Operation method and system of endoscope, terminal and storage medium

By using the multi-scale Retinex algorithm of mean templates and Laplace template processing technology in the endoscope, the problem of low efficiency of traditional optical endoscope image operating system is solved, the image quality and diagnosis and treatment efficiency are improved, and the calculation volume is reduced .

CN119007970APending Publication Date: 2024-11-22HAINAN MEDICAL INNOVATION TECHNOLOGY CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411058943.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The image operating system of traditional optical endoscopes is not suitable for electronic endoscopes, and the traditional multi-scale Retinex algorithm is used to perform convolution operations on larger-scale templates, which affects the efficiency of the algorithm.

Method used

The multi-scale Retinex algorithm of the mean template is used to filter the lesion site images obtained by the endoscopy to obtain the brightness component and reflection component, and the image edge details are processed through the Laplace template, and image enhancement is performed after filtering and superposition. Generate a report.

Benefits of technology

It significantly improves image quality, shortens diagnosis and treatment time, improves diagnosis and treatment efficiency, reduces calculation volume, and improves the efficiency of the algorithm.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007970A_ABST
    Figure CN119007970A_ABST
Patent Text Reader

Abstract

The invention relates to an operation method and system of an endoscope, a terminal and a storage medium. The method comprises the following steps: acquiring patient information and inputting the patient information into the system; acquiring an image of the lesion part of the patient in the endoscope system; after an endoscope system obtains an image of a focus part of a patient, an enhanced image is obtained by adopting a multi-scale Retinex algorithm of a mean template. Wherein the obtained image is filtered through a multi-scale Retinex algorithm of a mean template to obtain a brightness component and a reflection component, the brightness component is filtered to obtain balanced brightness, and the reflection component is compensated to obtain a preliminary enhanced image. The original image is processed through a Laplace template to obtain image edge detail information, the image edge detail information and the preliminarily enhanced image are superposed, and the image is stretched and corrected to a display range to obtain a final enhanced image, so that the image quality is greatly improved; finally, examination information of the patient is determined through the examination image of the focus part, an examination report is generated, diagnosis and treatment time is shortened, and diagnosis and treatment efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of endoscope operation methods and operating systems, and in particular to an endoscope operation method, system, terminal and storage medium. Background Art

[0002] Medical endoscopes are medical devices that are inserted into the hollow organs or cavities of the human body and can inspect the hollow organs and cavities of the human body without direct surgery. With the development of technology, electronic endoscopes are more and more widely used in medical endoscopes. However, due to different technical routes, the image operating system of traditional optical endoscopes is not suitable for electronic endoscopes. At the same time, the traditional multi-scale Retinex algorithm has a large amount of calculation when performing convolution operations on templates with larger scales, which affects the efficiency of the algorithm.

[0003] Chinese patent publication number CN115034985A discloses an underwater image enhancement method, including inverting the original image taken underwater to obtain a dark channel image; calculating the global background light and underwater ambient light based on the dark channel image; calculating the transmittance of the water medium to light; calculating the preliminary defogging underwater image based on the global background light and the transmittance of the water medium to light; using a multi-scale Retinex algorithm to perform image enhancement processing on the preliminary defogging underwater image; using a color restoration function to compensate for image distortion; using a histogram to intercept and balance the proportion of multi-scale Retinex processing values ​​of different color channels in the final processed image to obtain a secondary processed underwater image; using a bilateral filter of Gaussian filtering and guided filtering to perform noise processing on the secondary processed underwater image to obtain a final image. The present invention improves the clarity of the original image taken underwater with fog and color cast and low quality, and reduces the degree of color deviation and noise. The patent uses a multi-scale Retinex algorithm with a Gaussian template, which has a large amount of calculation and affects the efficiency of the algorithm. Summary of the invention

[0004] The technical problem to be solved by the present invention is that the image operating system of the traditional optical endoscope is not suitable for the electronic endoscope. At the same time, the traditional multi-scale Retinex algorithm has a large amount of calculation when performing convolution operations on templates with larger scales, which affects the efficiency of the algorithm. In view of the above-mentioned defects of the prior art, an operation method, system, terminal and storage medium of an endoscope are provided.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for operating an endoscope is constructed, comprising:

[0007] Obtain patient information and enter it into the system;

[0008] The endoscope system obtains images of the patient's lesion site;

[0009] Generate and output a report of the patient based on the image of the patient's lesion site;

[0010] After acquiring the image of the patient's lesion site, the endoscope system uses a multi-scale Retinex algorithm of a mean template to obtain an enhanced image, and generates and outputs a report on the patient based on the enhanced image.

