Report generation method and system, computer equipment, storage medium and program product

Abstract

The invention relates to a report generation method and system, computer equipment, a storage medium and a program product. The method comprises the following steps: acquiring an inspection video for performing target type inspection on an interested part of a to-be-inspected object so as to identify an operation instrument in the inspection video, determining inspection information of the target type inspection according to motion information of the operation instrument, and further generating an inspection report of the to-be-inspected object according to the inspection information of the target type inspection. According to the method, the inspection information is determined based on identification of the operation instrument in the inspection video, the operation instrument and the background environment are large in difference, obvious in difference and capable of being accurately identified, the accuracy of the inspection information is improved, and then the accuracy of the generated inspection report is improved.

Description

Technical Field

[0001] The present application relates to the field of medical assistance technology, and in particular to a report generation method, system, computer device, storage medium and program product. Background Art

[0002] An examination report with both pictures and text is a common medical examination report. Taking an endoscopic examination report as an example, usually, during the endoscopic examination, the doctor needs to perform a biopsy on the lesion and take a photo of the lesion before the biopsy for archiving, so as to complete the endoscopic examination report in combination with the biopsy results.

[0003] In traditional technology, in order to reduce manual workload, lesions are usually identified with the help of network models to automatically retain lesion images and generate endoscopic examination reports. However, the diverse morphology of lesions not only increases the difficulty of identification, but also often causes lesions to be unclear from normal tissues, such as the color characteristics of lesions in the digestive tract are similar to those of normal digestive tract tissues. All these reasons lead to poor accuracy of the obtained examination reports. Summary of the invention

[0004] Based on this, it is necessary to provide a report generation method, system, computer device, storage medium and program product to address the above technical issues.

[0005] In a first aspect, the present application provides a report generation method, comprising:

[0006] Acquire an inspection video for performing a target type inspection on a part of interest of the object to be inspected;

[0007] Identify the operating equipment in the inspection video, and determine the inspection information of the target type inspection based on the motion information of the operating equipment;

[0008] Generate an inspection report for the object to be inspected based on the inspection information of the target type inspection.

[0009] In one embodiment, the motion information of the operating device includes the appearance time of the operating device in the inspection video; and the inspection information of the target type inspection is determined according to the motion information of the operating device, including:

[0010] Determine the image of the lesion in the inspection video according to the appearance time of the operating instrument;

[0011] The inspection information of the target type inspection is generated according to the lesion image.

[0012] In one embodiment, determining a lesion image in an inspection video according to the appearance time of an operating instrument includes:

[0013] Determine the first appearance of the operating device based on the inspection video;

[0014] Obtain a reference video clip within a preset period of time before the first appearance moment in the inspection video;

[0015] The lesion image is determined in the reference video clip.

[0016] In one embodiment, determining a lesion image in a reference video segment includes:

[0017] Performing quality screening on each video frame in the reference video clip to obtain a clear video frame in each video frame;

[0018] The lesion position is detected for each clear video frame to obtain a lesion image in which the lesion area in all clear video frames is located in the target area; wherein the target area is an area in the lesion image formed with the center point of the lesion image as the center.

[0019] In one embodiment, the motion information of the operating instrument further includes the motion trajectory of the operating instrument; and the inspection information of the target type inspection is generated according to the lesion image, including:

[0020] Determine the number of times the operating device is operated in the inspection video according to the motion trajectory of the operating device;

[0021] The examination information of the target type examination is generated based on the lesion image and the number of operations.

[0022] In one embodiment, determining the number of operations of the operating instrument in the inspection video according to the motion trajectory of the operating instrument includes:

[0023] Obtaining the video frames to be analyzed in which the operating device exists in the inspection video, and obtaining the position of the operating device in each video frame to be analyzed;

[0024] Determine the motion trajectory of the operating device according to the time sequence of each video frame to be analyzed and the position of the operating device in the video frame to be analyzed;

[0025] The number of round trips of the operating instrument is counted according to the motion trajectory of the operating instrument to determine the number of operations.

[0026] In one embodiment, the inspection information of the target type inspection is generated according to the lesion image and the number of operations, including:

[0027] Determine the descriptive information of the target type examination based on the lesion image and the number of operations;

[0028] The inspection information of the target type inspection is generated according to the lesion image, the number of operations and the description information of the target type inspection.

[0029] In one embodiment, the description information of the target type inspection is determined according to the lesion image and the number of operations, including:

[0030] Determining lesion attribute information according to the lesion image; wherein the lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth;

[0031] Determine the lesion grade based on the lesion image and the number of operations;

[0032] The lesion attribute information and lesion grade are used as the descriptive information of the target type inspection.

[0033] In a second aspect, the present application also provides a report generation system, comprising:

[0034] A data acquisition unit, which acquires an inspection video for performing a target type inspection on a part of interest of the object to be inspected;

[0035] The device recognition unit recognizes the operating device in the inspection video and determines the inspection information of the target type inspection based on the motion information of the operating device;

[0036] The report generation unit generates an inspection report of the object to be inspected according to the inspection information of the target type inspection.

[0037] In a third aspect, the present application also provides an endoscope system, comprising:

[0038] Display, light source device, endoscope and report generation system as described above.

