion annotation data and M lesion areas is determined, including: for each group of first target lesion annotation data in the N groups of first target lesion annotation data, determining the pixel set of first-type lesion long and short diameter annotation line segments corresponding to the first target lesion annotation data; based on the mask image, determining the pixel category to which each pixel in the pixel set belongs; based on the pixel category to which each pixel in the pixel set belongs, determining the association relationship between the first target lesion annotation data and the M lesion areas.

[0006] In combination with the first aspect, in certain implementations of the first aspect, the association relationship between the first target lesion annotation data and the M lesion areas is determined based on the pixel categories to which the pixels in the pixel set each belong, including: determining the pixel category with the largest number of pixels based on the pixel categories to which the pixels in the pixel set each belong; determining the percentage data of the number of pixels in the pixel category with the largest number of pixels to the number of pixels in the pixel set; and determining the association relationship between the first target lesion annotation data and the M lesion areas based on the percentage data and a preset association percentage threshold.

[0007] In combination with the first aspect, in certain implementations of the first aspect, before associating the first target lesion annotation data that meets the preset annotation conditions to the reading form corresponding to the medical image to be associated based on the association relationship, the method also includes: determining P groups of second target lesion annotation data corresponding to the medical image to be associated; and determining the first target lesion annotation data that meets the preset annotation conditions based on the N groups of first target lesion annotation data and the P groups of second target lesion annotation data.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the second target lesion labeling data corresponds to second-type lesion long and short diameter labeling line segments, and based on N groups of first target lesion labeling data and P groups of second target lesion labeling data, the first target lesion labeling data that meets the preset labeling conditions is determined, including: based on the first-type lesion long and short diameter labeling line segments corresponding to each of the N groups of first target lesion labeling data, determining the labeling feature information corresponding to each of the N groups of first target lesion labeling data; based on the second-type lesion long and short diameter labeling line segments corresponding to each of the P groups of second target lesion labeling data, determining the labeling feature information corresponding to each of the P groups of second target lesion labeling data; based on the labeling feature information corresponding to each of the P groups of second target lesion labeling data, verifying the labeling feature information corresponding to each of the N groups of first target lesion labeling data, and obtaining the verification results corresponding to each of the N groups of first target lesion labeling data; based on the verification results corresponding to each of the N groups of first target lesion labeling data, determining the first target lesion labeling data that meets the preset labeling conditions.

[0009] In combination with the first aspect, in certain implementations of the first aspect, based on the labeling feature information corresponding to each of the P groups of second target lesion labeling data, the labeling feature information corresponding to each of the N groups of first target lesion labeling data is verified to obtain the verification results corresponding to each of the N groups of first target lesion labeling data, including: for each group of first target lesion labeling data in the N groups of first target lesion labeling data, based on the association relationship between the first target lesion labeling data and the M lesion areas, the second target lesion labeling data in the P groups of second target lesion labeling data that belongs to the same lesion area as the first target lesion labeling data is determined as the reference target lesion labeling data corresponding to the first target lesion labeling data; and the labeling feature information corresponding to the reference target lesion labeling data is used to verify the first target lesion labeling information to obtain the verification result corresponding to the first target lesion labeling data.

[0010] In combination with the first aspect, in some implementations of the first aspect, the annotation feature information includes annotation line segment length information and / or annotation line segment angle information.

[0011] In combination with the first aspect, in certain implementations of the first aspect, determining P groups of second target lesion annotation data corresponding to the medical image to be associated includes: performing a Hough transform operation on each lesion area among M lesion areas to obtain a second type of long diameter annotation line segment corresponding to the lesion area; determining the shortest vertical line segment corresponding to the second type of long diameter annotation line segment as the second type of short diameter annotation line segment corresponding to the lesion area; generating second target lesion annotation data corresponding to the lesion area based on the second type of long diameter annotation line segment and the second type of short diameter annotation line segment corresponding to the lesion area; and determining P groups of second target lesion annotation data based on the second target lesion annotation data corresponding to each of the M lesion areas.

[0012] In the second aspect, an embodiment of the present application provides a form association device, which is applied to a film reading system, and the device includes: a first determination module, used to determine a mask image corresponding to a medical image to be associated including M lesion areas, wherein, in the mask image, the M lesion areas each correspond to a different pixel category; a second determination module, used to determine N groups of first target lesion annotation data corresponding to the medical image to be associated; a third determination module, used to determine the association relationship between the N groups of first target lesion annotation data and the M lesion areas based on the mask image; a data association module, used to associate the first target lesion annotation data that meets the preset annotation conditions to the film reading form corresponding to the medical image to be associated based on the association relationship.

[0013] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program for executing the form association method mentioned in any of the above embodiments.

[0014] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a processor; a memory for storing processor-executable instructions; and the processor is configured to execute the form association method mentioned in any of the above embodiments.

[0015] The form association method provided in the embodiment of the present application obtains a mask image of the medical image to be associated after lesion segmentation by determining a mask image corresponding to the medical image to be associated including M lesion areas, and the pixel categories corresponding to each of the M lesion areas are different, so as to identify each lesion area; by determining N groups of first target lesion annotation data corresponding to the medical image to be associated, it is convenient for the reader to analyze the lesion area; by determining the association relationship between the N groups of first target lesion annotation data and the M lesion areas based on the mask image, the purpose of identifying the lesion area to which the first target lesion annotation data belongs is achieved, so as to match the first target lesion annotation data with the lesion area to which it belongs one by one; by associating the first target lesion annotation data that meets the preset annotation conditions to the reading form corresponding to the medical image to be associated based on the association relationship, thereby avoiding errors caused by manual filling in of the form, and the operation process is convenient and fast, which greatly improves the work efficiency of the reader and the accuracy of the content of the reading form. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 Shown is a schematic diagram of a scenario applicable to an embodiment of the present application.