[0011] Preferably, after the endoscope system acquires the image of the patient's lesion site, the enhanced image is obtained by using a multi-scale Retinex algorithm of a mean template, including:

[0012] The acquired image of the lesion site is filtered to obtain a brightness component L(x,y) and a reflection component R(x,y), and the brightness component L(x,y) is filtered to obtain a balanced brightness component, and the reflection component R(x,y) is compensated to obtain a preliminary enhanced image.

[0013] Preferably, the acquired image of the lesion site is filtered:

[0014] L(x,y)=I(x,y)×F1(x,y)

[0015] Where F1(x,y) is the surround function of the first filtering, and L(x,y) is the brightness information in the original image;

[0016] Filter the height component L(x,y)

[0017] L1(x,y)=I(x,y)×F2(x,y)

[0018] Where F2(x,y) is the surround function of the secondary filter.

[0019] Preferably, the original image is processed using a Laplace template to obtain image edge detail information, and the preliminary enhanced image is superimposed on the edge image to obtain a final enhanced image, and a report on the patient is generated and output based on the final enhanced image.

[0020] Construct an endoscope operating system, including:

[0021] Information management module, used to input and manage patient information;

[0022] An endoscope control module, used to obtain images of the patient's lesion site;

[0023] An image processing module is used to enhance the image of the lesion site obtained by the endoscope to improve the image quality;

[0024] The report output module generates a patient report based on the enhanced image, and the image processing module uses a multi-scale Retinex algorithm with a mean template to obtain an enhanced image.

[0025] Preferably, the image processing module filters the acquired image of the lesion site to obtain a brightness component L(x, y) and a reflection component R(x, y), filters the brightness component L(x, y) to obtain a balanced brightness component, and compensates the reflection component R(x, y) to obtain a preliminary enhanced image.

[0026] Preferably, the acquired image of the lesion site is filtered:

[0027] L(x,y)=I(x,y)×F1(x,y)

[0028] Where F1(x,y) is the surround function of the first filtering, and L(x,y) is the brightness information in the original image;

[0029] Filter the height component L(x,y)

[0030] L1(x,y)=I(x,y)×F2(x,y)

[0031] Where F2(x,y) is the surround function of the secondary filter.

[0032] Preferably, the original image is processed using a Laplace template to obtain image edge detail information, and the preliminary enhanced image is superimposed on the edge image to obtain a final enhanced image, and a report on the patient is generated and output based on the final enhanced image.

[0033] A smart terminal is constructed, which includes at least one memory, at least one processor, and an endoscope operation program stored in the memory and executable on the processor, wherein the endoscope operation program, when executed by the processor, implements the steps of the endoscope operation method as described in any one of claims 1 to 4.

[0034] A computer-readable storage medium is constructed, wherein an endoscope operation program is stored on the computer-readable storage medium, and when the endoscope operation detection program is executed by a processor, the steps of the endoscope operation method according to any one of claims 1 to 4 are implemented.