[0039] In a fourth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0040] In a fifth aspect, the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0041] In a sixth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0042] In the above-mentioned report generation method, system, computer device, storage medium and program product, an inspection video of a target type inspection of a part of interest of the object to be inspected is obtained to identify the operating instrument in the inspection video. And based on the motion information of the operating instrument, the inspection information of the target type inspection is determined, and then the inspection report of the object to be inspected is generated based on the inspection information of the target type inspection. In the above-mentioned method, the inspection information is determined based on the identification of the operating instrument in the inspection video. The difference between the operating instrument and the background environment is large and obvious, and it can be accurately identified, which improves the accuracy of the inspection information, and then improves the accuracy of the generated inspection report. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is an internal structure diagram of a computer device in one embodiment;

[0044] Figure 2 A schematic diagram of a report generation method in one embodiment;

[0045] Figure 3 A schematic diagram of a process for determining inspection information for a target type inspection in one embodiment;

[0046] Figure 4 A schematic diagram of a flow chart of determining inspection information for a target type inspection in another embodiment;

[0047] Figure 5 A schematic diagram of a process for generating inspection information for a target type inspection in one embodiment;

[0048] Figure 6 A schematic diagram of a flow chart of generating inspection information for a target type inspection in another embodiment;

[0049] Figure 7 A schematic diagram of a process for determining a lesion image in one embodiment;

[0050] Figure 8 A schematic diagram of a process for determining a lesion image in another embodiment;

[0051] Fig. 9 A schematic diagram of a flow chart for determining the number of operations in one embodiment;

[0052] Fig.10 A schematic diagram of a motion trajectory of an operating device in an embodiment;

[0053] Fig.11 A schematic diagram of a process for determining description information of a target type check in one embodiment;

[0054] Fig.12 A structural block diagram of a report generation system in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] The report generation method provided in the embodiment of the present application can be applied to Figure 1 In the computer device shown in FIG. 1 , the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 1As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a report generation method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0057] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0058] In one embodiment, Figure 2 As shown, a report generation method is provided, which is applied to Figure 1 The computer device in the example is used to illustrate, including the following steps:

[0059] S210: Obtain an inspection video of a target type inspection of a part of interest of the object to be inspected.

[0060] The inspection video is a video image collected during the process of performing a target type inspection on the part of interest of the object to be inspected. The target type inspection corresponds to the type of inspection report generated. When the target type inspection is a biopsy, a biopsy report is generated accordingly.

[0061] Optionally, the part of interest of the object to be inspected may be any organ region on the object to be inspected. For example, the part of interest may be a digestive tract organ of the object to be inspected, such as the small intestine, colorectum, stomach, throat, etc. The inspection video may be a video image including the part of interest, or may be a video image inside the part of interest, such as an endoscopic video of the digestive tract.

[0062] Optionally, during the process of performing a target type inspection on the part of interest of the object to be inspected, the computer device can directly obtain the inspection video of the part of interest through the camera carried by itself. The inspection video of the part of interest can also be obtained by an image acquisition device, and the computer device communicates with the image acquisition device, and then obtains the inspection video of the part of interest from the image acquisition device. For example, the computer device can communicate with an endoscope to obtain an endoscopic video of the digestive tract.

[0063] S220: Identify the operating device in the inspection video, and determine the inspection information of the target type inspection according to the motion information of the operating device.

[0064] It should be noted that, in the process of inspecting the part of interest, an operating instrument is required to perform an inspection operation on the part of interest. Different inspection types require different corresponding inspection operations. In the case of a biopsy on the part of interest, the inspection operation on the part of interest includes biopsy sampling. Among them, the embodiments of the present application do not impose too many restrictions on the instrument type of the operating instrument, which can be determined according to actual application conditions. For example, in some embodiments, the operating instrument can be a biopsy forceps.

[0065] The motion information of the operating device can be determined based on the video frame in which the operating device appears in the inspection video. The inspection information of the target type inspection is the content information filled in the inspection report, which can be determined based on the motion information of the operating device. Different types of motion information are used to determine different types of inspection information.

[0066] Optionally, the motion information of the operating instrument may include any information of the time of occurrence, duration of occurrence, motion trajectory, motion type, etc. of the operating instrument. The inspection information of the target type inspection may include information related to the lesion in the part of interest, such as any information of the lesion image, lesion size, lesion type, etc. In some optional embodiments, the inspection information may also include information related to the inspection operation, such as any information of the number of operations, operation duration, operation interval, etc.

[0067] Optionally, the computer device may detect the operating equipment for each video frame in the inspection video to identify the operating equipment in the inspection video and obtain the video frame including the operating equipment in the inspection video; the computer device may also identify the operating equipment in the inspection video based on the attribute features (such as shape and / or color) of the operating equipment and obtain the video frame including the operating equipment in the inspection video.

[0068] Optionally, the computer device may determine the motion information of the operating instrument based on the video frame including the operating instrument in the inspection video, and determine the inspection information corresponding to the motion information of the operating instrument based on the correspondence between the motion information and the inspection information. For example, in the case where the motion information of the operating instrument includes the appearance time of the operating instrument, the computer device may determine the lesion image in the inspection information based on the appearance time of the operating instrument; in the case where the motion information of the operating instrument includes the appearance duration of the operating instrument, the computer device may determine the operation duration in the inspection information based on the appearance duration of the operating instrument.

[0069] S230: Generate an inspection report of the object to be inspected according to the inspection information of the target type inspection.

[0070] Optionally, in an application scenario where a biopsy is performed on the digestive tract (such as the rectum) of the subject to be examined, a digestive tract biopsy report of the subject to be examined is generated accordingly.

[0071] Optionally, after obtaining the inspection information of the target type inspection, the computer device may obtain a preset report template corresponding to the target type inspection, and fill the inspection information into the corresponding type of filling area according to the information type of the inspection information to generate an inspection report of the object to be inspected. For example, in the case where the inspection information includes a lesion image and the number of operations of the operating instrument, the computer device may fill the lesion image into the filling area of ​​the lesion image in the preset report template, and fill the number of operations of the operating instrument into the filling area of ​​the number of operations (or number of tests) in the preset report template to generate an inspection report of the object to be inspected.

[0072] Optionally, after obtaining the inspection information of the target type inspection, the computer device can further obtain the user information of the object to be inspected and the inspection results of the target type inspection of the part of interest, so as to fill the user information, inspection results and inspection information of the target type inspection of the object to be inspected into the corresponding filling areas in the preset report template to generate an inspection report for the object to be inspected.

[0073] Optionally, the computer device may also obtain the acquisition time of the inspection video as the inspection time of the object to be inspected, and / or the generation time of the inspection result as the report generation time, and fill the above inspection time and / or report generation time into the corresponding filling area in the preset report template.

