A quality assessment method and device for electronic endoscope detection process

Abstract

The present application relates to a quality assessment method and device for an electronic endoscope inspection process, comprising receiving a basic image sequence captured by an electronic endoscope, screening the basic image sequence to obtain a sample image sequence for highlighting markers; analyzing the sample image sequence frame by frame to select a target image sequence with markers; comparing the target image sequence with a preset marker image sequence for similarity to obtain a marker image for reference; and evaluating the accuracy of the basic image sequence based on the generation order of the marker images. By calculating the evaluation value corresponding to the operation of obtaining the basic image sequence based on the position label of the marker image in the preset marker image sequence, the standardization of the electronic endoscope operation can be more accurately evaluated, and the accuracy of the evaluation of the electronic endoscope operation can be improved. At the same time, the adjustment of the marker image can also adapt to the evaluation needs in more complex diagnosis and treatment environments.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a quality assessment method and device for an electronic endoscope detection process. Background Art

[0002] As a common medical device, electronic endoscopes play a vital role in various types of preoperative examinations. However, due to varying degrees of expertise among physicians, the integrity of examination results often varies, leading to issues such as non-standardized operation, incomplete observation, and inaccurate diagnostic assessments. To mitigate the impact of these differences in examination result integrity on diagnosis, a quality control solution for the endoscopic inspection process is needed.

[0003] The existing quality control system based on endoscopy scenes can only determine whether the captured images are accurate, but it is not closely integrated with the specific examination type and cannot adapt to the needs of complex clinical diagnosis and treatment environments. Summary of the Invention

[0004] Based on this, it is necessary to provide a quality assessment method and device that can improve the quality of the electronic endoscope detection process based on image similarity comparison results to address the above technical problems.

[0005] In a first aspect, the present application provides a quality assessment method for an electronic endoscope detection process.

[0006] The method comprises:

[0007] receiving a basic image sequence captured by an electronic endoscope, screening the basic image sequence to obtain a sample image sequence for highlighting the marker;

[0008] Analyzing the sample image sequence frame by frame, and selecting a target image sequence with a flag bit;

[0009] Comparing the target image sequence with a preset marker image sequence for similarity, and acquiring a marker image for reference from the preset marker image sequence based on the comparison result;

[0010] The accuracy of the basic image sequence is evaluated according to the generation order of the marker images.

[0011] In one embodiment, the receiving of a basic image sequence captured by an electronic endoscope and screening the basic image sequence to obtain a sample image sequence for highlighting the marker position includes:

[0012] receiving a basic image sequence captured by an electronic endoscope, and extracting a basic image from the basic image sequence;

[0013] Calculate the image variation of two adjacent frames of basic images in sequence;

[0014] The basic image is screened according to a numerical relationship between the image change amount and a preset threshold, and a sample image array is constructed based on the screened basic image.

[0015] In one embodiment, the sequentially calculating the image variation between two adjacent frames of basic images includes:

[0016] Calculate the variance of two adjacent frames of basic images respectively; or

[0017] Calculate the pixel values ​​of two adjacent frames of basic images respectively.

[0018] In one embodiment, screening the basic image according to the numerical relationship between the image change amount and a preset threshold, and constructing a sample image array based on the screened basic image, includes:

[0019] If the image change is greater than a preset threshold, deleting the previous frame in the time dimension of the two adjacent frames of basic image;

[0020] A sample image sequence is constructed based on the remaining base images.

[0021] In one embodiment, the comparing the target image sequence with a preset marker image sequence for similarity, and obtaining a marker image for reference from the preset marker image sequence based on the comparison result, includes:

[0022] Selecting each frame of target image from the target image sequence in turn to execute a preset similarity detection process to obtain a reference marker image corresponding to each frame of target image;

[0023] The similarity detection process is as follows:

[0024] Calculating the similarity between the current frame target image and each frame marker image in a preset marker image sequence to obtain multiple similarity results corresponding to the current frame target image;

[0025] From the multiple similarity results, a marker image corresponding to the maximum similarity is selected as a reference marker image of the current frame target image, and the reference marker image is deleted from the preset marker image sequence.

[0026] In one embodiment, updating the preset marker image sequence includes:

[0027] The first marker image is deleted from the preset marker image sequence.

