Endoscope image processing method, system, device and medium

Abstract

The invention discloses an endoscope image processing method, system and device and a medium, which are used for holmium laser lithotripsy, and the method comprises the following steps: when an endoscope works in a holmium laser mode and a holmium laser probe stretches out, controlling the endoscope to carry out gain adjustment; and obtaining a target endoscope image based on the endoscope after gain adjustment. According to the invention, the endoscope gain can be automatically adjusted in the holmium laser mode, the problem of image blurring caused by overlong extension of the holmium laser probe in the holmium laser mode is effectively improved, the image quality in the holmium laser mode is effectively improved, and a doctor can be better assisted in holmium laser lithotripsy.

Description

Technical Field

[0001] The present invention relates to the field of medical equipment and image processing technology, and in particular to an endoscopic image processing method, system, device and medium. Background Art

[0002] Holmium laser lithotripsy is one of the mainstream surgical methods for treating urinary stones such as kidney stones, ureteral stones, and bladder stones. In this operation, the doctor first uses an endoscope to insert a thin optical fiber (i.e., a holmium laser probe) into the location of the stone, and then uses the thermal effect of the holmium laser under the monitoring of the endoscope to directly break up the stone and then expel it. This procedure is a minimally invasive surgery, which has the advantages of less trauma, faster recovery, and fewer complications compared to traditional open surgery.

[0003] In holmium laser lithotripsy, since the holmium laser produces a large energy impact, when the holmium laser probe extends too short from the end of the endoscope, it will cause significant interference to the endoscopic image and cause image distortion; when the probe is extended too long, the image will be blurred due to the reduced brightness of the light source.

[0004] Therefore, there is a need for an image processing technology that can be used for holmium laser lithotripsy, which can improve the endoscopic image quality during holmium laser lithotripsy and help doctors perform holmium laser lithotripsy better. Summary of the invention

[0005] In view of this, the present invention provides an endoscopic image processing method, system, device and medium to solve the problem that the existing endoscopic image processing technology cannot perform image processing in the holmium laser mode, resulting in poor image quality.

[0006] The present invention provides an endoscopic image processing method for holmium laser lithotripsy, wherein the endoscope is equipped with a holmium laser probe, and the method comprises:

[0007] When the endoscope works in the holmium laser mode and the holmium laser probe is extended, the endoscope is controlled to perform gain adjustment; based on the endoscope after gain adjustment, a target endoscopic image is obtained.

[0008] Optionally, when the endoscope works in the holmium laser mode and the holmium laser probe is extended, the endoscope is controlled to perform gain adjustment; based on the endoscope after the gain adjustment, a target endoscopic image is obtained, including:

[0009] When the endoscope works in the holmium laser mode and the holmium laser probe is extended, an initial endoscopic image in the holmium laser mode is acquired, and the initial endoscopic image is identified to obtain an extended length of the holmium laser probe;

[0010] adjusting the endoscope gain according to the extension length of the holmium laser probe;

[0011] Based on the adjusted endoscope gain, the image of the endoscope in the holmium laser mode is reacquired to obtain the target endoscope image.

[0012] Optionally, after obtaining the extension length of the holmium laser probe, the method further comprises:

[0013] Whether the holmium laser probe meets the lithotripsy condition is determined according to the extension length of the holmium laser probe.

[0014] Optionally, judging whether the holmium laser probe meets the lithotripsy condition according to the extension length of the holmium laser probe includes:

[0015] Determining whether the extension length of the holmium laser probe is within a preset range;

[0016] If so, it is determined that the holmium laser probe meets the lithotripsy condition; otherwise, it is determined that the holmium laser probe does not meet the lithotripsy condition.

[0017] Optionally, when the holmium laser probe meets the lithotripsy condition, the method further includes:

[0018] Send out gravel warning signal;

[0019] The lithotripsy reminder signal is used to remind the holmium laser probe to allow lithotripsy work, and is also used to remind the endoscope to start adjusting the endoscope gain.

[0020] Optionally, the endoscope has an initial gain;

[0021] The step of adjusting the endoscope gain according to the extension length of the holmium laser probe comprises:

[0022] Determining the extension level corresponding to the holmium laser probe according to the extension length of the holmium laser probe;

[0023] According to the extension level, matching the adjustment gain value corresponding to the endoscope;

[0024] According to the adjustment gain value, the initial gain is increased to complete the endoscope gain adjustment.