[0035] The beneficial effects of the present invention are as follows: first, the patient information is input according to the established patient information template, and the endoscope is operated to obtain an image of the patient's lesion site, and the obtained image is filtered through the multi-scale Retinex algorithm of the mean template to obtain the brightness component and the reflection component, and the brightness component is filtered to obtain a balanced brightness, and the reflection component is compensated to obtain a preliminary enhanced image. Then, the original image is processed through the Laplace template to obtain the image edge detail information, the image edge detail information is superimposed with the preliminary enhanced image, and the final enhanced image is obtained by stretching and correcting to the display range, thereby greatly improving the image quality. Finally, the patient's examination information is determined through the inspection image of the lesion site and an inspection report is generated, which shortens the diagnosis and treatment time and improves the diagnosis and treatment efficiency. In order to realize the operation of the sub-endoscope and the processing of the corresponding image, and to achieve diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be further described below in conjunction with the accompanying drawings and embodiments. The drawings described below are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work:

[0037] Figure 1 A schematic diagram of a flow chart of an endoscope operation method according to a preferred embodiment of the present invention;

[0038] Figure 2 A schematic structural diagram of an endoscope according to a preferred embodiment of the present invention;

[0039] Figure 3 A schematic diagram of a flow chart of a graphics enhancement method according to a preferred embodiment of the present invention;

[0040] Figure 4 A schematic diagram of an endoscope operating system according to a preferred embodiment of the present invention;

[0041] Figure 5 The figure is a block diagram of the internal structure principle of the intelligent terminal according to the preferred embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the following will be described clearly and completely in combination with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are partial embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0043] A method for operating an endoscope according to a preferred embodiment of the present invention; Figure 1As shown, it is a flowchart of an endoscope operation method provided by an embodiment of the present invention. The method can be executed by a device, and the device can be implemented by software and / or hardware.

[0044] Specifically, in this embodiment, the endoscope operation method includes:

[0045] S10: Obtain patient information and enter it;

[0046] In a preferred embodiment of the present invention, information including the patient's name, age, gender, medical history, etc. is entered into the system, and the entered information items can be added and deleted as needed, thereby realizing customized management of the patient information to meet the needs of different medical institutions. After the patient information is entered, it is automatically saved locally to facilitate subsequent reading of the patient's information to avoid repeated entry of information, and after reading the patient information, the incorrectly filled information can also be modified.

[0047] Furthermore, after obtaining the patient information, the patient information can be managed and the information collection can be configured. In order to meet the needs of different groups of people, especially to meet export needs, the patient information collection configuration system can realize the independent setting of patient information fields, such as age, gender, place of origin, nationality, examination number, previous examination number and other fields, and the set field attributes can also be configured and preset, so as to obtain a customized patient information management system.

[0048] S20: The endoscope system obtains an image of the patient's lesion site;

[0049] In a preferred embodiment of the present invention, Figure 2 As shown, the endoscope 301 includes an endoscope handle 3013, which is connected to the hard mirror insertion part 3010 through a detachable connection part 3011, and the other end of the endoscope handle is connected to the connecting line 3014 for signal transmission, and an adjustment button 3012 is set on the endoscope handle to adjust the endoscope. The endoscope control system is connected to the endoscope handle through a connecting line, and can allocate and set the attributes of the endoscope-collected image, such as image resolution setting, sharpness setting, brightness setting, hue setting, saturation setting, and video frame rate setting to adjust the captured image parameters, so that doctors can flexibly configure image parameters according to the usage scenario to achieve better observation effects. At the same time, the endoscope system also supports dual endoscope control and display, which is convenient for comparative analysis.

[0050] S30: performing enhancement processing on the acquired image;

[0051] In a preferred embodiment of the present invention, the image quality of the image acquired by the endoscope terminal is further improved through encoding and decoding and machine learning algorithms, the image noise reduction algorithm is used to reduce the noise in the image, and the dark area enhancement algorithm is used to make the image look clearer and more realistic. The image can also be enlarged or reduced according to the required method or the magnification of the required display screen, and the magnification has a variety of different options such as 0.25, 0.5, 0.75, 1, 1.25, 1.5, 1.75, 2, 2.25, 2.5, etc., and video and photography can be performed during the image acquisition process. At the same time, in the image enhancement process, the mean template is replaced by the Gaussian template to reduce the amount of calculation, and then the compensation target image with part of the brightness component retained is filtered to achieve a good visual effect of the image brightness compensation, and then the image is enhanced in edge detail to highlight the edge detail information, and the enhanced image is superimposed with the edge image to obtain the final enhanced image.