[0018] Figure 2 Shown is a flow chart of a form association method provided by an exemplary embodiment of the present application.

[0019] Figure 3 The figure shows a flow chart of determining the association relationship between N groups of first target lesion annotation data and M lesion regions based on a mask image, provided by an exemplary embodiment of the present application.

[0020] Figure 4 The figure shows a flow chart of determining the association relationship between the first target lesion annotation data and M lesion regions based on the pixel categories to which the pixels in the pixel set belong, provided by an exemplary embodiment of the present application.

[0021] Figure 5 Shown is a flow chart of a form association method provided by another exemplary embodiment of the present application.

[0022] Figure 6The figure shows a flow chart of determining first target lesion labeling data that meets preset labeling conditions based on N groups of first target lesion labeling data and P groups of second target lesion labeling data provided by an exemplary embodiment of the present application.

[0023] Figure 7 The figure shows a flow chart of an exemplary embodiment of the present application, which verifies the annotation feature information corresponding to each of the N groups of first target lesion annotation data based on the annotation feature information corresponding to each of the P groups of second target lesion annotation data, and obtains the verification results corresponding to each of the N groups of first target lesion annotation data.

[0024] Figure 8 The figure shows a flow chart of determining P groups of second target lesion annotation data corresponding to the medical images to be associated, provided by an exemplary embodiment of the present application.

[0025] Figure 9 Shown is a structural diagram of a form association device provided by an exemplary embodiment of the present application.

[0026] Figure 10 Shown is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] In medical image reading systems, different centers use different equipment to upload image data, and the quality of the image data varies. Readers need to analyze a wide variety of image data and select usable image data from a large amount of image data for measurement. When manually filling out forms, measurement results may be under-, over-, or incorrectly entered, resulting in inconsistencies between the measurement results and the reading form content, making it impossible to guarantee the accuracy of the reading form content. Furthermore, measurement results may be affected by network conditions and unable to be transmitted and saved, thus preventing them from being sent to the reading form in a timely manner. Furthermore, manually filling out forms is time-consuming for readers, resulting in low work efficiency.

[0029] Figure 1 The following is a schematic diagram of a scenario applicable to the embodiment of the present application. Figure 1 As shown, the scenario to which the embodiment of the present application is applicable includes a terminal 1 and an image acquisition device 2, wherein a communication connection relationship exists between the server 1 and the image acquisition device 2.

[0030] Exemplarily, the terminal 1 may be a computing device such as a computer or a mobile phone, and the image acquisition device 2 may also be subordinate to the terminal 1 , which is not further limited in the embodiment of the present application.

[0031] Specifically, the image acquisition device 2 is used to acquire a medical image to be associated that includes a lesion area, and the terminal 1 is used to determine a mask image corresponding to the medical image to be associated that includes M lesion areas, wherein in the mask image, each of the M lesion areas corresponds to a different pixel category, and then determine N groups of first target lesion annotation data corresponding to the medical image to be associated. Then, based on the mask image, the association relationship between the N groups of first target lesion annotation data and the M lesion areas is determined. Finally, based on the association relationship, the first target lesion annotation data that meets the preset annotation conditions is associated with the film reading form corresponding to the medical image to be associated. That is, this scenario implements a form association method.

[0032] because Figure 1 The above scenario shown utilizes the terminal 1 to implement the form association method. Therefore, this scenario can not only improve the adaptability of the scenario, but also effectively reduce the computational complexity of the image acquisition device 2 .

[0033] Exemplary Methods

[0034] Figure 2 FIG. 1 is a flow chart of a form association method provided by an exemplary embodiment of the present application. For example, the form association method is applied to a film reading system. Figure 2 As shown, the form association method provided in the embodiment of the present application includes the following steps.

[0035] Step 10: Determine a mask image corresponding to the medical image to be associated including M lesion areas.

[0036] Specifically, in the mask image, each of the M lesion regions corresponds to a different pixel category, and M is a positive integer.

[0037] In one embodiment of the present application, a lesion segmentation operation is performed on a single frame of a medical image to be associated based on a preset segmentation model to obtain the region of the medical image to be associated in which the lesion exists. Each disconnected lesion region is then categorized to obtain a mask image corresponding to the medical image to be associated. Among the R pixels included in the mask image, for each of the R pixels, the pixel value of the pixel corresponds to the pixel category of the pixel, where R is a positive integer. For example, the background region corresponds to pixel category 0, lesion 1 corresponds to pixel category 1, and lesion 2 corresponds to pixel category 2.

[0038] Exemplarily, the preset segmentation model includes an instance segmentation model, which has the characteristics of both semantic segmentation and object detection, thereby improving the accuracy of lesion segmentation. Alternatively, other segmentation models may be used, as long as they can accurately segment the lesion area in the medical image to be associated. This embodiment of the present application does not further limit this.

[0039] It should be noted that the pixel values ​​of each connected region are approximate, each connected region is a lesion region, and disconnected regions are different lesion regions.

[0040] Step 20: Determine N groups of first target lesion annotation data corresponding to the medical image to be associated.

[0041] In one embodiment of the present application, the image reader determines N target lesion areas among M lesion areas, and labels the N target lesion areas respectively, obtaining N groups of first target lesion labeling data corresponding to the medical image to be associated, where N is a positive integer less than or equal to M.

[0042] Step 30: Determine the association relationship between the N groups of first target lesion annotation data and the M lesion regions based on the mask image.