[0025] Optionally, the identifying the initial endoscopic image to obtain the extension length of the holmium laser probe includes:

[0026] Obtaining a contour image of the extension portion corresponding to the holmium laser probe according to the initial endoscopic image;

[0027] Performing morphological processing on the protruding portion contour image, and using a skeleton extraction method to perform skeleton extraction on the protruding portion contour image after the morphological processing, to obtain a skeleton image of the protruding portion corresponding to the holmium laser probe;

[0028] Positioning the leading end point and the trailing end point in the skeleton image of the extension portion respectively to obtain the leading end point coordinates and the trailing end point coordinates;

[0029] The extension length of the holmium laser probe is calculated according to the coordinates of the head end point and the tail end point.

[0030] Optionally, obtaining a contour image of the extension portion corresponding to the holmium laser probe according to the initial endoscopic image includes:

[0031] Binarizing the initial endoscopic image to obtain a binary image;

[0032] Performing contour retrieval on the binary image to obtain a contour image;

[0033] The contour image is subjected to contour filtering to obtain a contour image of the extension portion corresponding to the holmium laser probe.

[0034] Optionally, the contour image includes a plurality of sub-image contours;

[0035] The performing contour filtering on the contour image to obtain the contour image of the extension portion corresponding to the holmium laser probe includes:

[0036] Pre-calibrating and obtaining the extension area corresponding to the holmium laser probe;

[0037] Obtaining a contour area corresponding to each sub-image contour in the contour image;

[0038] All the sub-image contours in the contour image whose contour area is larger than the extension area are screened out to obtain a plurality of potential extension contours;

[0039] Locate the contour of the tail end area of ​​the extension corresponding to the holmium laser probe from all the potential extension contours, and determine the remaining potential extension contours as potential intersection contours;

[0040] All the potential intersection contours that do not intersect with the contour of the tail end area of ​​the extension part are screened out to obtain the contour image of the extension part.

[0041] Optionally, before obtaining the contour image of the extension portion corresponding to the holmium laser probe according to the initial endoscopic image, the method further includes:

[0042] The initial endoscopic image is subjected to image preprocessing.

[0043] In addition, the present invention also provides an endoscopic image processing system for holmium laser lithotripsy, which is applied to the above-mentioned endoscopic image processing method, and the system comprises:

[0044] A gain adjustment module, used for controlling the endoscope to perform gain adjustment when the endoscope operates in a holmium laser mode and the holmium laser probe is extended;

[0045] The image acquisition module is used to obtain a target endoscopic image based on the endoscope after gain adjustment.

[0046] In addition, the present invention also provides an endoscopic image processing device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method steps in the aforementioned endoscopic image processing method when executed.

[0047] In addition, the present invention also provides a computer storage medium, which includes: at least one instruction, and when the instruction is executed by a computer, the method steps in the aforementioned endoscopic image processing method are implemented.

[0048] The beneficial effects of the present invention are as follows: when the user operates the holmium laser probe configured for the endoscope and extends the holmium laser probe from the working channel at the end of the endoscope head, it means that the endoscope enters the holmium laser mode. At this time, the endoscope is controlled to perform gain adjustment, which can automatically adjust the endoscope gain and accurately match the gain corresponding to the extension length of the holmium laser probe, thereby overcoming the image blur caused by the weak light condition when the holmium laser probe is extended. The quality of the target endoscopic image obtained can be effectively improved compared with the image before the gain adjustment, which truly solves the problem of image blur caused by the weakening of the light source brightness when the holmium laser probe is extended too long.

[0049] The endoscopic image processing method, system, device and medium of the present invention can realize automatic adjustment of endoscopic gain in holmium laser mode, effectively improve the image blur problem caused by the holmium laser probe extending too long in holmium laser mode, effectively improve the image quality in holmium laser mode, and can better assist doctors in performing holmium laser lithotripsy. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The features and advantages of the present invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present invention in any way. In the accompanying drawings:

[0051] Figure 1 A flow chart of an endoscope image processing method in Embodiment 1 of the present invention is shown;

[0052] Figure 2A flow chart of controlling an endoscope to adjust gain in a first embodiment of the present invention is shown;

[0053] Figure 3 A flow chart of obtaining the extension length of the holmium laser probe in the first embodiment of the present invention is shown;

[0054] Figure 4 Another flow chart of controlling the endoscope to adjust gain in the first embodiment of the present invention is shown;