[0052] S40: Forming and outputting an examination report of the patient based on the enhanced image;

[0053] In the preferred embodiment of the present invention, the format, layout and report content of the examination report can be set according to the needs of the patient, or selected according to the actual situation of different departments or different medical institutions to generate report template management, thereby optimizing the configuration of the report template, making the configuration more flexible and convenient. The patient report management also supports the management operation of the patient's examination report, supports multiple inquiries according to the examination time, name, examination doctor, etc., and supports the import and export of cases, which is convenient for the management and backup of patient data. At the same time, the patient report system can also determine the patient's examination information based on the endoscopic examination image of the lesion site, thereby forming an examination report, and generate the report according to the report template setting. At the same time, the report contains examination pictures, symptoms, descriptions, diagnoses, suggestions and other modules. Except for the picture information, all other parts are based on a large number of terms obtained in the clinic and built into the system, which is convenient for doctors to input quickly, shorten the diagnosis and treatment time, and improve efficiency.

[0054] Specifically, in the above embodiment, Figure 3 As shown, the above step S30: performing image enhancement processing on the acquired image includes:

[0055] S300: Selecting an appropriate mean template according to the lesion site image for filtering to obtain a height component and a reflection component;

[0056] In a preferred embodiment of the present invention, the image processing system has a built-in real-time image enhancement algorithm, and makes related improvements based on the multi-scale Retinex algorithm. The specific implementation method is as follows:

[0057] According to the original Retinex theory, the image is regarded as the object brightness component L(x, y) and the reflection component R(x, y), then the true image function I(x, y) is expressed as:

[0058] I(x,y)=L(x,y)×R(x,y) ①

[0059] The multi-scale Retinex algorithm processes the image through surround functions of different scales, which can be regarded as the linear weighted summation of single-scale Retinex of different scales. The formula is:

[0060]

[0061] Where K represents the number of wrap-around functions, W i Represents the weighted coefficient of the surround function at different scales. In actual environments, the standard deviation of the surround function is generally selected from three scales: large, medium and small, and the weight W i You can choose according to the different emphasis of actual needs. Under normal circumstances, it is more appropriate to choose the same 1 / 3 for each weight. The multi-scale Retinex algorithm takes into account the overall effect and local prominence of the image to a certain extent, and ensures dynamic range compression and color consistency.

[0062] In the present invention, the mean template is used to replace the Gaussian template in the multi-scale Retinex algorithm. It can be seen from formula ② that the multi-scale Retinex algorithm needs to calculate the convolution of the Gaussian template of each scale with the original image, and the amount of calculation for the convolution operation of the template with a larger scale is very large, which greatly affects the efficiency of the algorithm.

[0063] When the scale of the Gaussian template is large, the weights in the Gaussian template weighting matrix are very small and the values ​​are very close. For a Gaussian template with a scale of 129×129, the weight range is 0.516×10 -4 ~0.6219×10 -4 , it can be seen from the numerical value that the difference between the maximum value of the weight and the minimum value of the weight is only 0.605×10 -5 Therefore, if the weights with little change in the Gaussian template are replaced with fixed values, the convolution operation will be simplified. The sum of the weights in the Gaussian template is approximately 1. The present invention adopts the idea of ​​the mean template to evenly distribute the weights to each value. For the above 129×129 template, the calculation amount is 1 / 1292 of the Gaussian template, and the result is approximately 0.609×10 -4 , select this value to replace the value in the Gaussian template, and convert the Gaussian template weight into a fixed value for calculation.

[0064] S301: filtering the height component to obtain a balanced brightness component, and compensating the reflection component to obtain a preliminary enhanced image;

[0065] Since the traditional Retinex algorithm completely removes the filtered brightness component from the original image, the equivalent formula of formula ① can be used to obtain the result of removing the brightness component, that is, formula ③ without considering the brightness component, which is specifically:

[0066] R(x,y)=logL(x,y)R(x,y)L(x,y)R(x,y)≈logR(x,y)R(x,y) ③

[0067] (x, y) is the weighted average of the surroundings, that is, Retinex is actually the ratio of the current point brightness to the weighted average brightness of the surroundings, which is consistent with the neurophysiological mechanism of human visual perception. If the current point brightness is basically the same as the surrounding light intensity, or the light changes slowly, the formula is approximately equal. However, in most cases, the image does not meet the conditions for the approximate equality, and the influence of light cannot be completely eliminated for areas with uneven light changes.