[0028] In one embodiment, the evaluating the accuracy of the basic image sequence according to the generation order of the marker images includes:

[0029] Establishing a calculation function based on the generation order of the marker image;

[0030] An evaluation result corresponding to the basic image sequence is generated according to the calculation result of the calculation function.

[0031] In a second aspect, the present application also provides a quality assessment device for an electronic endoscope detection process. The device comprises:

[0032] An image processing module is used to receive a basic image sequence taken by an electronic endoscope, filter the basic image sequence, and obtain a sample image sequence for highlighting the marker;

[0033] An image screening module is used to analyze the sample image sequence frame by frame and select a target image sequence with a flag bit;

[0034] An image calculation module is used to compare the target image sequence with a preset marker image sequence for similarity, and obtain a marker image for reference from the preset marker image sequence based on the comparison result;

[0035] An image evaluation module is used to evaluate the accuracy of the basic image sequence according to the generation order of the marker images.

[0036] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0037] receiving a basic image sequence captured by an electronic endoscope, screening the basic image sequence to obtain a sample image sequence for highlighting the marker;

[0038] Analyzing the sample image sequence frame by frame, and selecting a target image sequence with a flag bit;

[0039] Comparing the target image sequence with a preset marker image sequence for similarity, and acquiring a marker image for reference from the preset marker image sequence based on the comparison result;

[0040] The accuracy of the basic image sequence is evaluated according to the generation order of the marker images.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0042] receiving a basic image sequence captured by an electronic endoscope, screening the basic image sequence to obtain a sample image sequence for highlighting the marker;

[0043] Analyzing the sample image sequence frame by frame, and selecting a target image sequence with a flag bit;

[0044] Comparing the target image sequence with a preset marker image sequence for similarity, and acquiring a marker image for reference from the preset marker image sequence based on the comparison result;

[0045] The accuracy of the basic image sequence is evaluated according to the generation order of the marker images.

[0046] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0047] receiving a basic image sequence captured by an electronic endoscope, screening the basic image sequence to obtain a sample image sequence for highlighting the marker;

[0048] Analyzing the sample image sequence frame by frame, and selecting a target image sequence with a flag bit;

[0049] Comparing the target image sequence with a preset marker image sequence for similarity, and acquiring a marker image for reference from the preset marker image sequence based on the comparison result;

[0050] The accuracy of the basic image sequence is evaluated according to the generation order of the marker images.

[0051] The above-mentioned quality assessment method, device, computer equipment, storage medium and computer program product for the electronic endoscope detection process can more accurately evaluate the standardization of electronic endoscope operations by selecting the marker image that best represents the current electronic endoscope operation status, and calculating the evaluation value of the corresponding basic image sequence operation based on the position label of the marker image in the preset marker image sequence. It can improve the accuracy of the evaluation of electronic endoscope operations. At the same time, the adjustment of the marker image can also adapt to the evaluation needs in more complex diagnosis and treatment environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1is a diagram of an application environment of a quality assessment method for an electronic endoscope inspection process in one embodiment;

[0053] Figure 2 1 is a flow chart of a quality assessment method for an electronic endoscope inspection process in one embodiment;

[0054] Figure 3 A schematic diagram of a set of twin networks used for similarity calculation in one embodiment;

[0055] Figure 4 is a structural block diagram of a quality assessment device for an electronic endoscope inspection process in one embodiment;

[0056] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0058] The quality assessment method for electronic endoscope detection process provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be integrated with server 104 or placed on a cloud or other network server. A specific quality assessment method for the electronic endoscope inspection process is implemented in the terminal or server. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablet computers, etc. Server 104 can be implemented as a standalone server or a server cluster consisting of multiple servers.

[0059] In one embodiment, Figure 2 As shown, a quality assessment method for electronic endoscope detection process is provided, and the method is applied to Figure 1 The terminal 102 in the example is used as an example to illustrate, including the following steps:

[0060] Step S20 : ​​receiving a basic image sequence taken by an electronic endoscope, screening the basic image sequence, and obtaining a sample image sequence for highlighting the marker.

[0061] The base image sequence is a collection of numerous basic images captured directly by electronic endoscopes during clinical use. However, to accommodate landmark-based evaluation in subsequent steps, a series of screening procedures are performed on the base image sequence to obtain a sample image sequence that highlights landmarks for subsequent processing.

[0062] Step S40 , analyzing the sample image sequence frame by frame, and selecting a target image sequence with a flag.