[0055] Figure 5 A flow chart of determining whether the lithotripsy condition is met according to the extension length of the holmium laser probe in the first embodiment of the present invention is shown;

[0056] Figure 6 A flow chart of adjusting the endoscope gain according to the extension length of the holmium laser probe in the first embodiment of the present invention is shown;

[0057] Figure 7 The figure shows a structural diagram of an endoscope image processing system in the second embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0059] Embodiment 1

[0060] This embodiment provides an endoscopic image processing method for holmium laser lithotripsy, wherein the endoscope is equipped with a holmium laser probe, such as Figure 1 As shown, the method includes:

[0061] S1: When the endoscope works in the holmium laser mode and the holmium laser probe is extended, controlling the endoscope to adjust the gain;

[0062] S2: Obtain a target endoscopic image based on the endoscope after gain adjustment.

[0063] In this embodiment, when the user operates the holmium laser probe configured for the endoscope and extends the holmium laser probe from the working channel of the endoscope head end, it means that the endoscope enters the holmium laser mode. At this time, the endoscope is controlled to adjust the gain, which can automatically adjust the endoscope gain and accurately match the gain corresponding to the extended length of the holmium laser probe, thereby overcoming the image blur caused by the weak light conditions when the holmium laser probe is extended. The quality of the target endoscopic image obtained can be effectively improved compared to the image before the gain adjustment, which truly solves the problem of image blur caused by the reduced brightness of the light source when the holmium laser probe is extended too long.

[0064] The endoscopic image processing method of this embodiment can realize automatic adjustment of the endoscopic gain in the holmium laser mode, effectively improve the image blur problem caused by the holmium laser probe extending too long in the holmium laser mode, effectively improve the image quality in the holmium laser mode, and can better assist doctors in performing holmium laser lithotripsy.

[0065] Each step of the endoscopic image processing method for holmium laser lithotripsy in this embodiment is described in detail below.

[0066] Preferably, if Figure 2 As shown, S1 includes:

[0067] S11: when the endoscope works in the holmium laser mode and the holmium laser probe is extended, an initial endoscope image in the holmium laser mode is acquired, and the initial endoscope image is identified to obtain an extended length of the holmium laser probe;

[0068] S12: adjusting the endoscope gain according to the extension length of the holmium laser probe;

[0069] Correspondingly, S2 includes:

[0070] Based on the adjusted endoscope gain, the image of the endoscope in the holmium laser mode is reacquired to obtain a target endoscope image.

[0071] When the user operates the holmium laser probe configured for the endoscope, the endoscope enters the holmium laser mode and the holmium laser probe is extended, the initial endoscopic image in this mode is obtained at this time, and the image recognition technology can be used to automatically identify the length of the holmium laser probe extending from the working channel of the endoscope head end (i.e., the holmium laser probe extension length); the endoscope gain is automatically adjusted based on the holmium laser probe extension length, which can more accurately match the gain corresponding to the holmium laser probe extension length, and overcome the image blur caused by weak light conditions under the holmium laser probe extension length; finally, based on the adjusted endoscope gain, the image in the holmium laser mode is reacquired as the final target endoscopic image, which truly solves the problem of image blur caused by the reduced brightness of the light source when the holmium laser probe is extended too long, and effectively realizes the improvement of image quality in the holmium laser mode.

[0072] Specifically, an endoscope is usually provided with a camera, which is a device used to capture and transmit images during surgery. It usually includes an image sensor (such as CCD or CMOS) and related signal processing circuits. Endoscope gain is an important parameter in these signal processing circuits, which determines the degree of amplification of the image signal, thereby affecting the brightness of the image. In this embodiment S1, the initial endoscopic image is acquired by the image sensor.

[0073] Specifically, when an endoscope is used for holmium laser lithotripsy, a normal mode and a holmium laser mode are usually set on it. In the normal mode, the holmium laser is not turned on. In this mode, the gain of the endoscope is relatively small. Since the holmium laser is not turned on, there will be no image interference caused by the energy impact generated by the holmium laser. Under this smaller endoscope gain, the picture quality is high. In the holmium laser mode, the energy impact generated by the holmium laser will interfere with the collected image. If the smaller endoscope gain continues to be used, when the probe is extended too long, the image will be blurred due to the brightness of the light source. For the selection of the normal mode and the holmium laser mode, the user usually implements them separately through the endoscope button or the touch button on the image processing host interface. When the user selects the holmium laser mode, the holmium laser probe can be operated to extend it out of the working channel of the endoscope head end. The specific extension length is manually controlled by the user.

