Focus partition scanning method, device and equipment and storage medium

Abstract

The invention discloses a focus partition scanning method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the following steps: acquiring an image set acquired by a capsule endoscopy in gastrointestinal tract detection, and determining a scanning interval from the image set according to a user instruction; determining a scanning strategy corresponding to each scanning interval; the scanning strategy comprises frame-by-frame scanning and frame-skipping scanning; and according to the scanning strategy, performing focus scanning on the image in the corresponding scanning interval to obtain a scanning result of each scanning interval. By supporting a user to set a scanning interval, focus scanning can be only performed on images in the scanning interval, a scanning result can be quickly output, and time waste caused by global scanning is avoided; meanwhile, by using the scanning strategy corresponding to each scanning interval, focus scanning can be performed on different scanning intervals by using different scanning strategies, and the flexibility and accuracy of focus scanning are improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a lesion zoning scanning method, device, equipment and storage medium. Background Art

[0002] Capsule endoscopy, commonly known as capsule endoscopy, is an endoscope in the shape of a capsule that can be used to examine the human intestine. In the prior art, the detection rate of lesions is improved by increasing the pixels and frame rate of capsule endoscopy; however, high pixels and high frame rates also mean that the storage capacity of the image is greatly increased, and the lesion scanning time will also increase accordingly, and the scanning results cannot be obtained quickly during use. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a lesion zoning scanning method, device, equipment and storage medium, which can quickly output scanning results and improve the flexibility and accuracy of lesion scanning. The specific scheme is as follows:

[0004] In a first aspect, the present application discloses a lesion partition scanning method, comprising:

[0005] Acquire an image set collected by the capsule endoscope during gastrointestinal tract detection, and determine a scanning interval from the image set according to a user instruction;

[0006] Determine a scanning strategy corresponding to each of the scanning intervals; the scanning strategy includes frame-by-frame scanning and frame-skipping scanning;

[0007] The images in the corresponding scanning intervals are scanned for lesions according to the scanning strategy to obtain scanning results for each of the scanning intervals.

[0008] Optionally, acquiring an image set collected by the capsule endoscope during gastrointestinal tract detection, and determining a scanning interval from the image set according to a user instruction, includes:

[0009] Displaying the image set and a progress bar corresponding to the image set through a human-computer interaction interface;

[0010] A user selection instruction for a target time point in the progress bar is obtained, and one or more scanning intervals are determined from the image set according to the selection instruction.

[0011] Optionally, determining a scanning interval from the image set according to a user instruction includes:

[0012] Performing part recognition on the image set, dividing the image set into a plurality of image subsets according to the recognition result, and adding corresponding interval annotations to each of the image subsets; the interval annotations include an interval from the body to the esophagus, an interval from the esophagus to the stomach, an interval from the stomach to the small intestine, and an interval from the small intestine to the colon;

[0013] All the image subsets and the interval markings corresponding to each image subset are displayed through the human-computer interaction interface, so that the user can issue the selection instruction according to the interval markings.

[0014] Optionally, the determining a scanning strategy corresponding to each scanning interval includes:

[0015] The scanning strategy corresponding to each scanning interval is determined according to the interval label corresponding to each scanning interval and the mapping relationship between the preset interval label and the scanning strategy.

[0016] Optionally, before performing lesion scanning on the image in the corresponding scanning interval according to the scanning strategy, the method further includes:

[0017] Acquire an exclusion interval selected by a user for the image set; the priority of the exclusion interval is greater than the scanning interval;

[0018] The images within the scanning interval of the non-exclusion interval are scanned for lesions according to the scanning strategy.

[0019] Optionally, the step of acquiring an image set collected by capsule endoscopy during gastrointestinal tract detection includes:

[0020] Acquire an initial image collected by a capsule endoscope during gastrointestinal tract detection, perform similar image deletion processing on the initial image, obtain the image set based on the remaining images, and use the ratio of the number of remaining images to the number of initial images as a screening ratio;

[0021] The determining of the scanning strategy corresponding to each scanning interval includes:

[0022] Determine the screening ratio corresponding to each scanning interval; the ratio of the number of remaining images in the same scanning interval to the number of initial images in the interval is the screening ratio of the interval;

[0023] Determine the scanning coefficient corresponding to each scanning interval according to the screening ratio corresponding to the scanning interval and the function of the scanning coefficient and the screening ratio obtained by pre-fitting; the scanning coefficient is inversely proportional to the screening ratio;

[0024] A scanning strategy corresponding to the scanning interval is determined according to the scanning coefficient.