[0063] The obtained sample image sequence is sent to the server for frame-by-frame analysis, so as to select the target image with the flag bit and form the target image sequence.

[0064] Typically, deep learning network models are used to determine whether pre-set landmarks are present in an image. Deep learning models are acquired by manually labeling image data with landmarks from a large number of actual surgical videos. The data is then divided into training and test data. The training data is used to train the model, and the model that achieves the required specificity and sensitivity on the test data is used for landmark detection.

[0065] It is worth noting that the landmarks here refer to the image information of certain locations that will inevitably appear during routine electronic endoscopy examinations, such as the lower stomach, gastric body, pyriform sinus, and epiglottic wall. The clarity and completeness of the image information at these locations can be used as a reference for judging the quality of electronic endoscopy examinations, which can more accurately determine whether there are any missed inspections or other violations of the inspection standards during the examination process.

[0066] Step S60 : performing a similarity comparison between the target image sequence and the preset marker image sequence, and obtaining a marker image for reference from the preset marker image sequence based on the comparison result.

[0067] Among them, the preset marker image sequence represents the image features that must be obtained in the regular electronic endoscope detection process, and therefore can be used as a detection standard to determine whether the electronic endoscope detection process is compliant or not. Here, the target image sequence is compared with the preset marker image sequence for similarity, and the marker image that best represents the current electronic endoscope operation status is selected to facilitate the evaluation of the current electronic endoscope operation in subsequent steps.

[0068] Step S80: Evaluate the accuracy of the basic image sequence according to the generation order of the marker images.

[0069] Among them, the evaluation here is based on the marker image extracted in the previous step, and the evaluation value of the corresponding basic image sequence operation is calculated based on the position label of the marker image in the preset marker image sequence, which can more accurately evaluate the standardization of the electronic endoscope operation.

[0070] The above-mentioned quality assessment method for the electronic endoscope inspection process obtains at least one basic image in the inspection task, determines whether the image has a flag, then retrieves and compares the identified flag information with the flag information in the base database, and updates the base database based on the comparison results. Finally, the inspection task is evaluated based on the base database and the recognition comparison results. By selecting the flag image that best represents the current electronic endoscope operation status, and calculating the evaluation value of the corresponding basic image sequence operation based on the position label of the flag image in the preset flag image sequence, the standardization of the electronic endoscope operation can be more accurately evaluated, and the accuracy of the evaluation of the electronic endoscope operation can be improved. At the same time, the adjustment of the flag image can also adapt to the evaluation needs in more complex diagnosis and treatment environments.

[0071] In one embodiment, a basic image sequence captured by an electronic endoscope is received, and the basic image sequence is screened to obtain a sample image sequence for highlighting the marker, that is, step S20 includes:

[0072] Step S22, receiving a basic image sequence taken by the electronic endoscope, and extracting a basic image from the basic image sequence;

[0073] Step S24, sequentially calculating the image variation between two adjacent frames of basic images;

[0074] Step S26 , screening the basic image according to the numerical relationship between the image variation and the preset threshold, and constructing a sample image array for highlighting the marker based on the screened basic image.

[0075] In practice, in order to obtain a target image sequence used for image comparison in subsequent steps, the basic image sequence captured by the electronic endoscope needs to be processed.

[0076] A basic image sequence is a collection of basic images captured at preset intervals during clinical use by an electronic endoscope. To facilitate processing, the basic image sequence is decomposed into individual basic images. The change between two adjacent basic images is then determined to determine whether the difference is significant enough to remove one. After this removal, a sample image array consisting of the selected basic images is obtained.

[0077] The step S24 of sequentially calculating the image variation of two adjacent frames of basic images includes:

[0078] The variance of two adjacent frames of basic images is calculated respectively, or the pixel values ​​of two adjacent frames of basic images are calculated respectively.

[0079] In practice, there are two ways to calculate the change between two adjacent base images: calculating variance or pixel values. The former method calculates the variance of each base image frame, allowing for subsequent frame deletion when the difference in the variance between the two base images exceeds a preset threshold. The latter method calculates the pixel values ​​of each base image frame, triggering frame deletion in subsequent steps when the difference in the pixel values ​​between the two base images exceeds a preset threshold.