[0074] Preferably, if Figure 3 As shown, in this embodiment S11, the initial endoscopic image is identified to obtain the extension length of the holmium laser probe, including:

[0075] S111: obtaining a contour image of the extension portion corresponding to the holmium laser probe according to the initial endoscopic image;

[0076] S112: performing morphological processing on the protruding portion contour image, and using a skeleton extraction method to perform skeleton extraction on the protruding portion contour image after the morphological processing, to obtain a skeleton image of the protruding portion corresponding to the holmium laser probe;

[0077] S113: Positioning the leading end point and the trailing end point in the skeleton image of the extension portion respectively to obtain the leading end point coordinates and the trailing end point coordinates;

[0078] S114: Calculate the extension length of the holmium laser probe according to the coordinates of the head end point and the coordinates of the tail end point.

[0079] Obtaining the contour image of the extension corresponding to the holmium laser probe from the initial endoscopic image can facilitate the subsequent acquisition of the corresponding length of the extension, that is, the extension length of the holmium laser probe, based on the contour image of the extension; after obtaining the contour image of the extension, redundant points on the boundary of the contour of the extension can be eliminated through morphological processing (such as corrosion, expansion, etc.), making the image more concise; and then through the skeleton extraction method, the main structural features of the extension (such as shape and direction, etc.) can be further highlighted, useful information can be extracted, noise interference can be suppressed, and data redundancy can be reduced, which is helpful to improve the recognition accuracy and robustness of the holmium laser extension, and improve the accuracy of the subsequent calculated extension length of the holmium laser probe; after obtaining the skeleton image of the extension of the holmium laser probe, the coordinates of its head end point and tail end point are directly located, and the extension length of the holmium laser probe is directly calculated based on these two coordinates. Image processing and computer vision technology can be used to ensure the accuracy of the measurement of the extension length of the holmium laser probe, and automatic processing can be realized to reduce manual intervention errors, while also reducing manual operation time and improving work efficiency.

[0080] Furthermore, S111 includes:

[0081] S1111: performing binarization processing on the initial endoscopic image to obtain a binary image;

[0082] S1112: Perform contour retrieval on the binary image to obtain a contour image;

[0083] S1113: Perform contour filtering on the contour image to obtain the contour image of the extension portion corresponding to the holmium laser probe.

[0084] In the process of contour extraction of the protruding part contour image, firstly, binarization processing is performed to convert the initial endoscopic image into an image with only black and white colors, which can make the image more concise and clear, and at the same time reduce the amount of calculation, which is convenient for subsequent processing; then contour retrieval is performed to accurately extract all contours in the binary image, which is convenient for subsequent contour filtering; finally, through contour filtering, noise and unnecessary contours are filtered out, and the target contour can be extracted from all retrieved contours, and the contour image corresponding to the protruding part of the holmium laser probe, that is, the protruding part contour image, is matched. The above-mentioned contour extraction method of this embodiment has high accuracy and strong robustness, and can realize real-time processing of images, providing an accurate data basis for the subsequent analysis of the protruding length of the holmium laser probe.

[0085] The specific operations of the binarization process in step S1111 and the contour retrieval in step S1112 may adopt conventional operation methods, and the specific details are not repeated here.

[0086] Specifically, the contour image includes a plurality of sub-image contours;

[0087] S1113 includes:

[0088] S11131: Pre-calibrate and obtain the extension area corresponding to the holmium laser probe;

[0089] S11132: Obtaining the contour area corresponding to each sub-image contour in the contour image;

[0090] S11133: removing all the sub-image contours in the contour image whose contour areas are larger than the extension area, to obtain a plurality of potential extension contours;

[0091] S11134: Locate the contour of the tail end area of ​​the extension portion corresponding to the holmium laser probe from all the potential extension portion contours, and determine the remaining potential extension portion contours as potential intersection contours;

[0092] S11135: All the potential intersection contours that have no intersection with the contour of the tail end area of ​​the extension part are screened out to obtain the contour image of the extension part.