[0074] In the embodiment of the present application, the computer device obtains an inspection video of a target type inspection of a part of interest of the object to be inspected, so as to identify the operating device in the inspection video, and determine the inspection information of the target type inspection based on the motion information of the operating device, and then generate an inspection report of the object to be inspected based on the inspection information of the target type inspection. In the above method, the inspection information is determined based on the identification of the operating device in the inspection video. Since the difference between the operating device and the background environment is large and obvious, it can be accurately identified. Therefore, the embodiment of the present application can improve the accuracy of the inspection information, thereby improving the accuracy of the generated inspection report.

[0075] It should be understood that the entire process of generating the examination report in the embodiment of the present application is executed and implemented by a computer, and the generated examination report is only for the doctor's reference.

[0076] As an optional embodiment of the present application, the motion information of the operating device includes the appearance time of the operating device in the inspection video and the motion trajectory of the operating device. Based on this, in one embodiment, Figure 3 As shown, the above S220 determines the inspection information of the target type inspection according to the motion information of the operating device, including: S310 to S340.

[0077] S310: Determine a lesion image in the inspection video according to the appearance time of the operating instrument.

[0078] It should be noted that in actual applications, when a lesion appears in the inspection field of view, the operator needs to use an operating instrument to inspect the lesion. For example, the operator can control the camera / image acquisition device to stop moving, keep still, and use the operating instrument to inspect the lesion. Therefore, in the inspection video, if an operating instrument appears, and a lesion also appears in the video frame representing this time, the lesion image can be determined in the inspection video according to the time when the operating instrument appears.

[0079] Optionally, the computer device may detect the operating instrument for each video frame in the inspection video, determine the video frame where the operating instrument appears for the first time, and obtain the timestamp of the video frame where the operating instrument appears for the first time as the appearance time of the operating instrument, and then determine the lesion image in the inspection video according to the appearance time of the operating instrument. For example, the computer device may determine the video frame in the inspection video whose timestamp matches the appearance time of the operating instrument, and use the previous video frame of the video frame, that is, the previous video frame of the video frame where the operating instrument appears for the first time as the lesion image.

[0080] S320, determining the number of times the operating device is operated in the inspection video according to the movement trajectory of the operating device.

[0081] The number of times the operating device is operated is the number of times the operating device performs inspection operations.

[0082] Optionally, the computer device may obtain position information of the operating instrument in the video frame in which the operating instrument appears, determine a motion trajectory of the operating instrument based on the position information, and analyze the motion trajectory to obtain the number of inspection operations performed by the operating instrument in the inspection video.

[0083] Optionally, in an application scenario where a biopsy is performed on the digestive tract of the subject to be inspected, bleeding may occur during the biopsy sampling, and the sampling location is different each time. The computer device can obtain a video frame in which the operating instrument appears as the video to be analyzed, and then perform bleeding point detection on the video frame to be analyzed, so as to use the number of bleeding points detected at different locations as the number of biopsy sampling operations using the biopsy forceps.

[0084] S330. Determine description information of the target type inspection according to the lesion image and the number of operations.

[0085] Optionally, the description information of the target type inspection may include description information of the lesion in the part of interest, such as any information of the lesion location, lesion size, lesion type, etc. It may also include an overall description of the target type inspection, such as any information of the information such as the inspection time is long, the number of operations is frequent, etc., and may also include a description of the credibility of the inspection result, such as the inspection credibility is high.

[0086] S340: Generate inspection information of the target type inspection according to the lesion image, the number of operations, and the description information of the target type inspection.

[0087] Optionally, the computer device may summarize the lesion image, the number of operations, and the description information of the target type inspection determined based on different motion information of the operating instrument as the inspection information of the target type inspection.

[0088] In the embodiment of the present application, the computer device determines the lesion image in the inspection video according to the appearance time of the operating instrument, determines the number of operations of the operating instrument in the inspection video according to the motion trajectory of the operating instrument, and determines the description information of the target type inspection according to the lesion image and the number of operations, and then generates the inspection information of the target type inspection according to the lesion image, the number of operations and the description information of the target type inspection. In the above method, different motion information is used to determine different inspection information, and the obtained lesion image, the number of operations of the operating instrument and the description information of the target type inspection enrich the inspection information and improve the comprehensiveness of the inspection information in the generated inspection report.

[0089] Generally, the determination of the lesion image and the determination of the number of operations can be implemented independently, and there is no necessary binding relationship between the two. Therefore, the inspection information of the target type inspection can be obtained based only on the lesion image, based only on the number of operations, or based on the lesion image and the number of operations. Among them, the lesion image can be determined according to the appearance time of the operating instrument, and the number of operations can be determined according to the movement trajectory of the operating instrument.

[0090] In one embodiment, when the motion information of the operating device includes the appearance time of the operating device in the inspection video, such as Figure 4 As shown, in the above S220, the inspection information of the target type inspection is determined according to the motion information of the operating device, including: S410 to S420.

[0091] S410: Determine a lesion image in the inspection video according to the appearance time of the operating instrument.

[0092] For the specific process, please refer to S310 in the aforementioned embodiment and the specific contents in the related embodiments, which will not be repeated here.

[0093] S420: Generate inspection information of the target type inspection according to the lesion image.

[0094] When the motion information of the operating instrument only includes the moment when the operating instrument appears in the inspection video, the computer device can directly use the lesion image as the inspection information for the target type inspection, and can also determine other detection information based on the lesion image, and use the lesion image together with the determined other detection information as the inspection information for the target type inspection.

[0095] Optionally, other detection information determined based on the lesion image is lesion-related information, which may include at least one of lesion size, lesion type, and lesion grade.

[0096] On this basis, when the motion information of the operating device also includes the motion trajectory of the operating device, in one embodiment, as Figure 5 As shown, the above S420, generating inspection information of target type inspection according to the lesion image, includes: S510 to S520.

[0097] S510: Determine the number of times the operating device is operated in the inspection video according to the movement trajectory of the operating device.

[0098] For the specific process, please refer to S320 in the aforementioned embodiment and the specific contents in the related embodiments, which will not be repeated here.