[0025] Optionally, determining the scanning strategy corresponding to the scanning interval according to the scanning coefficient includes:

[0026] A scanning strategy corresponding to the scanning interval is determined according to a magnitude relationship between the scanning coefficient and a preset coefficient threshold and a frame rate of the image set.

[0027] In a second aspect, the present application discloses a lesion partition scanning device, comprising:

[0028] A scanning interval determination module is used to obtain an image set collected by the capsule endoscope during gastrointestinal tract detection, and determine a scanning interval from the image set according to a user instruction;

[0029] A scanning strategy determination module, used to determine the scanning strategy corresponding to each scanning interval; the scanning strategy includes frame-by-frame scanning and frame skipping scanning;

[0030] The scanning module is used to perform lesion scanning on the image in the corresponding scanning interval according to the scanning strategy to obtain the scanning result of each scanning interval.

[0031] In a third aspect, the present application discloses an electronic device, comprising:

[0032] Memory, used to store computer programs;

[0033] The processor is used to execute the computer program to implement the aforementioned lesion zoning scanning method.

[0034] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein the computer program implements the aforementioned lesion zoning scanning method when executed by a processor.

[0035] In the present application, the image set collected by the capsule endoscope in the gastrointestinal tract detection is obtained, and the scanning interval is determined from the image set according to the user's instructions; the scanning strategy corresponding to each scanning interval is determined; the scanning strategy includes frame-by-frame scanning and frame skipping scanning; the images in the corresponding scanning interval are scanned for lesions according to the scanning strategy to obtain the scanning results of each scanning interval. It can be seen that by supporting the user to set the scanning interval, it is possible to scan the lesions only for the images in the scanning interval, quickly output the scanning results, and avoid wasting time on the global scan; at the same time, by using the scanning strategy corresponding to each scanning interval, it is possible to use different scanning strategies to scan the lesions of different scanning intervals, thereby improving the flexibility and accuracy of lesion scanning. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] FIG1 is a flow chart of a lesion partition scanning method provided by the present application;

[0038] FIG2 is a schematic diagram of a specific interval selection provided by the present application;

[0039] FIG3 is a schematic diagram of the structure of a lesion partition scanning device provided by the present application;

[0040] FIG4 is a structural diagram of an electronic device provided in this application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] In the prior art, the detection rate of lesions is improved by increasing the pixels and frame rate of capsule endoscopes; however, high pixels and high frame rates also mean that the storage capacity of images will increase, and the lesion scanning time will also increase accordingly, and the scanning results cannot be obtained quickly during use. In order to overcome the above technical problems, this application proposes a lesion partition scanning method that can quickly output scanning results and improve the flexibility and accuracy of lesion scanning.

[0043] The present application embodiment discloses a lesion partition scanning method, as shown in FIG1 , the method may include the following steps:

[0044] Step S11: acquiring an image set collected by the capsule endoscope during gastrointestinal tract detection, and determining a scanning interval from the image set according to a user instruction.

[0045] First, obtain the image set collected by the capsule endoscope during gastrointestinal detection, that is, the images collected by the capsule endoscope from the esophagus to the colon, and determine the scanning interval from the image set according to the user's instructions, that is, this application supports lesion detection on some scanned images, rather than all collected images. The existing scheme detects a complete case each time, that is, a complete image set, which requires a long period of preprocessing or takes time to upload the image to the server for processing, and cannot quickly give the lesion scanning results in a short time; and many times, users (such as doctors) are only interested in images of a certain time period and hope to quickly output the lesion results within that time period; this application uses lesion zoning scanning, and the user can select the detection segment, and then only scan the lesion on each small segment, quickly output the scanning results, and improve the flexibility of lesion detection.

[0046] In some embodiments, the acquisition of the image set collected by the capsule endoscope in the gastrointestinal tract detection and the determination of the scanning interval from the image set according to the user's instructions may include: displaying the image set and the progress bar corresponding to the image set through the human-computer interaction interface; obtaining the user's selection instruction for the target time point in the progress bar, and determining one or more scanning intervals from the image set according to the selection instruction. For example, the user opens the film reading interface, and a "fragment scanning" button is provided on the film reading interface. The user clicks the button and a fragment selection page pops up; the user can preview the images corresponding to different times by pulling the progress bar, and select the start time point and the end time point by clicking twice on the progress bar, and the time period between the start time point and the end time point is used as the scanning interval, and multiple scanning intervals can be added.