[0093] The contour image obtained by contour retrieval will include multiple sub-image contours, which contain more noise contours. Since the holmium laser probe is thinner and generally has a smaller area, in the above-mentioned contour filtering process, steps S11131 to S11133 are first used to perform filtering based on the pre-calibrated extension area (referring to the maximum area of ​​the extension of the holmium laser probe), thereby realizing area filtering. Sub-image contours larger than the extension area can be filtered out, which is more in line with the actual situation of the holmium laser probe, reduces the amount of image data, and facilitates subsequent further filtering.

[0094] Since the holmium laser probe is usually installed at a specific position of the endoscope, the position of the tail end area of ​​the extension is fixed in the image. This embodiment performs filtering with the located contour of the tail end area of ​​the extension through steps S11134 to S11135, thereby achieving position filtering. It can filter out sub-image contours that have no intersection with the contour of the tail end area of ​​the extension, and obtain an accurate contour image of the extension.

[0095] In the above step S11131, the area of ​​the extension, that is, the maximum area of ​​the extension of the holmium laser probe, is obtained by a conventional calibration method, such as an experimental calibration method; in the above step S11134, the contour of the tail end area of ​​the extension corresponding to the holmium laser probe is positioned by a conventional positioning method based on image recognition technology, such as using deep learning technology to train a positioning model, and using the positioning model to locate the contour of the tail end area of ​​the extension. The specific details will not be repeated here.

[0096] In the above step S11135, the intersection calculation with the contour of the tail end area of ​​the extension portion can be implemented by using a pixel-level intersection method or a contour-level intersection method; for the pixel-level intersection method, the intersection between the two images can be calculated by a bitwise AND operation (AND operation), that is, if the pixel values ​​of the two images at the same position are both 1 (white), then the pixel value of the intersection image at the position is also 1, that is, there is an intersection between the two images; otherwise it is 0. For the contour-level intersection method, the minimum distance between the two contours, the overlapping part and other parameters can be calculated, and based on the comparison between these parameters and the set values, it is determined whether they have an intersection.

[0097] Specifically, in S112, the skeleton extraction method specifically refers to a method that can simplify the object in the image into a thin and long skeleton structure, including a medial axis transformation method, a thinning algorithm, and the like.

[0098] Specifically, in S113, the method for locating the head end point and the tail end point may be the same as the method for locating the contour of the tail end area of ​​the protruding portion, which will not be described in detail here.

[0099] Specifically, in S114, after the coordinates of the head end point and the tail end point are located in S113, the extension length of the holmium laser probe can be obtained by directly calculating the straight-line distance between the two end points or the curve distance along the skeleton.

[0100] Preferably, if Figure 3 As shown, before S111, the method further includes:

[0101] S110: performing image preprocessing on the initial endoscopic image.

[0102] By performing image preprocessing on the initial endoscopic image, the image contrast can be enhanced, the noise can be reduced, the image stability can be enhanced, and the processing efficiency can be improved, which helps to improve the recognition efficiency and accuracy of the entire holmium laser probe extension length.

[0103] The preprocessing in this embodiment includes but is not limited to grayscale processing, Gaussian blur processing, etc.

[0104] Correspondingly, in this embodiment S111 is specifically as follows: obtaining, based on the initial endoscopic image after image preprocessing, a contour image of the extension portion corresponding to the holmium laser probe configured in the endoscope.

[0105] Preferably, if Figure 4 As shown, after S11 and before S12, the method further includes:

[0106] S13: judging whether the holmium laser probe meets the lithotripsy condition according to the extension length of the holmium laser probe.

[0107] Whether the holmium laser probe meets the lithotripsy conditions can be directly judged by the extended length of the holmium laser probe. The method is simple, efficient and easy to implement. By judging the lithotripsy conditions, on the one hand, it can facilitate the automatic triggering of the subsequent endoscopic gain adjustment control, and on the other hand, it helps to control the subsequent holmium laser probe to automatically enter the holmium laser lithotripsy work.

[0108] When it is determined that the holmium laser probe does not meet the lithotripsy condition according to the extended length of the holmium laser probe, the endoscope does not perform subsequent gain adjustment.

[0109] Preferably, if Figure 5 As shown, S13 includes:

[0110] S131: Determine whether the extension length of the holmium laser probe is within a preset range;

[0111] S132A: If yes, determine that the holmium laser probe meets the lithotripsy condition;

[0112] S132B: Otherwise, it is determined that the holmium laser probe does not meet the lithotripsy condition.

[0113] By directly comparing the extended length of the holmium laser probe identified by image with the preset range, it is possible to efficiently determine whether the current holmium laser probe meets the lithotripsy conditions, thereby facilitating the automatic triggering of the subsequent endoscopic gain adjustment control, thereby achieving automatic improvement of the endoscopic image quality.