[0080] In one embodiment, the basic images are screened according to the numerical relationship between the image variation and a preset threshold, and a sample image array is constructed based on the screened basic images. Step S26 includes:

[0081] Step S262: if the image change is greater than a preset threshold, the previous frame in the time dimension of two adjacent frames of basic images is deleted;

[0082] Step S264: constructing a sample image sequence for highlighting the marker based on the remaining basic images.

[0083] During implementation, if the image change between two adjacent frames of basic images is greater than a preset threshold, it indicates that the difference between the two adjacent frames of basic images is too large, and there may be a large offset in the corresponding area of ​​the basic image. At this time, the earlier frame in the time dimension, that is, the previous frame, is deleted first.

[0084] The above processing is performed on all basic images, and a sample image sequence is constructed based on the remaining basic images.

[0085] In one embodiment, a target image sequence is compared with a preset marker image sequence for similarity, and a marker image for reference is obtained from the preset marker image sequence based on the comparison result, that is, step S60 includes:

[0086] Each frame of target image is selected from the target image sequence in turn to execute a preset similarity detection process to obtain a reference marker image corresponding to each frame of target image.

[0087] The similarity detection process is:

[0088] Step S62, calculating the similarity between the current frame target image and each frame marker image in the preset marker image sequence, and obtaining a plurality of similarity results corresponding to the current frame target image;

[0089] Step S64 : selecting the marker image corresponding to the maximum similarity from the multiple similarity results as the reference marker image of the current frame target image, and deleting the reference marker image from the preset marker image sequence.

[0090] In implementation, the sample image sequence obtained in the foregoing step S20 is processed through step S40 to obtain a target image sequence with flag bits. In this step, a similarity comparison is performed between the target image sequence and a preset flag bit image sequence, and the flag bit image with the highest similarity to each frame of the target image in the former is selected from the latter. The sequence number representing the relative position of the selected flag bit image in the preset flag bit image sequence is used as a reference value for whether the electronic endoscope conforms to the detection process. Furthermore, in subsequent steps, a compliance assessment of the detection operation of the electronic endoscope is performed based on the reference value here.

[0091] Before the specific comparison operation, it is necessary to explain the preset flag bit image sequence. The preset flag bit images are a certain number of flag bit images provided by a doctor based on prior knowledge and existing data. The set of all preset flag bit images is used as a bottom library, and the flag bit images in the bottom library are sorted according to the order in which the flag bits should appear during the inspection process.

[0092] After constructing the preset flag bit image sequence, the comparison process can be carried out. Specifically:

[0093] Select the first target image from the target image sequence, and calculate the similarity between the first target image and each frame of the flag bit image in the preset flag bit image sequence; select the flag bit image corresponding to the maximum similarity as the first flag bit image for the reference use of the corresponding first target image.

[0094] Exemplarily, denote the bottom library set as Ψ, and 0 < i ≤ N, where ψ i is the flag bit image sequence, N is the total number of flag bits to be inspected, and the value range is a positive integer, and 0 < j ≤ M, where α ij is the j-th bottom library image of flag bit i, M is the number of comparison images required for a single flag bit in the bottom library, and the value ranges of i and j are positive integers.

[0095] The main idea of the comparison is: calculate the similarity between images, and if the similarity reaches the threshold, it is considered that the comparison is successful.

[0096] For the first target image I rect , its matching similarity result is as shown in Formula One:

[0097]

[0098] Obtain the values of i and j when I sim is taken, and denote them as i sim and j sim .

[0099] S in Formula 1 is a similarity calculation between the first target image and a frame of marker image in a preset marker image sequence.

[0100] It should be noted that the similarity calculation can typically be implemented through a set of twin networks, such as Figure 3 As shown, the two network models Network_A and Network_B each accept a graph as network input, the two networks share weight W, and each outputs a set of multi-dimensional feature vectors with the same dimension, and then calculates the Euclidean distance between the two output vectors.<G(x1),G(x2)> ) is used to determine the similarity S between the two input images.

[0101] After performing the above similarity calculation on the first target image to filter out the corresponding marker image, the operation is repeated for each remaining target image frame in the target image sequence to determine all the marker images in the target image sequence for reference purposes.

[0102] It should be noted that each time the similarity calculation is performed to screen out the corresponding marker image, the update operation shown in step S66 must be performed.

[0103] Specifically, step S66 includes:

[0104] Step S662: Delete the first marker image from the preset marker image sequence.