[0043] In one embodiment of the present application, based on the characteristics that the pixel value of each pixel point of the mask image corresponds to the pixel category of the pixel point, the association relationship between N groups of first target lesion labeling data and M lesion areas is determined. Specifically, for each group of first target lesion labeling data in the N groups of first target lesion labeling data, the lesion area to which the first target lesion labeling data belongs among the M lesion areas is determined.

[0044] Step 60: Based on the association relationship, the first target lesion annotation data that meets the preset annotation conditions is associated with the image reading form corresponding to the medical image to be associated.

[0045] In one embodiment of the present application, the preset labeling condition may be a condition for determining whether the first target lesion labeling data is correctly labeled. For example, the first target lesion labeling data may be compared with the second target lesion labeling data to verify whether the first target lesion labeling data is correctly labeled.

[0046] In one embodiment of the present application, the image reading form corresponding to the medical image to be associated can be a unified format image reading form. For example, for different subjects, only the subject's name (or other identifiable number) needs to be filled in the image reading form to associate the subject's first target lesion annotation data that meets the preset annotation conditions with the image reading form corresponding to the subject. The image reading form can also be in other formats, as long as it meets the conditions for accurately associating the first target lesion annotation data, and this embodiment of the present application does not further limit this.

[0047] In one embodiment of the present application, the reader annotates the medical image to be associated of the current subject in the reading system, and the terminal obtains a group of first target lesion annotation data corresponding to the medical image to be associated based on the aforementioned annotation, which meets the preset annotation conditions. The terminal then presents in real time the annotation page of the medical image to be associated that the reader is currently working on and the reading form interface, wherein the corresponding position of the reading form interface displays the aforementioned first target lesion annotation data that meets the preset annotation conditions. The aforementioned annotation page of the medical image to be associated and the reading form interface can be presented on the same page to facilitate the reader to view them at the same time, or after the reader obtains N groups of first target lesion annotation data corresponding to the medical image to be associated, the terminal associates the N groups of first target lesion annotation data to their respective corresponding positions in the reading form interface in real time.

[0048] In actual application, the mask image corresponding to the medical image to be associated, which includes M lesion areas, is first determined; then, N groups of first target lesion annotation data corresponding to the medical image to be associated are determined; then, based on the mask image, the association relationship between the N groups of first target lesion annotation data and the M lesion areas is determined; finally, based on the association relationship, the first target lesion annotation data that meets the preset annotation conditions is associated with the film reading form corresponding to the medical image to be associated.

[0049] The form association method provided in the embodiment of the present application obtains a mask image of the medical image to be associated after lesion segmentation by determining a mask image corresponding to the medical image to be associated including M lesion areas, and the pixel categories corresponding to each of the M lesion areas are different, so as to identify each lesion area; by determining N groups of first target lesion annotation data corresponding to the medical image to be associated, it is convenient for the reader to analyze the lesion area; by determining the association relationship between the N groups of first target lesion annotation data and the M lesion areas based on the mask image, the purpose of identifying the lesion area to which the first target lesion annotation data belongs is achieved, so as to match the first target lesion annotation data with the lesion area to which it belongs one by one; by associating the first target lesion annotation data that meets the preset annotation conditions to the reading form corresponding to the medical image to be associated based on the association relationship, thereby avoiding errors caused by manual filling in of the form, and the operation process is convenient and fast, while greatly improving the work efficiency of the reader and the accuracy of the content of the reading form.

[0050] Figure 3 The figure shows a flow chart of determining the association relationship between N groups of first target lesion annotation data and M lesion areas based on a mask image provided by an exemplary embodiment of the present application. Figure 2 The present application is extended based on the embodiment shown Figure 3 The embodiment shown is described below in detail. Figure 3 The embodiment shown is Figure 2 The differences and similarities between the illustrated embodiments are not described in detail.

[0051] like Figure 3 As shown, in the form association method provided in the embodiment of the present application, the first target lesion annotation data corresponds to the long and short diameter annotation line segments of the first type of lesions. Based on the mask image, the steps of determining the association relationship between N groups of first target lesion annotation data and M lesion areas include the following steps.

[0052] Step 31 : for each set of first target lesion labeling data in the N sets of first target lesion labeling data, determine a pixel set of the first type of lesion major and minor diameter labeling line segments corresponding to the first target lesion labeling data.

[0053] In one embodiment of the present application, the first type of lesion long and short diameter annotated line segments are the long diameter annotated line segments and the short diameter annotated line segments annotated by the image reader on the target lesion area. Exemplarily, a set of pixel points corresponding to the first type of lesion long and short diameter annotated line segments is determined.

[0054] Step 32: Determine the pixel category to which each pixel in the pixel set belongs based on the mask image.

[0055] In one embodiment of the present application, the pixel category to which each pixel in the pixel set belongs is determined based on the characteristic that the pixel value of each pixel point of the mask image corresponds to the pixel category of the pixel point.

[0056] Step 33 : determining the association relationship between the first target lesion annotation data and the M lesion regions based on the pixel categories to which the pixels in the pixel set belong.

[0057] In one embodiment of the present application, the lesion area to which the first target lesion annotation data belongs is determined based on the pixel categories to which the pixels in the pixel set belong.

[0058] In actual application, first, for each group of first target lesion annotation data in N groups of first target lesion annotation data, the pixel set of the first type of lesion long and short diameter annotation line segments corresponding to the first target lesion annotation data is determined; then, based on the mask image, the pixel categories to which each pixel in the pixel set belongs are determined; then, based on the pixel categories to which each pixel in the pixel set belongs, the association relationship between the first target lesion annotation data and the M lesion areas is determined.