[0114] Specifically, the preset range can be preset and adjusted according to actual conditions.

[0115] Under normal circumstances, the distance at which the CMOS at the end of the endoscope head can obtain a clear image is 0.5 to 1 cm; the electricity and magnetism during holmium laser lithotripsy will interfere with the sensor of the endoscope probe. Usually, when the holmium laser probe is extended by 1.5 cm, especially when it is about 2 cm, the CMOS cannot obtain a clear image. Therefore, in this embodiment, the preset range is set to ≥1.5 cm, preferably ≥2 cm, that is, when the extended length of the holmium laser probe is ≥1.5 cm (preferably when the extended length of the holmium laser probe is ≥2 cm), the endoscope is considered to meet the lithotripsy conditions, and when the extended length of the holmium laser probe is <1.5 cm (preferably when the extended length of the holmium laser probe is <2 cm), the endoscope is considered to not meet the lithotripsy conditions.

[0116] Preferably, if Figure 5 As shown, when the holmium laser probe meets the lithotripsy condition, the method further includes:

[0117] S133: issuing a gravel warning signal;

[0118] The lithotripsy reminder signal is used to remind the holmium laser probe to allow lithotripsy work, and is also used to remind the endoscope to start adjusting the endoscope gain.

[0119] By triggering the lithotripsy reminder signal, on the one hand, it reminds the user that the endoscope has started to adjust the endoscope gain, which can help the user accurately grasp the progress of endoscopic image processing; on the other hand, it reminds the user that the holmium laser probe is allowed to enter the lithotripsy work, helping doctors to better perform holmium laser lithotripsy surgery.

[0120] Specifically, the stone crushing reminder signal may be in the form of a buzzer signal, a light signal, or a flashing signal on a display interface of the image processing host, which is not limited in this embodiment.

[0121] Preferably, the endoscope has an initial gain;

[0122] like Figure 6 As shown, in this embodiment S12, adjusting the endoscope gain according to the extension length of the holmium laser probe includes:

[0123] S121: determining an extension level corresponding to the holmium laser probe according to the extension length of the holmium laser probe;

[0124] S122: matching an adjustment gain value corresponding to the endoscope according to the extension level;

[0125] S123: Increasing the initial gain according to the adjusted gain value to complete the endoscope gain adjustment.

[0126] Different extension lengths of holmium laser probes correspond to different lighting conditions and imaging environments. The extension level is determined by the extension length of the holmium laser probe, and different adjustment gain values ​​can be matched according to different extension levels. Then, based on the initial gain, the gain can be increased to achieve different degrees of endoscopic gain adjustment, thereby ensuring that high-quality endoscopic images can be obtained under different lighting conditions. The above method can more efficiently match the gain value that needs to be adjusted, and realize automatic gain adjustment that is more in line with the actual situation in the holmium laser mode, thereby helping to achieve adaptive adjustment of endoscopic image quality in holmium laser lithotripsy.

[0127] In this embodiment S122, a mapping table of extension levels and adjustment gain values ​​may be pre-set, wherein a mapping table stores a one-to-one mapping relationship between multiple extension levels and adjustment gain values. By querying the mapping table, the adjustment gain values ​​corresponding to different extension levels may be matched.

[0128] Usually, the gain of an endoscope is expressed in multiples, so the multiples can be directly used instead of the specific gain value.

[0129] In an optional embodiment, assuming that the initial gain is X1 (i.e., 1 times), when the holmium laser probe is extended to a length of [2cm, 3cm), its extension level is level 1, and its corresponding adjustment gain value is X1, i.e., 1 times, which is equivalent to increasing X1 on the basis of the initial X1, that is, the endoscope gain is adjusted to X2 (i.e., 2 times); when the holmium laser probe is extended to a length of [3cm, 4cm), its extension level is level 2, and its corresponding adjustment gain value is X4, i.e., 4 times, which is equivalent to increasing X4 on the basis of the initial X1, that is, the endoscope gain is adjusted to X5 (i.e., 5 times); when the holmium laser probe is extended to a length of [4cm, 5cm), its extension level is level 3, and its corresponding adjustment gain value is X9, i.e., 9 times, which is equivalent to increasing X9 on the basis of the initial X1, that is, the endoscope gain is adjusted to X10 (i.e., 10 times), and so on. The above-mentioned specific level divisions and corresponding adjustment gain value settings can be adjusted according to actual conditions.