[0099] S520: Generate inspection information of the target type inspection according to the lesion image and the number of operations.

[0100] When the motion information of the operating instrument includes both the appearance time of the operating instrument in the inspection video and the motion trajectory of the operating instrument in the inspection video, the computer device can directly use the lesion image determined based on the appearance time of the operating instrument and the number of operations of the operating instrument determined based on the motion trajectory of the operating instrument as the inspection information of the target type inspection, and can also determine other detection information based on the lesion image and the number of operations, and use the lesion image, the number of operations together with the other determined detection information as the inspection information of the target type inspection.

[0101] Optionally, other detection information determined based on the lesion image and the number of operations includes lesion-related information and operation-related information. The lesion-related information may include at least one of lesion size, lesion type, and lesion level, and the operation-related information may include at least one of operation duration, operation interval, and operation complexity level.

[0102] In one embodiment, if Figure 6 As shown, the above S520, generating inspection information of the target type inspection according to the lesion image and the number of operations, includes: S610 to S620.

[0103] S610: Determine description information of the target type inspection according to the lesion image and the number of operations.

[0104] For the specific process, please refer to S330 in the aforementioned embodiment and the specific contents in the related embodiments, which will not be repeated here.

[0105] S620: Generate inspection information of the target type inspection according to the lesion image, the number of operations, and the description information of the target type inspection.

[0106] For the specific process, please refer to S340 in the aforementioned embodiment and the specific contents in the related embodiments, which will not be repeated here.

[0107] It should be noted that the embodiment of the present application does not specifically limit the order of determining the lesion image and the number of operations. Figures 4 to 6 In the corresponding embodiment, a process is listed in which the lesion image is first determined based on the appearance time of the operating instrument, the number of operations of the operating instrument is then determined based on the motion trajectory of the operating instrument, and the inspection information is then determined based on the lesion image and the number of operations. In other embodiments, the number of operations of the operating instrument may be first determined based on the motion trajectory of the operating instrument, the lesion image is then determined based on the appearance time of the operating instrument, and the inspection information is then determined based on the lesion image and the number of operations.

[0108] Considering that in actual applications, the operator generally uses the operating instrument to inspect the lesion only when the lesion appears in the inspection field of view, that is, the operating instrument in the inspection video lags behind the appearance of the lesion. Therefore, in an optional embodiment of the present application, Figure 7 As shown, the above S310, determining the lesion image in the inspection video according to the appearance time of the operating instrument, includes: S710 to S730.

[0109] S710. Determine the first appearance time of the operating instrument according to the inspection video.

[0110] In an embodiment of the present application, the video frames of the inspection video can be selected to detect the operating device, so as to determine the video frames in which the operating device exists. On this basis, the video frame in which the operating device appears earliest is determined, and the timestamp of the video frame is obtained to determine the first appearance time of the operating device. Among them, the embodiment of the present application does not make too many restrictions on the detection method of the operating device, which can be determined according to the actual application. For example, some object recognition algorithms can be used to identify the operating device, and some detection models can also be used to identify the operating device.

[0111] Optionally, the computer device may input each video frame in the inspection video into the detection model of the operating instrument to identify the video frames in which the operating instrument exists in the inspection video, and obtain the timestamps of the video frames in which the operating instrument exists, and use the earliest timestamp as the first appearance time of the operating instrument. For example, taking the application scenario of performing a biopsy on the digestive tract of the subject to be inspected as an example, the corresponding operating instrument is a biopsy forceps. The computer device inputs each video frame in the digestive tract inspection video into the biopsy forceps detection model to identify the video frames in the digestive tract inspection video in which the biopsy forceps exists.

[0112] The detection model of the operating instrument is a network model obtained by training a large number of images of the operating instrument as samples. Optionally, the detection model of the operating instrument can be a classification model obtained by a support vector machine (SVM) algorithm or a deep learning classification network ResNet, or a detection model obtained by a Histogram of Oriented Gradient (HOG) algorithm or a deep learning target detection network yolo.

[0113] S720: Obtain a reference video segment within a preset period of time before the first appearance moment in the inspection video.

[0114] Optionally, after determining the first appearance time of the operating device in the inspection video, the computer device can obtain a video frame in the inspection video whose timestamp is within a preset time period before the first appearance time according to the first appearance time as a reference video clip (hereinafter referred to as a reference video clip). Among them, the embodiment of the present application does not make too many restrictions on the range of the preset time period obtained, and can be selected and set according to actual needs. For example, it can be a range of n seconds before the first appearance time, where n can be any positive number, such as any value from 3 to 5.

[0115] Take an example for illustration, assuming n=5, and assuming T=50s is the first appearance time of the operating device in the inspection video, that is, the operating device first appears at the 50th second of the inspection video. On this basis, the computer device can obtain video frames within a preset period of time such as 5s before the 50th second, that is, the video frames between the 45th second and the 50th second in the inspection video can be used as reference video clips.

[0116] S730: Determine a lesion image in the reference video segment.

[0117] After obtaining the reference video clip, the embodiment of the present application can confirm whether the video frame in the reference video clip contains a lesion. Among them, the embodiment of the present application does not make too many restrictions on the method of determining whether it is a lesion, and it can be determined according to the actual application situation.

[0118] As an optional embodiment of the present application, considering that in actual applications, operators often use operating instruments only after discovering lesions. And the value of n is generally small (such as a value between 3 and 5), that is, the reference video clip obtained is also a video clip shot within a short period of time before the use of the operating instrument. Therefore, in actual applications, it can be determined that there are lesions in all video frames in the reference video clip and no operating instrument. That is, each video frame in the reference video clip contains a lesion. Optionally, the computer device can select a video frame in the reference video clip as a lesion image. For example, select any video frame in the reference video clip, or the last video frame as the lesion image.

[0119] In the embodiment of the present application, the computer device determines the first appearance time of the operating instrument according to the inspection video, so as to obtain a reference video clip within a preset period before the first appearance time in the inspection video, so as to determine the lesion image in the reference video clip. In the above method, the priori that the operating instrument lags behind the appearance of the lesion in the inspection video is utilized, the range of video data for determining the lesion image is narrowed, the efficiency of determining the lesion image is improved, and the efficiency of report generation is improved as a whole.