[0059] The form association method provided in the embodiment of the present application determines the pixel set of the first type of lesion long and short diameter annotation line segments corresponding to the first target lesion annotation data for each group of first target lesion annotation data in N groups, and determines the pixel categories to which the pixels in the pixel set belong based on the mask image. Then, based on the pixel categories to which the pixels in the pixel set belong, the lesion area to which the first target lesion annotation data belongs is determined, and the first target lesion annotation data is accurately matched one-to-one with the lesion area to which it belongs, thereby improving the accuracy of the content of the film reading form.

[0060] Figure 4 The figure shows a flow chart of determining the association relationship between the first target lesion annotation data and M lesion areas based on the pixel categories to which the pixels in the pixel set belong, provided by an exemplary embodiment of the present application. Figure 3 The present application is extended based on the embodiment shown Figure 4 The embodiment shown is described below in detail. Figure 4 The embodiment shown is Figure 3 The differences and similarities between the illustrated embodiments are not described in detail.

[0061] like Figure 4 As shown, in the form association method provided in the embodiment of the present application, the step of determining the association relationship between the first target lesion annotation data and the M lesion areas based on the pixel categories to which the pixels in the pixel set belong includes the following steps.

[0062] Step 331 : determining a pixel category with the largest number of pixels based on the pixel categories to which the pixels in the pixel set belong.

[0063] In one embodiment of the present application, assuming that a pixel set includes 1000 pixels, 990 pixels belong to pixel category 1, 7 pixels belong to pixel category 2, and 3 pixels belong to pixel category 3, then based on the pixel categories to which the 1000 pixels belong, it is determined that the pixel category with the largest number of pixels is pixel category 1.

[0064] Step 332 : Determine the percentage data of the number of pixels in the pixel category with the largest number of pixels to the number of pixels in the pixel set.

[0065] In one embodiment of the present application, the percentage data of the number of pixels in pixel category 1 and the number of pixels in the pixel set is determined, that is, the percentage data of 990 and 1000 is 99%.

[0066] Step 333 : Determine the correlation relationship between the first target lesion annotation data and the M lesion regions based on the percentage data and a preset correlation percentage threshold.

[0067] In one embodiment of the present application, the preset association percentage threshold is 95%, that is, when the percentage data is greater than or equal to 95%, the percentage data is determined to meet the preset association percentage threshold condition, and then it is determined that the first target lesion annotation data belongs to the lesion area corresponding to pixel category 1.

[0068] In actual application, first, based on the pixel categories to which the pixels in the pixel set belong, the pixel category with the largest number of pixels is determined; then, the percentage data of the number of pixels in the pixel category with the largest number of pixels and the number of pixels in the pixel set is determined; then, based on the percentage data and the preset correlation percentage threshold, the correlation relationship between the first target lesion annotation data and the M lesion areas is determined.

[0069] The form association method provided in the embodiment of the present application determines the pixel category with the largest number of pixels, and determines the percentage data of the number of pixels in the pixel category with the largest number of pixels to the number of pixels in the pixel set. Then, when the percentage data meets the preset association percentage threshold, the lesion area to which the first target lesion annotation data belongs is determined, making the determined lesion area more convincing, thereby improving the reliability and accuracy of determining the lesion area to which the first target lesion annotation data belongs.

[0070] Figure 5 The figure shows a flow chart of a form association method provided by another exemplary embodiment of the present application. Figure 2 The present application is extended based on the embodiment shown Figure 5 The embodiment shown is described below in detail. Figure 5 The embodiment shown is Figure 2 The differences and similarities between the illustrated embodiments are not described in detail.

[0071] like Figure 5 As shown, in the form association method provided in the embodiment of the present application, before the step of associating the first target lesion annotation data that meets the preset annotation conditions to the reading form corresponding to the medical image to be associated based on the association relationship, the method also includes the following steps.

[0072] Step 40: Determine the P groups of second target lesion annotation data corresponding to the medical image to be associated.

[0073] In one embodiment of the present application, P lesion areas including N target lesion areas are determined among M lesion areas, and the P lesion areas are labeled separately to obtain P groups of second target lesion labeling data corresponding to the medical image to be associated, where P is a positive integer less than or equal to M, and P is greater than or equal to N.

[0074] Step 50: Determine first target lesion labeling data that meets preset labeling conditions based on the N groups of first target lesion labeling data and the P groups of second target lesion labeling data.

[0075] In one embodiment of the present application, for each set of N sets of first target lesion annotation data, the first target lesion annotation data and the second target lesion annotation data belonging to the same lesion region are compared to determine the first target lesion annotation data that meets a preset annotation condition. For example, the preset annotation condition is that the difference between the first target lesion annotation data and the second target lesion annotation data is less than or equal to a preset annotation threshold.

[0076] In actual application, first determine the P groups of second target lesion annotation data corresponding to the medical image to be associated; then determine the first target lesion annotation data that meets the preset annotation conditions based on the N groups of first target lesion annotation data and the P groups of second target lesion annotation data.

[0077] The form association method provided in the embodiment of the present application verifies the accuracy of the N groups of first target lesion annotation data by comparing the N groups of first target lesion annotation data and the P groups of second target lesion annotation data, and identifies the first target lesion annotation data that meets the preset annotation conditions as the accurately labeled first target lesion annotation data, thereby improving the reliability and accuracy of the N groups of first target lesion annotation data labeled by the image reader.