[0047] In some embodiments, determining the scanning interval from the image set according to user instructions may include: performing part recognition on the image set, dividing the image set into multiple image subsets according to the recognition results, and adding corresponding interval annotations for each of the image subsets; the interval annotations include an interval from the outside of the body to the esophagus, an interval from the esophagus to the stomach, an interval from the stomach to the small intestine, and an interval from the small intestine to the colon; and displaying all of the image subsets and the interval annotations corresponding to each image subset through the human-computer interaction interface so that the user can issue the selection instruction according to the interval annotations. That is, in order to further improve the user experience and convenience, the parts corresponding to the images in the image set are identified by utilizing a recognition model based on a neural network, including but not limited to the esophagus, stomach, small intestine and colon, and then the image set can be divided into multiple intervals through identification, and the images corresponding to each interval are used as a sub-image set, such as the interval from outside the body to the esophagus, the interval from the esophagus to the stomach, the interval from the stomach to the small intestine, and the interval from the small intestine to the colon; wherein, the interval from outside the body to the esophagus includes all esophagus images, the interval from the esophagus to the stomach contains all stomach images, the interval from the stomach to the small intestine contains all small intestine images, and the interval from the small intestine to the colon contains all colon images; at this time, the user can directly view the sub-image set of the corresponding interval according to the annotation. If the user wants to detect the stomach, he can only view the sub-image set corresponding to the esophagus to the stomach interval according to the annotation, and then select the scanning interval from the image set.

[0048] Step S12: Determine a scanning strategy corresponding to each scanning interval; the scanning strategy includes frame-by-frame scanning and frame skipping scanning.

[0049] After the scanning interval is determined, the scanning strategy corresponding to each scanning interval is further determined, that is, the present application supports the use of different scanning strategies for detection in different scanning intervals, thereby further improving the scanning efficiency.

[0050] In some embodiments, the determination of the scanning strategy corresponding to each of the scanning intervals may include: determining the scanning strategy corresponding to each of the scanning intervals according to the interval labeling corresponding to each of the scanning intervals, and the mapping relationship between the preset interval labeling and the scanning strategy. The interval labels include the interval from the outside of the body to the esophagus, the interval from the esophagus to the stomach, the interval from the stomach to the small intestine, and the interval from the small intestine to the colon, that is, the corresponding scanning strategies can be set in advance for different intervals, and the scanning strategy can be automatically determined by directly querying the corresponding relationship after the scanning interval is determined. Of course, the above scanning strategy can also be set directly by the user, that is, after selecting the scanning interval, the scanning strategy is manually set, that is, the scanning rate of the scanning interval is specified.

[0051] In some embodiments, the acquisition of an image set collected by the capsule endoscope during gastrointestinal detection may also include: acquiring an initial image collected by the capsule endoscope during gastrointestinal detection, performing similar image deletion processing on the initial image, obtaining the image set based on the remaining images, and taking the ratio of the number of remaining images to the number of initial images as a screening ratio; it can be understood that for images in the image set with too high similarity, if the detection results are consistent, only one image may be retained to avoid wasting resources; a higher screening ratio indicates that fewer images are deleted and more images remain.

[0052] Correspondingly, determining the scanning strategy corresponding to each of the scanning intervals may include: determining the screening ratio corresponding to each of the scanning intervals; the ratio of the number of remaining images in the same scanning interval to the number of initial images in the interval is the screening ratio of the interval; determining the scanning coefficient corresponding to each scanning interval according to the screening ratio corresponding to the scanning interval and the function of the scanning coefficient and the screening ratio obtained by pre-fitting; the scanning coefficient is inversely proportional to the screening ratio; determining the scanning strategy corresponding to the scanning interval according to the scanning coefficient; the scanning coefficient determines the speed of the scanning, the larger the scanning coefficient, the slower the scanning rate, the smaller the scanning coefficient, the faster the scanning rate. That is, if the screening ratio is higher, the fewer images are deleted, and a lower scanning coefficient can be used at this time, and a lower scanning coefficient corresponds to a high scanning rate, such as frame skipping scanning.

[0053] Specifically, determining the scanning strategy corresponding to the scanning interval according to the scanning coefficient includes: determining the scanning strategy corresponding to the scanning interval according to a size relationship between the scanning coefficient and a preset coefficient threshold and a frame rate of the image set.