[0120] In order to obtain a clear lesion image with the lesion centered, in an optional embodiment, as Figure 8As shown, the above S730, determining the lesion image in the reference video clip, includes: S810 to S820.

[0121] S810: Perform quality screening processing on each video frame in the reference video segment to obtain a clear video frame among the video frames.

[0122] In the embodiment of the present application, it is possible to select to perform image quality detection on each video frame in the reference video clip, so as to determine the video frame with clear image quality among the video frames. Among them, the embodiment of the present application does not make too many restrictions on the image quality detection method, which can be determined according to the actual application. For example, the image quality can be determined based on the image analysis algorithm, and some detection models can also be selected to determine the image instructions.

[0123] Optionally, the computer device may input each video frame in the reference video clip into an image quality classification model to obtain a quality level of each video frame. The quality level of the video frame is used to measure whether the video frame is clear. The higher the quality level, the clearer the corresponding video frame; the lower the quality level, the less clear (i.e., blurry) the corresponding video frame.

[0124] Optionally, after obtaining the quality level of each video frame in the reference video clip, the computer device may compare the quality level of each video frame with a preset level requirement to select video frames that meet the preset level requirement in the reference video clip as the above-mentioned clear video frames.

[0125] S820, performing lesion position detection on each clear video frame to obtain lesion images in which the lesion area in all clear images is located in the target area.

[0126] The target region is a region in the lesion image formed with the center point of the lesion image as the center. The lesion image with the lesion region located in the target region is the lesion image with the lesion region centered.

[0127] Typically, when a lesion appears in the inspection field of view, the operator will adjust the camera / image acquisition device to center the lesion, that is, to make the lesion located in the target area of ​​the lesion image.

[0128] In the embodiment of the present application, it is possible to select the detection of the lesion to be carried out on the clear video frame, thereby determining the position of the lesion area in each clear video frame. On this basis, it is determined that the lesion area is located in the clear video frame of the target area. Wherein, the embodiment of the present application does not make too many restrictions on the detection mode of the lesion, and can be determined according to practical application. For example, the lesion recognition algorithm of the corresponding type can be used to identify the lesion, and some detection models can also be selected to identify the lesion.

[0129] Optionally, after obtaining the clear video frames in the reference video clip, the computer device detects the lesion position on all the clear video frames, such as inputting each clear video frame into a lesion detection model to obtain the lesion position in each clear video frame, and then determines the clear video frame in which the lesion area is located in the target area as the lesion image.

[0130] In an embodiment of the present application, the computer device determines the first appearance time of the operating instrument according to the inspection video, and obtains a reference video clip within a preset time period before the first appearance time in the inspection video, and then determines the lesion image in the reference video clip. Specifically, each video frame in the reference video clip can be subjected to quality screening processing to obtain a clear video frame in each video frame, and then the lesion position detection is performed on each clear video frame to obtain a lesion image in which the lesion area is located in the target area in all clear video frames. The above method can be used to obtain a lesion image with a clean picture, that is, including the lesion but not the operating instrument, clear quality, and the lesion centered, thereby improving the presentation effect of the lesion image.

[0131] As an optional embodiment of determining the number of times an operating device is operated in an inspection video in the present application, Fig. 9 As shown, the above S320, determining the operation times of the operating instrument in the inspection video according to the movement trajectory of the operating instrument, includes: S910 to S930.

[0132] S910, obtaining the video frames to be analyzed in which the operating instrument exists in the inspection video, and obtaining the position of the operating instrument in each video frame to be analyzed.

[0133] Optionally, the computer device may identify the operating device in each video frame in the inspection video to obtain the video frames in which the operating device exists in the inspection video as the video frames to be analyzed, and may also obtain the position of the operating device in each video frame to be analyzed.

[0134] In the embodiment of the present application, the video frames of the inspection video can be selected to detect the operating device, so as to determine the video frames to be analyzed in which the operating device exists. On this basis, the position of the operating device in the video frame to be analyzed is obtained. Among them, the embodiment of the present application does not make too many restrictions on the detection method of the operating device, which can be determined according to the actual application. For example, some object recognition algorithms can be used to identify the operating device, and some detection models can also be used to identify the operating device.

[0135] Optionally, the computer device may input each video frame in the inspection video into the detection model of the operating instrument to identify the video frames to be analyzed in which the operating instrument exists in the inspection video, and obtain the position of the operating instrument in each video frame to be analyzed.

[0136] S920: Determine a motion trajectory of the operating device according to the time sequence of each to-be-analyzed video frame and the position of the operating device in the to-be-analyzed video frame.

[0137] When a lesion appears in the inspection field of view, the operator will generally control the camera / image acquisition device to stop moving, keep it still, and use the operating instrument to perform corresponding inspection operations on the part of interest until the inspection operation is completed. This indicates that the video frame to be analyzed in which the operating instrument appears in the inspection video is a still picture.

[0138] Optionally, the computer device may sequentially connect the positions of the operating instruments in the video frames to be analyzed according to the time sequence of each video frame to be analyzed to form a motion trajectory of the operating instrument. For example, assuming that the video frames to be analyzed include 10 video frames P1 to P10, since the video frames to be analyzed P1 to P10 are still images with the same background content, video frame P1 may be used for representation, such as Figure 7 As shown, the computer device obtains the position W1 of the operating device in the video frame to be analyzed P1, the position W2 of the operating device in the video frame to be analyzed P2, the position W3 of the operating device in the video frame to be analyzed P3, ... the position W8 of the operating device in the video frame to be analyzed P8, and sequentially connects the positions W1 to W10 of the operating device according to the time sequence of the video frames to be analyzed P1 to P10, so as to obtain the following: Fig.10 The motion trajectory of the operating instrument is shown by the dotted line.