[0078] Figure 6 The figure shows a flow chart of determining the first target lesion labeling data that meets the preset labeling conditions based on N groups of first target lesion labeling data and P groups of second target lesion labeling data provided by an exemplary embodiment of the present application. Figure 5 The present application is extended based on the embodiment shown Figure 6 The embodiment shown is described below in detail. Figure 6 The embodiment shown is Figure 5 The differences and similarities between the illustrated embodiments are not described in detail.

[0079] like Figure 6 As shown, in the form association method provided in the embodiment of the present application, the second target lesion annotation data corresponds to the second type of lesion long and short diameter annotation line segments, and based on N groups of first target lesion annotation data and P groups of second target lesion annotation data, the step of determining the first target lesion annotation data that meets the preset annotation conditions includes the following steps.

[0080] Step 51 : determining the labeling feature information corresponding to each of the N groups of first target lesion labeling data based on the long and short diameter labeling line segments of the first type of lesions corresponding to each of the N groups of first target lesion labeling data.

[0081] It should be noted that the annotation feature information includes annotation line segment length information and / or annotation line segment angle information.

[0082] In one embodiment of the present application, based on the long and short diameter marked line segments of the first type of lesions marked by the image reader on N target lesion areas, the marked line segment length information and / or marked line segment angle information corresponding to each of the N groups of first target lesion marking data are determined.

[0083] Step 52 : determining the annotation feature information corresponding to each of the P group of second target lesion annotation data based on the second type lesion long and short diameter annotation line segments corresponding to each of the P group of second target lesion annotation data.

[0084] In one embodiment of the present application, based on the second type of lesion long and short diameter marked segments respectively marked on P lesion areas, the marked segment length information and / or marked segment angle information corresponding to each of the P groups of second target lesion marking data are determined.

[0085] Step 53 : Based on the annotation feature information corresponding to each of the P groups of second target lesion annotation data, the annotation feature information corresponding to each of the N groups of first target lesion annotation data is verified to obtain the verification results corresponding to each of the N groups of first target lesion annotation data.

[0086] In one embodiment of the present application, the labeled line segment length information and / or labeled line segment angle information corresponding to each of the P groups of second target lesion labeling data are used as a reference to verify the labeled line segment length information and / or labeled line segment angle information corresponding to each of the N groups of first target lesion labeling data, and obtain the verification results corresponding to each of the N groups of first target lesion labeling data. Specifically, the verification result is the length difference information between the labeled line segment length information corresponding to the first target lesion labeling data and the labeled line segment length information corresponding to the second target lesion labeling data, and / or the angle difference information between the labeled line segment angle information corresponding to the first target lesion labeling data and the labeled line segment angle information corresponding to the second target lesion labeling data.

[0087] Step 54 : determining first target lesion labeling data that meets preset labeling conditions based on the verification results corresponding to each of the N groups of first target lesion labeling data.

[0088] In one embodiment of the present application, the preset annotation conditions are that the length difference (i.e., length difference information) is less than or equal to 5% of the length of the annotation line segment corresponding to the second target lesion annotation data (i.e., annotation line segment length information), and the angle difference (i.e., angle difference information) is less than or equal to 5°. For example, if the verification result corresponding to the first target lesion annotation data meets the above preset annotation conditions, the first target lesion annotation data can be associated with the image reading form.

[0089] In actual application, first, based on the first-category lesion long and short diameter annotation line segments corresponding to each of the N groups of first target lesion annotation data, the annotation feature information corresponding to each of the N groups of first target lesion annotation data is determined; then, based on the second-category lesion long and short diameter annotation line segments corresponding to each of the P groups of second target lesion annotation data, the annotation feature information corresponding to each of the P groups of second target lesion annotation data is determined; then, based on the annotation feature information corresponding to each of the P groups of second target lesion annotation data, the annotation feature information corresponding to each of the N groups of first target lesion annotation data is verified to obtain the verification results corresponding to each of the N groups of first target lesion annotation data; finally, based on the verification results corresponding to each of the N groups of first target lesion annotation data, the first target lesion annotation data that meets the preset annotation conditions is determined.

[0090] The form association method provided in the embodiment of the present application specifically describes the verification items (length difference information and / or angle difference information) for verifying N groups of first target lesion annotation data, provides clear verification data conditions for preset annotation conditions, and provides detailed verification steps for determining the first target lesion annotation data that meets the preset annotation conditions.

[0091] Figure 7 The figure shows a flow chart of verifying the corresponding annotation feature information of each of the N groups of first target lesion annotation data based on the corresponding annotation feature information of each of the P groups of second target lesion annotation data, and obtaining the corresponding verification results of each of the N groups of first target lesion annotation data, provided by an exemplary embodiment of the present application. Figure 6 The present application is extended based on the embodiment shown Figure 7 The embodiment shown is described below in detail. Figure 7 The embodiment shown is Figure 6 The differences and similarities between the illustrated embodiments are not described in detail.

[0092] like Figure 7 As shown, in the form association method provided in the embodiment of the present application, based on the annotation feature information corresponding to each of the P groups of second target lesion annotation data, the annotation feature information corresponding to each of the N groups of first target lesion annotation data is verified, and the verification result steps corresponding to each of the N groups of first target lesion annotation data are obtained, which include the following steps.

[0093] Step 531, for each group of first target lesion labeling data in the N groups of first target lesion labeling data, based on the association relationship between the first target lesion labeling data and the M lesion areas, the second target lesion labeling data in the P groups of second target lesion labeling data, which belongs to the same lesion area as the first target lesion labeling data, is determined as the reference target lesion labeling data corresponding to the first target lesion labeling data.

[0094] In one embodiment of the present application, belonging to the same lesion area means that the pixel category corresponding to the lesion area to which the first target lesion annotation data belongs is the same as the pixel category corresponding to the lesion area to which the second target lesion annotation data belongs.