[0130] After the endoscope gain adjustment is completed according to the method described in S12 of this embodiment, the endoscope acquires images with the adjusted endoscope gain, thereby obtaining a target endoscopic image with overall improved image quality, and then the subsequent holmium laser lithotripsy work can be assisted based on the target endoscopic image.

[0131] Embodiment 2

[0132] An endoscopic image processing system for holmium laser lithotripsy is applied to the endoscopic image processing method of embodiment 1, such as Figure 7 As shown, the system includes:

[0133] A gain adjustment module, used for controlling the endoscope to perform gain adjustment when the endoscope operates in a holmium laser mode and the holmium laser probe is extended;

[0134] The image acquisition module is used to obtain a target endoscopic image based on the endoscope after gain adjustment.

[0135] In this embodiment, when the user operates the holmium laser probe configured for the endoscope and extends the holmium laser probe from the working channel of the endoscope head end, it means that the endoscope enters the holmium laser mode. At this time, the gain adjustment module is used to control the endoscope to adjust the gain, which can automatically adjust the endoscope gain and accurately match the gain corresponding to the extended length of the holmium laser probe, thereby overcoming the image blur caused by the weak light conditions when the holmium laser probe is extended. The target endoscopic image obtained by the image acquisition module can be effectively improved in quality compared to the image before the gain adjustment, truly solving the problem of image blur caused by the reduced brightness of the light source when the holmium laser probe is extended too long.

[0136] The endoscopic image processing system of this embodiment can realize automatic adjustment of the endoscopic gain in the holmium laser mode, effectively improve the image blur problem caused by the holmium laser probe extending too long in the holmium laser mode, effectively improve the image quality in the holmium laser mode, and can better assist doctors in performing holmium laser lithotripsy.

[0137] The functions of each module in the endoscopic image processing system described in this embodiment are the same as the method steps of the endoscopic image processing method described in Example 1. Therefore, for details not included in this embodiment, please refer to Example 1 and Example 2. Figure 1 and Figure 6 The detailed description will not be repeated here.

[0138] Embodiment 3

[0139] This embodiment also provides an endoscopic image processing device, including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method steps in the endoscopic image processing method of the first embodiment when executed.

[0140] Through the computer program stored in the memory and running on the processor, automatic adjustment of the endoscope gain can be achieved in the holmium laser mode, which effectively improves the image blur problem caused by the holmium laser probe extending too long in the holmium laser mode, effectively improves the image quality in the holmium laser mode, and can better assist doctors in performing holmium laser lithotripsy.

[0141] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of a computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0142] The memory can be used to store computer programs and / or models. The processor realizes various functions of the computer device by running or executing the computer programs and / or models stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0143] It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by a computer program. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer programs may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0145] These computer programs can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0146] This embodiment further provides a computer storage medium, which includes: at least one instruction, which implements the method steps in the endoscopic image processing method of embodiment 1 when the instruction is executed by a computer.

[0147] By executing a computer storage medium containing at least one instruction, automatic adjustment of the endoscope gain can be achieved in the holmium laser mode, effectively improving the image blur problem caused by the holmium laser probe extending too long in the holmium laser mode, effectively improving the image quality in the holmium laser mode, and being able to better assist doctors in performing holmium laser lithotripsy.

[0148] Similarly, for details not yet provided in this embodiment, please refer to Embodiment 1, Embodiment 2 and Figures 1 to 7 The detailed description will not be repeated here.

[0149] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. An endoscopic image processing method, characterized in that: For holmium laser lithotripsy, the endoscope is equipped with a holmium laser probe, and the method comprises: When the endoscope works in the holmium laser mode and the holmium laser probe is extended, the endoscope is controlled to perform gain adjustment; based on the endoscope after gain adjustment, a target endoscopic image is obtained.

2. The endoscopic image processing method according to claim 1, characterized in that: When the endoscope works in the holmium laser mode and the holmium laser probe is extended, controlling the endoscope to perform gain adjustment; Based on the endoscope after gain adjustment, a target endoscope image is obtained, including: When the endoscope works in the holmium laser mode and the holmium laser probe is extended, an initial endoscopic image in the holmium laser mode is acquired, and the initial endoscopic image is identified to obtain an extended length of the holmium laser probe; adjusting the endoscope gain according to the extension length of the holmium laser probe; Based on the adjusted endoscope gain, the image of the endoscope in the holmium laser mode is reacquired to obtain the target endoscope image.