[0139] Optionally, to improve the trajectory accuracy, after obtaining the position of the operating device in the video frame to be analyzed, for all two adjacent video frames to be analyzed, the computer device can obtain the distance between the positions of the operating devices in the two adjacent video frames to be analyzed. If the distance is less than a preset distance threshold (which can be understood as the operating device shaking), delete the video frame to be analyzed with a later time sequence in the two adjacent video frames to be analyzed, and then determine the motion trajectory of the operating device based on the position of the operating device in the remaining video frames to be analyzed. Fig.10 As shown, when the distance L between the position W3 of the operating device in the video frame P3 to be analyzed and the position W4 of the operating device in the video frame P4 to be analyzed is less than the distance threshold L0, the computer device deletes the video frame P4 to be analyzed to determine the movement trajectory of the operating device according to the positions W1~W3, W5~W10 of the operating device in the remaining video frames P1~P3, P5~P10 to be analyzed.

[0140] S930. Count the number of round trips of the operating device according to the motion trajectory of the operating device to determine the number of operations.

[0141] Optionally, after obtaining the motion trajectory of the operating instrument, the computer device may determine the number of round trips of the operating instrument (also referred to as a "round trip cycle") based on the motion trajectory, and use the number of round trips as the number of operations performed by the operating instrument. For example, taking the application scenario of performing a biopsy on the digestive tract of the subject to be inspected as an example, when the computer device determines the motion trajectory of the biopsy forceps as follows: Fig.10 As shown, the number of round trips of the biopsy forceps is statistically obtained to be 1, and thus the number of biopsy sampling operations of the biopsy forceps is 1.

[0142] In the embodiment of the present application, the computer device obtains the video frames to be analyzed in which the operating instrument exists in the inspection video, obtains the position of the operating instrument in each video frame to be analyzed, and determines the motion trajectory of the operating instrument according to the timing of each video frame to be analyzed and the position of the operating instrument in the video frame to be analyzed, and then counts the number of round trips of the operating instrument according to the motion trajectory of the operating instrument to determine the number of operations. In the above method, the motion trajectory of the operating instrument can accurately reflect the number of operations of the operating instrument for inspection operations, improve the accuracy of the data and enrich the report content.

[0143] As an optional embodiment of determining the description information of the target type check in this application, such as Fig.11 As shown, the above S330, determining the description information of the target type inspection according to the lesion image and the number of operations, includes: S1110 to S1130.

[0144] S1110. Determine lesion attribute information according to the lesion image.

[0145] The lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth.

[0146] Optionally, after obtaining the lesion image, the computer device may extract the lesion area in the lesion image, and determine the lesion attribute information based on the lesion area. For example, the size of the lesion area may be extracted as the lesion size, the shape of the lesion area may be extracted as the lesion shape, or the roughness analysis may be performed on the lesion area to determine whether the lesion surface is smooth.

[0147] S1120. Determine the lesion grade according to the lesion image and the number of operations.

[0148] The lesion grade is used to characterize the severity of the lesion in the lesion image. The higher the lesion grade, the more severe the lesion in the lesion image.

[0149] In the embodiment of the present application, the lesion grade can be predicted based on the lesion image and the number of operations. Wherein, the embodiment of the present application does not make too many restrictions on the prediction method of the lesion grade, and can be determined according to practical applications. For example, some prediction algorithms can be used to obtain the lesion grade, and some prediction models can also be used to obtain the lesion grade.

[0150] Optionally, the computer device may input the lesion image and the number of operations determined based on the inspection video of the site of interest into a grade prediction model, and the grade prediction model outputs the severity of the lesion in the lesion image, that is, the lesion grade.

[0151] Optionally, the grade prediction model is a deep learning model trained using a large number of historical lesion images and a corresponding number of operations.

[0152] S1130. Use the lesion attribute information and lesion grade as descriptive information of the target type inspection.

[0153] Optionally, the computer device may use the lesion attribute information and the lesion level together as descriptive information of the target type inspection.

[0154] In an embodiment of the present application, a computer device determines lesion attribute information based on a lesion image, and determines a lesion grade based on the lesion image and the number of operations, and then uses the lesion attribute information and the lesion grade as descriptive information for the target type inspection. Among them, the lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth. In the above method, the lesion image can accurately reflect the lesion attribute characteristics, the lesion image and the number of operations can realize the evaluation of the lesion grade, and the credibility of the obtained lesion attribute characteristics and lesion grade further enriches the report content.

[0155] It should be understood that the information such as lesion attribute characteristics and lesion grade obtained in the embodiments of the present application is only for doctors' reference.

[0156] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0157] Based on the same inventive concept, the embodiment of the present application also provides a report generation system for implementing the above-mentioned report generation method. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above-mentioned method, so the specific limitations in one or more report generation system embodiments provided below can refer to the above-mentioned limitations on the report generation method, and will not be repeated here.

[0158] In one embodiment, Fig.12 As shown, a report generation system is provided, comprising: a data acquisition unit 1201, an instrument identification unit 1202 and a report generation unit 1203, wherein:

[0159] The data acquisition unit 201 acquires an inspection video for performing a target type inspection on a part of interest of the object to be inspected;

[0160] The device recognition unit 1202 recognizes the operating device in the inspection video and determines the inspection information of the target type inspection according to the motion information of the operating device;

[0161] The report generating unit 1203 generates an inspection report of the object to be inspected according to the inspection information of the target type inspection.

[0162] In one embodiment, the motion information of the operating device includes checking the time when the operating device appears in the video; the device identification unit 1202 includes:

[0163] An image submodule, used to determine the image of the lesion in the inspection video according to the appearance time of the operating instrument;

[0164] The information submodule is used to generate inspection information of the target type inspection according to the lesion image.

[0165] In one embodiment, the image submodule includes:

[0166] A time unit, used to determine the first appearance time of the operating instrument based on the inspection video;

[0167] A reference unit, used to obtain a reference video segment within a preset period before the first appearance moment in the inspection video;

[0168] The lesion unit is used to determine the lesion image in the reference video segment.