[0095] Step 532 : Using the annotation feature information corresponding to the reference target lesion annotation data, the first target lesion annotation information is verified to obtain a verification result corresponding to the first target lesion annotation data.

[0096] In one embodiment of the present application, the first target lesion labeling data and the second target lesion labeling data belonging to the same lesion area are compared and verified, thereby improving the reliability of the verification result.

[0097] In actual application, first, for each group of first target lesion annotation data in the N groups of first target lesion annotation data, based on the association between the first target lesion annotation data and the M lesion areas, the second target lesion annotation data in the P groups of second target lesion annotation data that belongs to the same lesion area as the first target lesion annotation data is determined as the benchmark target lesion annotation data corresponding to the first target lesion annotation data; then, the annotation feature information corresponding to the benchmark target lesion annotation data is used to verify the first target lesion annotation information to obtain the verification result corresponding to the first target lesion annotation data.

[0098] The form association method provided in the embodiment of the present application clarifies the benchmark target lesion annotation data used to verify the first target lesion annotation data, that is, the second target lesion annotation data belonging to the same lesion area as the first target lesion annotation data, making the verification operation more targeted, thereby making the verification results more convincing and improving the reliability of the verification results.

[0099] Figure 8 The figure shows a flow chart of determining the P group of second target lesion annotation data corresponding to the medical image to be associated provided by an exemplary embodiment of the present application. Figure 5 The present application is extended based on the embodiment shown Figure 8 The embodiment shown is described below in detail. Figure 8 The embodiment shown is Figure 5 The differences and similarities between the illustrated embodiments are not described in detail.

[0100] like Figure 8 As shown, in the form association method provided in the embodiment of the present application, the step of determining the P group of second target lesion annotation data corresponding to the medical image to be associated includes the following steps.

[0101] Step 41 : For each of the M lesion areas, perform a Hough transform operation on the lesion area to obtain a second type of long diameter annotated line segment corresponding to the lesion area.

[0102] Specifically, the Hough transform operation is used to determine the longest line segment corresponding to the lesion area, and obtain the second type of long diameter annotated line segment corresponding to the lesion area.

[0103] Step 42: determine the shortest vertical line segment corresponding to the second-type long-diameter annotated line segment as the second-type short-diameter annotated line segment corresponding to the lesion area.

[0104] Step 43 : generating second target lesion annotation data corresponding to the lesion area based on the second type of long diameter annotation line segments and the second type of short diameter annotation line segments corresponding to the lesion area.

[0105] In one embodiment of the present application, second target lesion annotation data corresponding to the lesion area is generated based on the length information and angle information of the second type of long diameter annotation line segments and the length information and angle information of the second type of short diameter annotation line segments.

[0106] Step 44 : Determine P groups of second target lesion labeling data based on the second target lesion labeling data corresponding to each of the M lesion regions.

[0107] In actual application, first, a Hough transform operation is performed on each of the M lesion areas to obtain the second-class long-diameter labeled line segment corresponding to the lesion area; then, the shortest vertical line segment corresponding to the second-class long-diameter labeled line segment is determined as the second-class short-diameter labeled line segment corresponding to the lesion area; then, based on the second-class long-diameter labeled line segment and the second-class short-diameter labeled line segment corresponding to the lesion area, the second target lesion labeling data corresponding to the lesion area is generated; finally, based on the second target lesion labeling data corresponding to each of the M lesion areas, the P group of second target lesion labeling data is determined.

[0108] The form association method provided in the embodiment of the present application accurately identifies the longest line segment corresponding to the lesion area by performing a Hough transform operation on the lesion area. This longest line segment is also the second type of long diameter annotated line segment corresponding to the lesion area, and further obtains the second target lesion annotated data of group P. The embodiment of the present application improves the accuracy of identifying the longest line segment corresponding to the lesion area based on the Hough transform operation, thereby improving the accuracy of the second target lesion annotated data of group P.

[0109] Figure 9 The figure shows a schematic diagram of the structure of a form association device provided by an exemplary embodiment of the present application. Figure 9 As shown, the form association device provided in the embodiment of the present application includes:

[0110] A first determining module 100 is configured to determine a mask image corresponding to a medical image to be associated that includes M lesion regions, wherein in the mask image, the M lesion regions each correspond to a different pixel category;

[0111] The second determining module 200 is used to determine N groups of first target lesion annotation data corresponding to the medical image to be associated;

[0112] A third determination module 300 is configured to determine, based on the mask image, an association relationship between the N groups of first target lesion annotation data and the M lesion regions;

[0113] The data association module 600 is configured to associate the first target lesion annotation data that meets the preset annotation conditions with the image reading form corresponding to the medical image to be associated based on the association relationship.

[0114] In one embodiment of the present application, the third determination module 300 is further used to determine, for each group of first target lesion annotation data in N groups of first target lesion annotation data, a pixel set of the first type of lesion long and short diameter annotation line segments corresponding to the first target lesion annotation data; based on the mask image, determine the pixel category to which each pixel in the pixel set belongs; and based on the pixel category to which each pixel in the pixel set belongs, determine the association relationship between the first target lesion annotation data and the M lesion areas.

[0115] In one embodiment of the present application, the third determination module 300 is further used to determine the pixel category with the largest number of pixels based on the pixel categories to which the pixels in the pixel set belong; determine the percentage data of the number of pixels in the pixel category with the largest number of pixels to the number of pixels in the pixel set; and determine the association relationship between the first target lesion annotation data and the M lesion areas based on the percentage data and a preset association percentage threshold.