[0068] The low-frequency part L(x,y) represents the area where the grayscale changes slowly. Therefore, the brightness component obtained from the original image can be filtered to retain part of the brightness information in the original image. In the Retinex algorithm, the brightness image is obtained by low-pass filtering, and its formula is:

[0069] L(x,y)=I(x,y)×F1(x,y) ④

[0070] F1(x,y) is the surround function of the first filtering, and L(x,y) is the brightness information in the original image. Due to the uneven brightness, the grayscale changes in L(x,y) are still dynamic, and the areas where the grayscale changes dynamically are exactly the areas with uneven brightness in the original image. So L(x,y) is filtered again, and the formula is:

[0071] L1(x,y)=I(x,y)×F2(x,y) ⑤

[0072] F2(x,y) is the surround function of the secondary filtering. For the filter templates of F1(x,y) and F2(x,y), the aforementioned mean template can be selected. The template size is adjusted by the mean value to eliminate the high-frequency part of L(x,y), thereby obtaining a relatively balanced brightness L1(x,y), and achieving a good visual effect for image brightness compensation.

[0073] S302: Processing the original image using the Laplace template to obtain image edge detail information;

[0074] Due to the mechanism of image contrast, when the human eye observes two areas of different brightness in an image, if the contrast at the edge increases, a strong contrast and contrast will be generated, making the image contour clearer. The Laplace operator can retain the grayscale difference between pixels, enhance the contrast at the grayscale mutation, and highlight the edge detail information of the image while retaining the image background. In order to be more suitable for digital image processing, a discrete Laplace operator template form is used. Common Laplace operator templates include the two templates shown in formula ⑥:

[0075] or

[0076] The edge of the image is the area where the grayscale in the original image jumps, so the Laplacian template is helpful to highlight the edge detail information.

[0077] S303: superimposing the preliminary enhanced image and the edge image, and performing stretching correction to obtain a final enhanced image;

[0078] According to formula ⑦, the real image function I(x,y) is multiplied by the Laplace operator and then the difference is obtained to obtain the superposition of the enhanced image and the edge image, and then stretched and corrected to the normal display range of the display to obtain the final enhanced image.

[0079] f(x,y)=I(x,y)-I(x,y)*K ⑦

[0080] In the present invention, the patient information is first input according to the established patient information template, and the endoscope is operated to obtain the image of the patient's lesion site. The obtained image is filtered through the multi-scale Retinex algorithm of the mean template to obtain the brightness component and the reflection component, and the brightness component is filtered to obtain a balanced brightness, and the reflection component is compensated to obtain a preliminary enhanced image. Then, the original image is processed by the Laplace template to obtain the image edge detail information, the image edge detail information is superimposed with the preliminary enhanced image, and the final enhanced image is obtained by stretching and correcting to the display range, thereby greatly improving the image quality. Finally, the patient's examination information is determined through the examination image of the lesion site and an examination report is generated, which shortens the diagnosis and treatment time and improves the diagnosis and treatment efficiency.

[0081] Corresponding to the operation method of the endoscope, the present invention also provides an operation system of the endoscope, specifically, as Figure 4 As shown, the endoscope operating system includes: an information management module 100 , an endoscope control module 200 , an image processing module 300 and a report output module 400 .

[0082] Information management module 100, used to input and manage patient information;

[0083] Specifically, information including the patient's name, age, gender, medical history, etc. will be entered into the system, and information items can be added and deleted as needed, thereby achieving customized management of patient information to meet the needs of different medical institutions. After the patient information is entered, it will be automatically saved locally to facilitate subsequent reading of the patient's information to avoid repeated entry of information. After reading the patient information, the incorrectly filled information can also be modified.