[0054] For example, based on a certain number of cases, after a complete scan, a function of the scan coefficient and the screening ratio is fitted: S = ax + bx^2 + cx^3, where x is the screening ratio and S is the scan coefficient. After the user selects the scan interval, the scan coefficient can be automatically calculated through the fitting formula. Of course, any other function that can achieve the corresponding effect in addition to the above form can also be used. At the same time, the user can also manually modify the calculated scan coefficient according to the actual situation of the cases. The process of determining the scanning strategy corresponding to the scan interval based on the size relationship between a specific scan coefficient and a preset coefficient threshold and the frame rate of the image set is as follows: If S < N1, then skip-frame scanning; if N1 ≤ S < N2 and the frame rate p ≥ 1.5 frames / second, then skip-frame scanning; if N1 ≤ S < N2 and the frame rate p < 1.5 frames / second, then frame-by-frame scanning; if S >= N2, then frame-by-frame scanning; where N1 can be set to 0.5, N2 can be set to 0.8, and N1 and N2 can be adjusted numerically according to the actual cases.

[0055] Step S13: Perform lesion scanning on the images within the corresponding scan interval according to the scanning strategy to obtain the scan results of each scan interval.

[0056] After determining the scan interval and the scanning strategy, perform lesion scanning and obtain the scan results of each scan interval.

[0057] In some embodiments, before performing lesion scanning on the images within the corresponding scan interval according to the scanning strategy, it may further include: obtaining an exclusion interval selected by the user for the image set; the priority of the exclusion interval is higher than that of the scan interval; perform lesion scanning on the images within the scan interval of the non-exclusion interval according to the scanning strategy. That is, if the user finds that the selected scan interval contains invalid images during viewing, the exclusion interval is selected, and this interval is excluded from the scan interval. That is, if an interval is both included in the scan interval and the exclusion interval, according to the principle of the higher priority of the exclusion interval, this interval is not detected, that is, the interval segment that does not need to be scanned within the scan interval is actively filtered. Specifically, the user can click the preset "exclusion interval" button, and select the start time point and end time point of the exclusion interval by clicking twice, and add the time period to the exclusion interval, supporting the addition of multiple exclusion intervals. For example, as shown in Figure 2, it is a schematic diagram of a specific interval selection, including two scan intervals and one exclusion interval, and the scan coefficients of the two scan intervals are 0.6 and 0.7 respectively.

[0058] As can be seen from the above, in this embodiment, the image set collected by the capsule endoscope in the gastrointestinal tract detection is obtained, and the scanning interval is determined from the image set according to the user instruction; the scanning strategy corresponding to each scanning interval is determined; the scanning strategy includes frame-by-frame scanning and frame skipping scanning; according to the scanning strategy, the image in the corresponding scanning interval is scanned for lesions to obtain the scanning results of each scanning interval. It can be seen that by supporting the user to set the scanning interval, it is possible to scan the lesions only for the images in the scanning interval, quickly output the scanning results, and avoid wasting time on the global scan; at the same time, by using the scanning strategy corresponding to each scanning interval, it is possible to use different scanning strategies to scan the lesions of different scanning intervals, thereby improving the flexibility and accuracy of lesion scanning.

[0059] Correspondingly, the embodiment of the present application further discloses a lesion partition scanning device, as shown in FIG3 , the device comprises:

[0060] A scanning interval determination module 11 is used to obtain an image set collected by the capsule endoscope during gastrointestinal tract detection, and determine a scanning interval from the image set according to a user instruction;

[0061] A scanning strategy determination module 12, used to determine a scanning strategy corresponding to each of the scanning intervals; the scanning strategy includes frame-by-frame scanning and frame-skipping scanning;

[0062] The scanning module 13 is used to perform lesion scanning on the image in the corresponding scanning interval according to the scanning strategy to obtain the scanning result of each scanning interval.

[0063] As can be seen from the above, in this embodiment, the image set collected by the capsule endoscope in the gastrointestinal tract detection is obtained, and the scanning interval is determined from the image set according to the user instruction; the scanning strategy corresponding to each scanning interval is determined; the scanning strategy includes frame-by-frame scanning and frame skipping scanning; according to the scanning strategy, the image in the corresponding scanning interval is scanned for lesions to obtain the scanning results of each scanning interval. It can be seen that by supporting the user to set the scanning interval, it is possible to scan the lesions only for the images in the scanning interval, quickly output the scanning results, and avoid wasting time on the global scan; at the same time, by using the scanning strategy corresponding to each scanning interval, it is possible to use different scanning strategies to scan the lesions of different scanning intervals, thereby improving the flexibility and accuracy of lesion scanning.