[0116] In one embodiment of the present application, the form associating device further includes:

[0117] A fourth determining module 400 is configured to determine P groups of second target lesion annotation data corresponding to the medical image to be associated;

[0118] The fifth determining module 500 is configured to determine first target lesion labeling data that meets a preset labeling condition based on N groups of first target lesion labeling data and P groups of second target lesion labeling data.

[0119] In one embodiment of the present application, the fifth determination module 500 is further used to determine the labeling feature information corresponding to each of the N groups of first target lesion labeling data based on the first type of lesion long and short diameter labeling line segments corresponding to each of the N groups of first target lesion labeling data; determine the labeling feature information corresponding to each of the P groups of second target lesion labeling data based on the second type of lesion long and short diameter labeling line segments corresponding to each of the P groups of second target lesion labeling data; verify the labeling feature information corresponding to each of the N groups of first target lesion labeling data based on the labeling feature information corresponding to each of the P groups of second target lesion labeling data, and obtain the verification results corresponding to each of the N groups of first target lesion labeling data; and determine the first target lesion labeling data that meets the preset labeling conditions based on the verification results corresponding to each of the N groups of first target lesion labeling data.

[0120] In one embodiment of the present application, the fifth determination module 500 is also used to, for each group of first target lesion labeling data in the N groups of first target lesion labeling data, based on the association relationship between the first target lesion labeling data and the M lesion areas, determine the second target lesion labeling data in the P groups of second target lesion labeling data that belongs to the same lesion area as the first target lesion labeling data as the reference target lesion labeling data corresponding to the first target lesion labeling data; use the labeling feature information corresponding to the reference target lesion labeling data to verify the first target lesion labeling information and obtain the verification result corresponding to the first target lesion labeling data.

[0121] In one embodiment of the present application, the fourth determination module 400 is also used to perform a Hough transform operation on each of the M lesion areas to obtain a second-class long-diameter labeled line segment corresponding to the lesion area; determine the shortest vertical line segment corresponding to the second-class long-diameter labeled line segment as the second-class short-diameter labeled line segment corresponding to the lesion area; generate second target lesion labeling data corresponding to the lesion area based on the second-class long-diameter labeled line segment and the second-class short-diameter labeled line segment corresponding to the lesion area; and determine P groups of second target lesion labeling data based on the second target lesion labeling data corresponding to each of the M lesion areas.

[0122] It should be understood that Figure 9 The operations and functions of the first determination module 100, the second determination module 200, the third determination module 300, the data association module 600, the fourth determination module 400 and the fifth determination module 500 in the provided form association device can refer to the above Figures 2 to 8 To avoid repetition, the provided form association methods are not described here.

[0123] Below, reference Figure 10 To describe the electronic device according to the embodiment of the present application. Figure 10 Shown is a schematic structural diagram of an electronic device provided by an exemplary embodiment of the present application.

[0124] like Figure 10 As shown, the electronic device 70 includes one or more processors 701 and a memory 702 .

[0125] The processor 701 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 70 to perform desired functions.

[0126] The memory 702 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may, for example, include random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may, for example, include read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 701 may execute the program instructions to implement the form association method of each embodiment of the present application described above and / or other desired functions. Various contents such as medical images to be associated, mask images, N groups of first target lesion annotation data, etc. may also be stored in the computer-readable storage medium.

[0127] In one example, the electronic device 70 may further include an input device 703 and an output device 704 , and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0128] The input device 703 may include, for example, a keyboard, a mouse, and the like.

[0129] The output device 704 can output various information to the outside, including the medical image to be associated, the mask image, N sets of first target lesion annotation data, etc. The output device 704 can include, for example, a display, a speaker, a printer, a communication network and its connected remote output device, etc.

[0130] Of course, to simplify, Figure 10 Only some of the components related to the present application in the electronic device 70 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, the electronic device 70 may further include any other appropriate components according to specific application scenarios.

[0131] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the form association method according to various embodiments of the present application described above in this specification.

[0132] The computer program product may be written in any combination of one or more programming languages ​​to implement the program code for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0133] In addition, an embodiment of the present application may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the form association method according to various embodiments of the present application described above in this specification.

[0134] The computer-readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can, for example, include but is not limited to a system, device or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0135] The basic principles of the present application have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in this application are merely illustrative and not restrictive, and it should not be assumed that these advantages, strengths, and effects are required of each embodiment of this application. In addition, the specific details disclosed above are merely illustrative and facilitating understanding, and are not restrictive. The above details do not limit this application to necessarily being implemented using the above specific details.

[0136] The block diagrams of the devices, devices, equipment, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, devices, equipment, and systems can be connected, arranged, or configured in any manner. Words such as "include," "comprise," "have," and the like are open-ended words, meaning "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or" and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0137] It should also be noted that in the apparatus, device, and method of the present application, each component or each step can be decomposed and / or recombined, and such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0138] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0139] The above description has been provided for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A form association method, characterized in that: Applied to a film reading system, the method includes: Determining a mask image corresponding to a medical image to be associated that includes M lesion regions, wherein in the mask image, the M lesion regions respectively correspond to different pixel categories; Determining N groups of first target lesion annotation data corresponding to the medical image to be associated; Determining, based on the mask image, an association relationship between the N groups of first target lesion annotation data and the M lesion regions; Based on the association relationship, the first target lesion annotation data that meets the preset annotation conditions is associated with the image reading form corresponding to the medical image to be associated; Before associating the first target lesion annotation data that meets the preset annotation conditions with the image reading form corresponding to the medical image to be associated based on the association relationship, the method further includes: Determining P groups of second target lesion annotation data corresponding to the medical image to be associated; Determining the first target lesion labeling data that meets the preset labeling conditions based on the N groups of first target lesion labeling data and the P groups of second target lesion labeling data; The determining of the P group of second target lesion annotation data corresponding to the medical image to be associated includes: For each of the M lesion areas, Performing a Hough transform operation on the lesion area to obtain a second type of long diameter marked line segment corresponding to the lesion area; Determine the shortest vertical line segment corresponding to the second-type long-diameter annotated line segment as the second-type short-diameter annotated line segment corresponding to the lesion area; generating second target lesion annotation data corresponding to the lesion area based on the second type of long diameter annotation line segments and the second type of short diameter annotation line segments corresponding to the lesion area; The P groups of second target lesion labeling data are determined based on the second target lesion labeling data corresponding to each of the M lesion areas.