[0169] In one embodiment, the focus unit comprises:

[0170] The quality subunit is used to perform quality screening on each video frame in the reference video clip to obtain a clear video frame in each video frame;

[0171] The position subunit is used to detect the lesion position of each clear video frame to obtain a lesion image in which the lesion area in all clear video frames is located in the target area; wherein the target area is the area in the lesion image formed with the center point of the lesion image as the center.

[0172] In one embodiment, the motion information of the operating device further includes the motion trajectory of the operating device; the information submodule includes:

[0173] An operation number unit, used to determine the operation number of the operating instrument in the inspection video according to the motion trajectory of the operating instrument;

[0174] The inspection information unit is used to generate inspection information of the target type inspection according to the lesion image and the number of operations.

[0175] In one embodiment, the operation number unit includes:

[0176] The position subunit is used to obtain the video frames to be analyzed in which the operating device exists in the inspection video, and obtain the position of the operating device in each video frame to be analyzed;

[0177] A trajectory subunit, used to determine the motion trajectory of the operating instrument according to the time sequence of each video frame to be analyzed and the position of the operating instrument in the video frame to be analyzed;

[0178] The statistical subunit is used to count the number of round trips of the operating instrument according to the motion trajectory of the operating instrument to determine the number of operations.

[0179] In one embodiment, the checking information unit includes:

[0180] A description subunit, used to determine description information of the target type examination according to the lesion image and the number of operations;

[0181] The inspection subunit is used to generate inspection information of the target type inspection according to the lesion image, the number of operations and the description information of the target type inspection.

[0182] In one embodiment, the description subunit includes:

[0183] An attribute subunit, used to determine lesion attribute information according to the lesion image; wherein the lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth;

[0184] A grade subunit, used to determine the grade of the lesion according to the lesion image and the number of operations;

[0185] The information subunit is used to use the lesion attribute information and the lesion grade as the descriptive information of the target type inspection.

[0186] Each module in the above report generation system can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0187] In one embodiment, an endoscope system is provided, comprising:

[0188] A display, a light source device, an endoscope, and a report generating system for any of the above.

[0189] The display may be used to display the inspection report generated by the report generating system.

[0190] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0191] Acquire an inspection video of a target type inspection of a part of interest of the object to be inspected; identify an operating instrument in the inspection video, and determine inspection information of the target type inspection based on motion information of the operating instrument; and generate an inspection report of the object to be inspected based on the inspection information of the target type inspection.

[0192] In one embodiment, the motion information of the operating device includes checking the appearance time of the operating device in the video; when the processor executes the computer program, the following steps are also implemented:

[0193] A lesion image is determined in the inspection video according to the appearance time of the operating instrument; and inspection information of the target type inspection is generated according to the lesion image.

[0194] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0195] Determine the first appearance time of the operating instrument according to the inspection video; obtain a reference video clip within a preset time period before the first appearance time in the inspection video; and determine the lesion image in the reference video clip.

[0196] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0197] Perform quality screening on each video frame in the reference video clip to obtain a clear video frame in each video frame; perform lesion position detection on each clear video frame to obtain a lesion image in which the lesion area in all clear video frames is located in the target area; wherein the target area is an area in the lesion image formed with the center point of the lesion image as the center.

[0198] In one embodiment, the motion information of the operating device further includes the motion trajectory of the operating device; when the processor executes the computer program, the following steps are also implemented:

[0199] The number of times the operating instrument is operated in the inspection video is determined according to the motion trajectory of the operating instrument; and the inspection information of the target type inspection is generated according to the lesion image and the number of operations.

[0200] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0201] Obtain the video frames to be analyzed in which the operating instrument exists in the inspection video, and obtain the position of the operating instrument in each video frame to be analyzed; determine the movement trajectory of the operating instrument according to the time sequence of each video frame to be analyzed and the position of the operating instrument in the video frame to be analyzed; and count the number of round trips of the operating instrument according to the movement trajectory of the operating instrument to determine the number of operations.

[0202] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0203] Determine the description information of the target type inspection according to the lesion image and the number of operations; generate the inspection information of the target type inspection according to the lesion image, the number of operations and the description information of the target type inspection.

[0204] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0205] Determine lesion attribute information based on the lesion image; wherein the lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth; determine the lesion level based on the lesion image and the number of operations; use the lesion attribute information and the lesion level as descriptive information of the target type inspection.

[0206] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0207] Acquire an inspection video of a target type inspection of a part of interest of the object to be inspected; identify an operating instrument in the inspection video, and determine inspection information of the target type inspection based on motion information of the operating instrument; and generate an inspection report of the object to be inspected based on the inspection information of the target type inspection.

[0208] In one embodiment, the motion information of the operating device includes checking the appearance time of the operating device in the video; when the computer program is executed by the processor, the following steps are also implemented:

[0209] A lesion image is determined in the inspection video according to the appearance time of the operating instrument; and inspection information of the target type inspection is generated according to the lesion image.

[0210] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0211] Determine the first appearance time of the operating instrument according to the inspection video; obtain a reference video clip within a preset time period before the first appearance time in the inspection video; and determine the lesion image in the reference video clip.

[0212] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0213] Perform quality screening on each video frame in the reference video clip to obtain a clear video frame in each video frame; perform lesion position detection on each clear video frame to obtain a lesion image in which the lesion area in all clear video frames is located in the target area; wherein the target area is an area in the lesion image formed with the center point of the lesion image as the center.

[0214] In one embodiment, the motion information of the operating device also includes the motion trajectory of the operating device; when the computer program is executed by the processor, the following steps are also implemented:

[0215] The number of times the operating instrument is operated in the inspection video is determined according to the motion trajectory of the operating instrument; and the inspection information of the target type inspection is generated according to the lesion image and the number of operations.

[0216] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0217] Obtain the video frames to be analyzed in which the operating instrument exists in the inspection video, and obtain the position of the operating instrument in each video frame to be analyzed; determine the movement trajectory of the operating instrument according to the time sequence of each video frame to be analyzed and the position of the operating instrument in the video frame to be analyzed; and count the number of round trips of the operating instrument according to the movement trajectory of the operating instrument to determine the number of operations.