[0064] In some specific embodiments, the scanning interval determination module 11 may specifically include:

[0065] A display unit, used to display the image set and a progress bar corresponding to the image set through a human-computer interaction interface;

[0066] The selection instruction acquisition unit is used to acquire the user's selection instruction for the target time point in the progress bar, and determine one or more scanning intervals from the image set according to the selection instruction.

[0067] In some specific embodiments, the scanning interval determination module 11 may specifically include:

[0068] An interval annotation adding unit is used to perform part recognition on the image set, divide the image set into multiple image subsets according to the recognition result, and add corresponding interval annotations to each image subset; the interval annotations include an interval from the body to the esophagus, an interval from the esophagus to the stomach, an interval from the stomach to the small intestine, and an interval from the small intestine to the colon;

[0069] The display unit is used to display all the image subsets and the interval annotations corresponding to each image subset through the human-computer interaction interface, so that the user can issue the selection instruction according to the interval annotations.

[0070] In some specific embodiments, the scanning strategy determination module 12 may specifically include:

[0071] The scanning strategy determining unit is used to determine the scanning strategy corresponding to each scanning interval according to the interval label corresponding to each scanning interval and the mapping relationship between the preset interval label and the scanning strategy.

[0072] In some specific embodiments, the lesion partition scanning device may specifically include:

[0073] an exclusion interval determination unit, used to obtain an exclusion interval selected by a user for the image set before performing lesion scanning on the image in the corresponding scanning interval according to the scanning strategy; the priority of the exclusion interval is greater than that of the scanning interval;

[0074] A scanning unit is used to perform lesion scanning on the image within the scanning interval of the non-exclusion interval according to the scanning strategy.

[0075] In some specific embodiments, the scanning interval determination module 11 may specifically include:

[0076] An image processing unit, used for acquiring an initial image collected by a capsule endoscope during gastrointestinal tract detection, performing similar image deletion processing on the initial image, obtaining the image set based on the remaining images, and taking the ratio of the number of remaining images to the number of initial images as a screening ratio;

[0077] Accordingly, the scanning strategy determination module 12 may include:

[0078] A screening ratio determination unit, used to determine the screening ratio corresponding to each scanning interval; the ratio of the number of remaining images in the same scanning interval to the number of initial images in the interval is the screening ratio of the interval;

[0079] A scanning coefficient determination unit, used to determine the scanning coefficient corresponding to each scanning interval according to the screening ratio corresponding to the scanning interval and a pre-fitted function of the scanning coefficient and the screening ratio; the scanning coefficient is inversely proportional to the screening ratio;

[0080] A scanning strategy determining unit is used to determine the scanning strategy corresponding to the scanning interval according to the scanning coefficient.

[0081] In some specific embodiments, the scanning strategy determination unit may be specifically configured to determine the scanning strategy corresponding to the scanning interval according to a size relationship between the scanning coefficient and a preset coefficient threshold and a frame rate of the image set.

[0082] Furthermore, an embodiment of the present application also discloses an electronic device, as shown in FIG4 . The content in the figure cannot be regarded as any limitation on the scope of use of the present application.

[0083] FIG4 is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the lesion partition scanning method disclosed in any of the aforementioned embodiments.

[0084] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0085] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon include an operating system 221, a computer program 222, and data 223 including an image set, etc. The storage method can be temporary storage or permanent storage.

[0086] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, so as to realize the operation and processing of the massive data 223 in the memory 22 by the processor 21, and it can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the lesion partition scanning method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0087] Furthermore, the embodiment of the present application also discloses a computer storage medium, in which computer executable instructions are stored, and when the computer executable instructions are loaded and executed by the processor, the steps of the lesion zoning scanning method disclosed in any of the above embodiments are implemented. By supporting the user to set the scanning interval, it is possible to perform lesion scanning only on the images within the scanning interval, quickly output the scanning results, and avoid wasting time on global scanning; at the same time, by using the scanning strategy corresponding to each scanning interval, it is possible to use different scanning strategies to scan lesions in different scanning intervals, thereby improving the flexibility and accuracy of lesion scanning.