2. The form association method according to claim 1, characterized in that: The first target lesion annotation data corresponds to the first type of lesion long and short diameter annotation line segments, and determining the association relationship between the N groups of first target lesion annotation data and the M lesion regions based on the mask image includes: For each set of first target lesion annotation data in the N sets of first target lesion annotation data, Determining a pixel set of the first type of lesion major and minor diameter annotated line segments corresponding to the first target lesion annotated data; determining, based on the mask image, a pixel category to which each pixel in the pixel set belongs; Based on the pixel categories to which the pixels in the pixel set belong, an association relationship between the first target lesion annotation data and the M lesion regions is determined.

3. The form association method according to claim 2, characterized in that: The determining, based on the pixel categories to which the pixels in the pixel set belong, the association relationship between the first target lesion annotation data and the M lesion regions includes: Determining a pixel category with the largest number of pixels based on the pixel categories to which the pixels in the pixel set belong; Determine percentage data of the number of pixels in the pixel category with the largest number of pixels to the number of pixels in the pixel set; Based on the percentage data and a preset correlation percentage threshold, an association relationship between the first target lesion annotation data and the M lesion regions is determined.

4. The form association method according to claim 1, characterized in that: The second target lesion labeling data corresponds to a second type of lesion long and short diameter labeling line segment, and determining the first target lesion labeling data that meets the preset labeling conditions based on the N groups of first target lesion labeling data and the P groups of second target lesion labeling data includes: Determining the annotation feature information corresponding to each of the N groups of first target lesion annotation data based on the first type lesion long and short diameter annotation line segments corresponding to each of the N groups of first target lesion annotation data; Determining the annotation feature information corresponding to each of the P group of second target lesion annotation data based on the second type lesion long and short diameter annotation line segments corresponding to each of the P group of second target lesion annotation data; Verify the respective corresponding annotation feature information of the N groups of first target lesion annotation data based on the respective corresponding annotation feature information of the P groups of second target lesion annotation data, and obtain the respective corresponding verification results of the N groups of first target lesion annotation data; Based on the verification results corresponding to each of the N groups of first target lesion labeling data, the first target lesion labeling data that meets the preset labeling conditions is determined.

5. The form association method according to claim 4, characterized in that: The verifying the respective corresponding annotation feature information of the N groups of first target lesion annotation data based on the respective corresponding annotation feature information of the P groups of second target lesion annotation data, and obtaining the respective corresponding verification results of the N groups of first target lesion annotation data, includes: For each set of first target lesion annotation data in the N sets of first target lesion annotation data, Based on the association relationship between the first target lesion labeling data and the M lesion regions, second target lesion labeling data belonging to the same lesion region as the first target lesion labeling data in the P group of second target lesion labeling data is determined as the reference target lesion labeling data corresponding to the first target lesion labeling data; The first target lesion labeling information is verified using the labeling feature information corresponding to the reference target lesion labeling data to obtain a verification result corresponding to the first target lesion labeling data.

6. The form association method according to claim 4 or 5, characterized in that: The annotation feature information includes annotation line segment length information and / or annotation line segment angle information.

7. A form association device, characterized in that: Applied to a film reading system, the device comprises: A first determining module is configured to determine a mask image corresponding to a medical image to be associated that includes M lesion regions, wherein in the mask image, the M lesion regions respectively correspond to different pixel categories; A second determining module is used to determine N groups of first target lesion annotation data corresponding to the medical image to be associated; a third determining module, configured to determine, based on the mask image, an association relationship between the N groups of first target lesion annotation data and the M lesion regions; a data association module, configured to associate the first target lesion annotation data meeting the preset annotation conditions with the image reading form corresponding to the medical image to be associated based on the association relationship; Before associating the first target lesion annotation data that meets the preset annotation conditions with the image reading form corresponding to the medical image to be associated based on the association relationship, the method further includes: Determining P groups of second target lesion annotation data corresponding to the medical image to be associated; Determining the first target lesion labeling data that meets the preset labeling conditions based on the N groups of first target lesion labeling data and the P groups of second target lesion labeling data; The determining of the P group of second target lesion annotation data corresponding to the medical image to be associated includes: For each of the M lesion areas, Performing a Hough transform operation on the lesion area to obtain a second type of long diameter marked line segment corresponding to the lesion area; Determine the shortest vertical line segment corresponding to the second-type long-diameter annotated line segment as the second-type short-diameter annotated line segment corresponding to the lesion area; generating second target lesion annotation data corresponding to the lesion area based on the second type of long diameter annotation line segments and the second type of short diameter annotation line segments corresponding to the lesion area; The P groups of second target lesion labeling data are determined based on the second target lesion labeling data corresponding to each of the M lesion areas.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and the computer program is used to execute the form association method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to execute the form association method described in any one of claims 1 to 6 above.

Images