[0218] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0219] Determine the description information of the target type inspection according to the lesion image and the number of operations; generate the inspection information of the target type inspection according to the lesion image, the number of operations and the description information of the target type inspection.

[0220] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0221] Determine lesion attribute information based on the lesion image; wherein the lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth; determine the lesion level based on the lesion image and the number of operations; use the lesion attribute information and the lesion level as descriptive information of the target type inspection.

[0222] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0223] Acquire an inspection video of a target type inspection of a part of interest of the object to be inspected; identify an operating instrument in the inspection video, and determine inspection information of the target type inspection based on motion information of the operating instrument; and generate an inspection report of the object to be inspected based on the inspection information of the target type inspection.

[0224] In one embodiment, the motion information of the operating device includes checking the appearance time of the operating device in the video; when the computer program is executed by the processor, the following steps are also implemented:

[0225] A lesion image is determined in the inspection video according to the appearance time of the operating instrument; and inspection information of the target type inspection is generated according to the lesion image.

[0226] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0227] Determine the first appearance time of the operating instrument according to the inspection video; obtain a reference video clip within a preset time period before the first appearance time in the inspection video; and determine the lesion image in the reference video clip.

[0228] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0229] Perform quality screening on each video frame in the reference video clip to obtain a clear video frame in each video frame; perform lesion position detection on each clear video frame to obtain a lesion image in which the lesion area in all clear video frames is located in the target area; wherein the target area is an area in the lesion image formed with the center point of the lesion image as the center.

[0230] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0231] The number of times the operating instrument is operated in the inspection video is determined according to the motion trajectory of the operating instrument; and the inspection information of the target type inspection is generated according to the lesion image and the number of operations.

[0232] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0233] Obtain the video frames to be analyzed in which the operating instrument exists in the inspection video, and obtain the position of the operating instrument in each video frame to be analyzed; determine the movement trajectory of the operating instrument according to the time sequence of each video frame to be analyzed and the position of the operating instrument in the video frame to be analyzed; and count the number of round trips of the operating instrument according to the movement trajectory of the operating instrument to determine the number of operations.

[0234] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0235] Determine the description information of the target type inspection according to the lesion image and the number of operations; generate the inspection information of the target type inspection according to the lesion image, the number of operations and the description information of the target type inspection.

[0236] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0237] Determine lesion attribute information based on the lesion image; wherein the lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth; determine the lesion level based on the lesion image and the number of operations; use the lesion attribute information and the lesion level as descriptive information for target type detection.

[0238] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0239] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0240] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0241] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A report generation method, characterized in that: The method comprises: Acquire an inspection video for performing a target type inspection on a part of interest of the object to be inspected; Identifying an operating device in the inspection video, and determining inspection information of the target type inspection based on motion information of the operating device; An inspection report of the object to be inspected is generated according to the inspection information of the target type inspection.

2. The method according to claim 1, characterized in that The movement information of the operating device includes the appearance time of the operating device in the inspection video; The step of determining the inspection information of the target type inspection according to the motion information of the operating device includes: Determining a lesion image in the inspection video according to the appearance time of the operating instrument; The inspection information of the target type inspection is generated according to the lesion image.

3. The method according to claim 2, characterized in that The step of determining the lesion image in the inspection video according to the appearance time of the operating instrument comprises: Determining the first appearance time of the operating instrument according to the inspection video; Acquire a reference video clip within a preset time period before the first appearance moment in the inspection video; The lesion image is determined in the reference video segment.

4. The method according to claim 3, characterized in that The step of determining the lesion image in the reference video segment comprises: Performing quality screening processing on each video frame in the reference video clip to obtain a clear video frame among the video frames; Lesion position detection is performed on each of the clear video frames to obtain the lesion image in which the lesion area in all clear video frames is located in the target area; wherein the target area is an area in the lesion image formed with the center point of the lesion image as the center.

5. The method according to claim 2, characterized in that: The motion information of the operating instrument also includes the motion trajectory of the operating instrument; the inspection information of the target type inspection generated according to the lesion image includes: Determining the number of times the operating instrument is operated in the inspection video according to the motion trajectory of the operating instrument; The inspection information of the target type inspection is generated according to the lesion image and the number of operations.

6. The method according to claim 5, characterized in that The step of determining the number of times the operating device is operated in the inspection video according to the motion trajectory of the operating device includes: Obtaining the video frames to be analyzed in which the operating device exists in the inspection video, and obtaining the position of the operating device in each of the video frames to be analyzed; Determining a motion trajectory of the operating device according to the time sequence of each of the to-be-analyzed video frames and the position of the operating device in the to-be-analyzed video frames; The number of round trips of the operating device is counted according to the motion trajectory of the operating device to determine the number of operations.

7. The method according to claim 5, characterized in that The step of generating the inspection information of the target type inspection according to the lesion image and the number of operations includes: Determining description information of the target type inspection according to the lesion image and the number of operations; The inspection information of the target type inspection is generated according to the lesion image, the number of operations and the description information of the target type inspection.

8. The method according to claim 7, characterized in that The step of determining the description information of the target type inspection according to the lesion image and the number of operations includes: Determining lesion attribute information according to the lesion image; wherein the lesion attribute information includes at least one of the lesion size, shape, and whether the surface is smooth; Determining a lesion grade according to the lesion image and the number of operations; The lesion attribute information and the lesion grade are used as descriptive information of the target type inspection.

9. A report generation system, characterized in that: The system comprises: A data acquisition unit, which acquires an inspection video for performing a target type inspection on a part of interest of the object to be inspected; An instrument recognition unit, which recognizes the operating instrument in the inspection video and determines the inspection information of the target type inspection according to the motion information of the operating instrument; A report generating unit generates an inspection report of the object to be inspected according to the inspection information of the target type inspection.

10. An endoscope system, characterized in that: The endoscope system comprises: A display, a light source device, an endoscope, and a report generating system as claimed in claim 9.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

13. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images