[0084] Furthermore, after obtaining the patient information, the patient information can be managed and the information collection can be configured. In order to meet the needs of different groups of people, especially to meet export needs, the patient information collection configuration system can realize the independent setting of patient information fields, such as age, gender, place of origin, nationality, examination number, previous examination number and other fields, and the set field attributes can also be configured and preset, so as to obtain a customized patient information management system.

[0085] An endoscope control module 200 is used to obtain an image of a patient's lesion site;

[0086] Specifically, Figure 2 As shown, the endoscope 301 includes an endoscope handle 3013, which is connected to the hard mirror insertion part 3010 through a detachable connection part 3011, and the other end of the endoscope handle is connected to the connecting line 3014 for signal transmission, and an adjustment button 3012 is set on the endoscope handle to adjust the endoscope. The endoscope control system is connected to the endoscope handle through a connecting line, and can allocate and set the attributes of the endoscope-collected image, such as image resolution setting, sharpness setting, brightness setting, hue setting, saturation setting, and video frame rate setting to adjust the captured image parameters, so that doctors can flexibly configure image parameters according to the usage scenario to achieve better observation effects. At the same time, the endoscope system also supports dual endoscope control and display, which is convenient for comparative analysis.

[0087] An image processing module 300 is used to enhance the image of the lesion site acquired by the endoscope to improve the image quality;

[0088] Specifically, first, an appropriate mean template is selected according to the image of the acquired lesion site for filtering processing to obtain a brightness component and a reflection component, and the brightness component is filtered to obtain a balanced brightness component and compensate the reflection component to obtain a preliminary enhanced image, and then the original image is processed through the Laplace template to obtain image edge detail information, and finally the enhanced image is superimposed on the edge image, and stretched and corrected to the normal display range of the display to obtain the final enhanced image. The specific image enhancement method is the same as the endoscope operation method, and will not be repeated here.

[0089] A report output module 400 generates a patient report based on the enhanced image;

[0090] Specifically, the format, layout and content of the examination report can be set according to the needs of the patient, or selected according to the actual situation of different departments or different medical institutions to generate report template management, thereby optimizing the configuration of the report template and making the configuration more flexible and convenient. Patient report management also supports the management of patient examination reports, supports multiple inquiries such as examination time, name, and examination doctor, and supports the import and export of cases, which is convenient for the management and backup of patient data. At the same time, the patient report system can also determine the patient's examination information based on the endoscopic examination image of the lesion site, thereby forming an examination report, and generate a report based on the report template settings. At the same time, the report contains examination pictures, symptoms, descriptions, diagnoses, suggestions and other modules. Except for picture information, all other parts are based on a large number of terms obtained in clinical practice and built into the system, which is convenient for doctors to input quickly, shorten diagnosis and treatment time, and improve efficiency.

[0091] Based on the above embodiments, the present invention further provides an intelligent terminal, whose principle block diagram is as follows: Figure 5 As shown, the above-mentioned intelligent terminal includes a processor, a memory, a network interface and a display screen connected through a system bus. The processor of the intelligent terminal is used to provide computing and control capabilities. The memory of the intelligent terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and an endoscope operation program. The memory provides an environment for the operation of the operating system and the endoscope operation program in the non-volatile storage medium. The network interface of the intelligent terminal is used to communicate with an external terminal through a network connection. When the endoscope operation program is executed by the processor, the steps of any one of the above-mentioned endoscope operation methods are implemented. The display screen of the intelligent terminal can be a liquid crystal display screen or other display screens.

[0092] Those skilled in the art will understand that Figure 5 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the smart terminal to which the scheme of the present invention is applied. The specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0093] In an embodiment of the present invention, a smart terminal is provided. The smart terminal includes a memory, a processor, and an endoscope operation program stored in the memory and executable on the processor. When the endoscope operation program is executed by the processor, the following operation instructions are performed:

[0094] Obtain patient information and enter it;

[0095] Acquire image data of the patient's lesion site through an endoscope system;

[0096] Filtering the image data of the lesion site to obtain a brightness component and a reflection component;

[0097] The brightness component is filtered to obtain a balanced brightness, and the reflection component is compensated to obtain a preliminary enhanced image;

[0098] Use the Laplace template to process the original image to obtain the image edge detail information;

[0099] Superimposing the preliminary enhanced image with the image edge detail information;

[0100] The superimposed image is stretched and corrected to obtain the final enhanced image;

[0101] Generate and output the patient's examination report based on the final enhanced image.