3. The endoscopic image processing method according to claim 2, characterized in that: After obtaining the extension length of the holmium laser probe, the method further comprises: Whether the holmium laser probe meets the lithotripsy condition is determined according to the extension length of the holmium laser probe.

4. The endoscopic image processing method according to claim 3, characterized in that: The step of judging whether the holmium laser probe meets the lithotripsy condition according to the extension length of the holmium laser probe comprises: Determining whether the extension length of the holmium laser probe is within a preset range; If so, it is determined that the holmium laser probe meets the lithotripsy condition; otherwise, it is determined that the holmium laser probe does not meet the lithotripsy condition.

5. The endoscopic image processing method according to claim 3, characterized in that: When the holmium laser probe meets the lithotripsy condition, the method further includes: Send out gravel warning signal; The lithotripsy reminder signal is used to remind the holmium laser probe to allow lithotripsy work, and is also used to remind the endoscope to start adjusting the endoscope gain.

6. The endoscopic image processing method according to claim 2, characterized in that: The endoscope has an initial gain; The step of adjusting the endoscope gain according to the extension length of the holmium laser probe comprises: Determining the extension level corresponding to the holmium laser probe according to the extension length of the holmium laser probe; According to the extension level, matching the adjustment gain value corresponding to the endoscope; According to the adjustment gain value, the initial gain is increased to complete the endoscope gain adjustment.

7. The endoscopic image processing method according to claim 2, characterized in that: The identifying the initial endoscopic image to obtain the extension length of the holmium laser probe includes: Obtaining a contour image of the extension portion corresponding to the holmium laser probe according to the initial endoscopic image; Performing morphological processing on the protruding portion contour image, and using a skeleton extraction method to perform skeleton extraction on the protruding portion contour image after the morphological processing, to obtain a skeleton image of the protruding portion corresponding to the holmium laser probe; Positioning the leading end point and the trailing end point in the skeleton image of the extension portion respectively to obtain the leading end point coordinates and the trailing end point coordinates; The extension length of the holmium laser probe is calculated according to the coordinates of the head end point and the tail end point.

8. The endoscopic image processing method according to claim 7, characterized in that: The step of obtaining a contour image of the extension portion corresponding to the holmium laser probe according to the initial endoscopic image comprises: Binarizing the initial endoscopic image to obtain a binary image; Performing contour retrieval on the binary image to obtain a contour image; The contour image is subjected to contour filtering to obtain a contour image of the extension portion corresponding to the holmium laser probe.

9. The endoscopic image processing method according to claim 8, characterized in that: The contour image includes a plurality of sub-image contours; The performing contour filtering on the contour image to obtain the contour image of the extension portion corresponding to the holmium laser probe includes: Pre-calibrating and obtaining the extension area corresponding to the holmium laser probe; Obtaining a contour area corresponding to each sub-image contour in the contour image; All the sub-image contours in the contour image whose contour area is larger than the extension area are screened out to obtain a plurality of potential extension contours; Locate the contour of the tail end area of ​​the extension corresponding to the holmium laser probe from all the potential extension contours, and determine the remaining potential extension contours as potential intersection contours; All the potential intersection contours that do not intersect with the contour of the tail end area of ​​the extension part are screened out to obtain the contour image of the extension part.

10. The endoscopic image processing method according to claim 7, characterized in that: Before obtaining the contour image of the extension portion corresponding to the holmium laser probe according to the initial endoscopic image, the method further includes: The initial endoscopic image is subjected to image preprocessing.

11. An endoscope image processing system, characterized in that: Used for holmium laser lithotripsy, applied to the endoscopic image processing method according to any one of claims 1 to 10, the system comprising: A gain adjustment module, used for controlling the endoscope to perform gain adjustment when the endoscope operates in a holmium laser mode and the holmium laser probe is extended; The image acquisition module is used to obtain a target endoscopic image based on the endoscope after gain adjustment.

12. An endoscope image processing device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein the computer program implements the method steps in the endoscopic image processing method according to any one of claims 1 to 10 when executed.

13. A computer storage medium, characterized in that: The computer storage medium comprises: at least one instruction, which implements the method steps in the endoscopic image processing method according to any one of claims 1 to 10 when the instruction is executed by a computer.

Images