[0105] In implementation, according to the previous content, the serial number reflecting the relative position of the marker image selected based on the similarity calculation in the original preset marker image sequence is the key to subsequent evaluation. Therefore, in order to prevent serial number confusion, after each similarity calculation is performed to select the corresponding marker image, the obtained marker image needs to be removed from the preset marker image sequence (i.e., the base library).

[0106] In one embodiment, the accuracy of the basic image sequence is evaluated according to the generation order of the marker images, that is, step S80 includes:

[0107] Step S82, establishing a calculation function based on the sequence of generating the flag image;

[0108] Step S84: generating an evaluation result corresponding to the basic image sequence according to the calculation result of the calculation function.

[0109] In the implementation, in the base library Ψ={ψ1,ψ2,...,ψ N}, where N is the serial number of the flag bit, and the flag bit images in the base library are arranged in ascending order of the serial number. Since the flag bits that have been checked can be removed from the base library during the inspection process, the order of the remaining flag bit images remains unchanged.

[0110] The check score calculation process is as follows, and the matching similarity result I is obtained. sim and the corresponding flag bit number i sim and image number j sim If it matches the similarity result I sim If it is greater than the set threshold, it is considered as sequence number i sim The flag bit check is completed.

[0111] However, since each flag has a linear inspection order, the final score is also related to the order in which the inspection is completed. Assume that the first flag image in the base library is numbered i, and the inspection process score is initialized to 0 at the beginning of the inspection, then the inspection completion number is i. sim After the flag is set, the score is updated as shown in Formula 2:

[0112] score+=N-abs(i sim -i) Formula 2;

[0113] In the formula, score+ is the score accumulation operator, N is the flag bit number, and abs() is the absolute value operator. Formula 2 states that when the first flag bit image is exactly the flag bit image corresponding to the first target image, the value obtained by abs() is zero, meaning that the operation score corresponding to the first target image can reach the maximum value N. Similarly, the greater the difference in the serial numbers between the target image and the corresponding flag bit image, the larger the value obtained by abs() and the smaller the score value corresponding to the target image, indicating that the operation of the electronic endoscope corresponding to the target image deviates further from the specified operation and the worse the evaluation value.

[0114] After all inspections are completed, the database is traversed to determine whether there are any unchecked flags. For each flag that exists, the score is deducted accordingly based on the pre-set importance of the flag, and the system reports any missed parts. The final score serves as the basis for evaluating the quality of the inspection.

[0115] The above-mentioned quality assessment method for the electronic endoscope inspection process obtains at least one basic image in the inspection task, determines whether the image has a flag, then retrieves and compares the identified flag information with the flag information in the base database, and updates the base database based on the comparison results. Finally, the inspection task is evaluated based on the base database and the recognition comparison results. By selecting the flag image that best represents the current electronic endoscope operation status, and calculating the evaluation value of the corresponding basic image sequence operation based on the position label of the flag image in the preset flag image sequence, the standardization of the electronic endoscope operation can be more accurately evaluated, and the accuracy of the evaluation of the electronic endoscope operation can be improved. At the same time, the adjustment of the flag image can also adapt to the evaluation needs in more complex diagnosis and treatment environments.

[0116] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed 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 portion of steps or stages in other steps.

[0117] Based on the same inventive concept, embodiments of the present application also provide a quality assessment device for an electronic endoscope inspection process, which is used to implement the aforementioned quality assessment method for an electronic endoscope inspection process. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the quality assessment device for an electronic endoscope inspection process provided below can be found in the limitations of the quality assessment method for an electronic endoscope inspection process described above, and will not be repeated here.

[0118] In one embodiment, Figure 4 As shown, a quality assessment device 40 for an electronic endoscope detection process is provided, comprising: an image processing module 42, an image screening module 44, an image calculation module 46 and an image assessment module 48, wherein:

[0119] An image processing module 42 is configured to receive a basic image sequence captured by an electronic endoscope, filter the basic image sequence, and obtain a sample image sequence for highlighting the marker;

[0120] The base image sequence is a collection of numerous basic images captured directly by electronic endoscopes during clinical use. However, to accommodate landmark-based evaluation in subsequent steps, a series of screening procedures are performed on the base image sequence to obtain a sample image sequence that highlights landmarks for subsequent processing.

[0121] An image screening module 44 is configured to analyze the sample image sequence frame by frame and select a target image sequence with a flag bit;

[0122] The obtained sample image sequence is sent to the server for frame-by-frame analysis, so as to select the target image with the flag bit and form the target image sequence.