[0088] Furthermore, the embodiment of the present application also discloses a computer program product, in which a computing program is stored, and when the computer program is loaded and executed by a processor, the steps of the lesion zoning scanning method disclosed in any of the above embodiments are implemented. By supporting the user to set the scanning interval, it is possible to perform lesion scanning only on the images within the scanning interval, quickly output the scanning results, and avoid wasting time on global scanning; at the same time, by using the scanning strategy corresponding to each scanning interval, it is possible to use different scanning strategies to perform lesion scanning on different scanning intervals, thereby improving the flexibility and accuracy of lesion scanning.

[0089] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0090] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0091] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0092] The above is a detailed introduction to a lesion zoning scanning method, device, equipment and storage medium provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for a general technician in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A lesion partition scanning method, characterized in that: include: Acquire an image set collected by the capsule endoscope during gastrointestinal tract detection, and determine a scanning interval from the image set according to a user instruction; Determine a scanning strategy corresponding to each of the scanning intervals; the scanning strategy includes frame-by-frame scanning and frame-skipping scanning; The images in the corresponding scanning intervals are scanned for lesions according to the scanning strategy to obtain scanning results for each of the scanning intervals.

2. The lesion partition scanning method according to claim 1, characterized in that: The step of acquiring an image set collected by the capsule endoscope during gastrointestinal tract detection and determining a scanning interval from the image set according to a user instruction includes: Displaying the image set and a progress bar corresponding to the image set through a human-computer interaction interface; A user selection instruction for a target time point in the progress bar is obtained, and one or more scanning intervals are determined from the image set according to the selection instruction.

3. The lesion partition scanning method according to claim 2, characterized in that: The step of determining a scanning interval from the image set according to a user instruction includes: Performing part recognition on the image set, dividing the image set into a plurality of image subsets according to the recognition result, and adding corresponding interval annotations to each of the image subsets; the interval annotations include an interval from the body to the esophagus, an interval from the esophagus to the stomach, an interval from the stomach to the small intestine, and an interval from the small intestine to the colon; All the image subsets and the interval markings corresponding to each image subset are displayed through the human-computer interaction interface, so that the user can issue the selection instruction according to the interval markings.

4. The lesion partition scanning method according to claim 3, characterized in that: The determining of the scanning strategy corresponding to each scanning interval includes: The scanning strategy corresponding to each scanning interval is determined according to the interval label corresponding to each scanning interval and the mapping relationship between the preset interval label and the scanning strategy.

5. The lesion partition scanning method according to claim 1, characterized in that: Before performing lesion scanning on the image in the corresponding scanning interval according to the scanning strategy, the method further includes: Acquire an exclusion interval selected by a user for the image set; the priority of the exclusion interval is greater than the scanning interval; The images within the scanning interval of the non-exclusion interval are scanned for lesions according to the scanning strategy.

6. The lesion partition scanning method according to any one of claims 1 to 5, characterized in that: The step of obtaining an image set collected by capsule endoscopy during gastrointestinal tract detection includes: Acquire an initial image collected by a capsule endoscope during gastrointestinal tract detection, perform similar image deletion processing on the initial image, obtain the image set based on the remaining images, and use the ratio of the number of remaining images to the number of initial images as a screening ratio; The determining of the scanning strategy corresponding to each scanning interval includes: Determine the screening ratio corresponding to each scanning interval; the ratio of the number of remaining images in the same scanning interval to the number of initial images in the interval is the screening ratio of the interval; Determine the scanning coefficient corresponding to each scanning interval according to the screening ratio corresponding to the scanning interval and the function of the scanning coefficient and the screening ratio obtained by pre-fitting; the scanning coefficient is inversely proportional to the screening ratio; A scanning strategy corresponding to the scanning interval is determined according to the scanning coefficient.

7. The lesion partition scanning method according to claim 6, characterized in that: The determining the scanning strategy corresponding to the scanning interval according to the scanning coefficient includes: A scanning strategy corresponding to the scanning interval is determined according to a magnitude relationship between the scanning coefficient and a preset coefficient threshold and a frame rate of the image set.

8. A lesion zoning scanning device, characterized in that: include: A scanning interval determination module is used to obtain an image set collected by the capsule endoscope during gastrointestinal tract detection, and determine a scanning interval from the image set according to a user instruction; A scanning strategy determination module, used to determine the scanning strategy corresponding to each scanning interval; the scanning strategy includes frame-by-frame scanning and frame skipping scanning; The scanning module is used to perform lesion scanning on the image in the corresponding scanning interval according to the scanning strategy to obtain the scanning result of each scanning interval.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the lesion partitioning scanning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein when the computer programs are executed by a processor, the lesion partitioning scanning method as described in any one of claims 1 to 7 is implemented.

Images