[0102] An embodiment of the present invention further provides a computer-readable storage medium, on which an endoscope operation program is stored. When the endoscope operation program is executed by a processor, the steps of any one of the endoscope operation methods provided in the embodiments of the present invention are implemented.

[0103] It should be understood that the present invention is described by some embodiments, and those skilled in the art will appreciate that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. In addition, under the teachings of the present invention, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the scope of protection of the present invention.

Claims

1. A method for operating an endoscope, comprising: Obtain patient information and enter it into the system; The endoscope system obtains images of the patient's lesion site; Generate and output a report of the patient based on the image of the patient's lesion site, characterized in that; After acquiring the image of the patient's lesion site, the endoscope system uses a multi-scale Retinex algorithm of a mean template to obtain an enhanced image, and generates and outputs a report on the patient based on the enhanced image.

2. The operating method according to claim 1, characterized in that: After the endoscope system acquires the image of the patient's lesion, it uses the multi-scale Retinex algorithm of the mean template to obtain an enhanced image, including: The acquired image of the lesion site is filtered to obtain a brightness component L(x,y) and a reflection component R(x,y), and the brightness component L(x,y) is filtered to obtain a balanced brightness component, and the reflection component R(x,y) is compensated to obtain a preliminary enhanced image.

3. The operating method according to claim 2, characterized in that: Filter the acquired image of the lesion: L(x,y)=I(x,y)×F1(x,y) Where F1(x,y) is the surround function of the first filtering, and L(x,y) is the brightness information in the original image; Filter the height component L(x,y) L1(x,y)=I(x,y)×F2(x,y) Where F2(x,y) is the surround function of the secondary filter.

4. The operating method according to claim 2, characterized in that: The original image is processed using the Laplace template to obtain the image edge detail information, and the preliminary enhanced image is combined with the edge image to obtain the final enhanced image. The patient report is generated and output based on the final enhanced image.

5. An operating system for an endoscope, comprising: Information management module, used to input and manage patient information; An endoscope control module, used to obtain images of the patient's lesion site; An image processing module is used to enhance the image of the lesion site obtained by the endoscope to improve the image quality; The report output module generates a patient report based on the enhanced image, and is characterized in that the image processing module uses a multi-scale Retinex algorithm of a mean template to obtain an enhanced image.

6. The operating system according to claim 5, characterized in that: The image processing module filters the acquired image of the lesion site to obtain a brightness component L(x,y) and a reflection component R(x,y), filters the brightness component L(x,y) to obtain a balanced brightness component, and compensates the reflection component R(x,y) to obtain a preliminary enhanced image.

7. The operating system according to claim 6, characterized in that: Filter the acquired image of the lesion: L(x,y)=I(x,y)×F1(x,y) Where F1(x,y) is the surround function of the first filtering, and L(x,y) is the brightness information in the original image; Filter the height component L(x,y) L1(x,y)=I(x,y)×F2(x,y) Where F2(x,y) is the surround function of the secondary filter.

8. The operating system according to claim 6, characterized in that: The original image is processed using the Laplace template to obtain the image edge detail information, and the preliminary enhanced image is combined with the edge image to obtain the final enhanced image. The patient report is generated and output based on the final enhanced image.

9. An intelligent terminal, characterized in that: The intelligent terminal includes at least one memory, at least one processor, and an endoscope operation program stored in the memory and executable on the processor. When the endoscope operation program is executed by the processor, the steps of the endoscope operation method as described in any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an endoscope operation program, and when the endoscope operation detection program is executed by the processor, the steps of the endoscope operation method according to any one of claims 1 to 4 are implemented.

Citation Information

Cited By

  • Image processing device, image processing method, and program

    WO2026181370A1

  • Image processing device, medical system, image processing method, and program

    WO2026181373A1