[0123] Typically, deep learning network models are used to determine whether pre-set landmarks are present in an image. Deep learning models are acquired by manually labeling image data with landmarks from a large number of actual surgical videos. The data is then divided into training and test data. The training data is used to train the model, and the model that achieves the required specificity and sensitivity on the test data is used for landmark detection.

[0124] It is worth noting that the landmarks here refer to the image information of certain locations that will inevitably appear during routine electronic endoscopy examinations, such as the lower stomach, gastric body, pyriform sinus, and epiglottic wall. The clarity and completeness of the image information at these locations can be used as a reference for judging the quality of electronic endoscopy examinations, which can more accurately determine whether there are any missed inspections or other violations of the inspection standards during the examination process.

[0125] An image calculation module 46 is configured to compare the target image sequence with a preset marker image sequence for similarity, and obtain a marker image for reference from the preset marker image sequence based on the comparison result;

[0126] Among them, the preset marker image sequence represents the image features that must be obtained in the regular electronic endoscope detection process, and therefore can be used as a detection standard to determine whether the electronic endoscope detection process is compliant or not. Here, the target image sequence is compared with the preset marker image sequence for similarity, and the marker image that best represents the current electronic endoscope operation status is selected to facilitate the evaluation of the current electronic endoscope operation in subsequent steps.

[0127] The image evaluation module 48 is configured to evaluate the accuracy of the basic image sequence according to the generation order of the marker images.

[0128] Among them, the evaluation here is based on the marker image extracted in the previous step, and the evaluation value of the corresponding basic image sequence operation is calculated based on the position label of the marker image in the preset marker image sequence, which can more accurately evaluate the standardization of the electronic endoscope operation.

[0129] The above-mentioned quality assessment device for the electronic endoscope inspection process, after obtaining at least one basic image in the inspection task, determines whether the image has a marker, then searches and compares the identified marker information with the marker information in the base database, and updates the base database based on the comparison results. Finally, the inspection task is evaluated based on the base database and the recognition comparison results. By selecting the marker image that best represents the current electronic endoscope operation status, and calculating the evaluation value of the corresponding basic image sequence operation based on the position label of the marker image in the preset marker image sequence, the standardization of the electronic endoscope operation can be more accurately evaluated, and the accuracy of the electronic endoscope operation evaluation can be improved. At the same time, the adjustment of the marker image can also adapt to the evaluation needs in more complex diagnosis and treatment environments.

[0130] Each module in the above-mentioned quality assessment device for electronic endoscope inspection process can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0131] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. 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, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store XX data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a quality assessment method for an electronic endoscope detection process is implemented.

[0132] Those skilled in the art will understand that Figure 5 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0133] 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:

[0134] Step S20, receiving a basic image sequence taken by an electronic endoscope, screening the basic image sequence, and obtaining a sample image sequence for highlighting the marker;

[0135] Step S40: Analyze the sample image sequence frame by frame and select a target image sequence with a marker. Step S60: Compare the target image sequence with a preset marker image sequence for similarity and obtain a marker image for reference from the preset marker image sequence based on the comparison result.

[0136] Step S80: Evaluate the accuracy of the basic image sequence according to the generation order of the marker images.

[0137] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0138] Step S20, receiving a basic image sequence taken by an electronic endoscope, screening the basic image sequence, and obtaining a sample image sequence for highlighting the marker;

[0139] Step S40: Analyze the sample image sequence frame by frame and select a target image sequence with a marker. Step S60: Compare the target image sequence with a preset marker image sequence for similarity and obtain a marker image for reference from the preset marker image sequence based on the comparison result.

[0140] Step S80: Evaluate the accuracy of the basic image sequence according to the generation order of the marker images.

[0141] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0142] Step S20, receiving a basic image sequence taken by an electronic endoscope, screening the basic image sequence, and obtaining a sample image sequence for highlighting the marker;

[0143] Step S40: Analyze the sample image sequence frame by frame and select a target image sequence with a marker. Step S60: Compare the target image sequence with a preset marker image sequence for similarity and obtain a marker image for reference from the preset marker image sequence based on the comparison result.

[0144] Step S80: Evaluate the accuracy of the basic image sequence according to the generation order of the marker images.

[0145] 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.

[0146] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of 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 the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0147] The technical features of the above embodiments can 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.

[0148] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A quality assessment method for an electronic endoscope inspection process, characterized in that: The quality assessment method comprises: receiving a basic image sequence captured by an electronic endoscope, screening the basic image sequence to obtain a sample image sequence for highlighting the marker; Analyzing the sample image sequence frame by frame, and selecting a target image sequence with a flag bit; Comparing the target image sequence with a preset marker image sequence for similarity, and acquiring a marker image for reference from the preset marker image sequence based on the comparison result; The accuracy of the basic image sequence is evaluated according to the generation order of the marker images; the generation order of the marker images is the position number of the marker images in the preset marker image sequence.

2. The quality assessment method for electronic endoscope detection process according to claim 1, characterized in that: The receiving of a basic image sequence captured by an electronic endoscope and screening of the basic image sequence to obtain a sample image sequence for highlighting the marker position include: receiving a basic image sequence captured by an electronic endoscope, and extracting a basic image from the basic image sequence; Calculate the image variation of two adjacent frames of basic images in sequence; The basic image is screened according to the numerical relationship between the image change amount and a preset threshold, and a sample image array for highlighting the flag position is constructed based on the screened basic image.

3. The quality assessment method for electronic endoscope detection process according to claim 2, characterized in that: The sequentially calculating the image variation of two adjacent frames of basic images includes: Calculate the variance of two adjacent frames of basic images respectively; or Calculate the pixel values ​​of two adjacent frames of basic images respectively.

4. The quality assessment method for electronic endoscope detection process according to claim 2, characterized in that: The step of screening the basic image according to the numerical relationship between the image change amount and a preset threshold, and constructing a sample image array for highlighting the flag position based on the screened basic image, includes: If the image change is greater than a preset threshold, deleting the previous frame in the time dimension of the two adjacent frames of basic image; A sample image sequence for highlighting the marker is constructed based on the remaining basic images.

5. The quality assessment method for electronic endoscope detection process according to claim 1, characterized in that: The step of comparing the target image sequence with a preset marker image sequence for similarity, and obtaining a marker image for reference from the preset marker image sequence based on the comparison result, includes: Selecting each frame of target image from the target image sequence in turn to execute a preset similarity detection process to obtain a reference marker image corresponding to each frame of target image; The similarity detection process is as follows: Calculating the similarity between the current frame target image and each frame marker image in a preset marker image sequence to obtain multiple similarity results corresponding to the current frame target image; From the multiple similarity results, a marker image corresponding to the maximum similarity is selected as a reference marker image of the current frame target image, and the reference marker image is deleted from the preset marker image sequence.

6. The quality assessment method for electronic endoscope detection process according to claim 5, characterized in that: Selecting each frame of target image from the target image sequence in sequence and executing a preset similarity detection process to obtain a reference marker image corresponding to each frame of target image, including: Selecting a first target image from the target image sequence, and calculating the similarity between the first target image and each frame of the marker image in the preset marker image sequence through a set of twin networks; Selecting the marker image corresponding to the maximum similarity as the first marker image for reference corresponding to the first target image, and updating the preset marker image sequence; Repeat the operation for each remaining frame of target image in the target image sequence; The updating of the preset marker image sequence includes: The first marker image is deleted from the preset marker image sequence.

7. The quality assessment method for electronic endoscope detection process according to claim 1, characterized in that: The step of evaluating the accuracy of the basic image sequence according to the generation order of the marker images includes: Establishing a calculation function based on the generation order of the marker image; An evaluation result corresponding to the basic image sequence is generated according to the calculation result of the calculation function.

8. A quality assessment device for an electronic endoscope inspection process, characterized in that: The quality assessment device comprises: An image processing module is used to receive a basic image sequence taken by an electronic endoscope, filter the basic image sequence, and obtain a sample image sequence for highlighting the marker; An image screening module is used to analyze the sample image sequence frame by frame and select a target image sequence with a flag bit; An image calculation module is used to compare the target image sequence with a preset marker image sequence for similarity, and obtain a marker image for reference from the preset marker image sequence based on the comparison result; An image evaluation module is used to evaluate the accuracy of the basic image sequence according to the generation order of the marker images; the generation order of the marker images is the position number of the marker images in the preset marker image sequence.

9. 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 7 are implemented.

10. 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 7 are implemented.

Images