Ai-assisted laparoscopic ileosigmoid neostomy for constipation treatment evaluation system

Abstract

This invention relates to the field of surgical assessment technology, specifically to an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system. The invention extracts the anastomosis surgical area; obtains lesion characteristic based on the positional relationship and grayscale change of each pixel within the anastomosis surgical area relative to the area center, and extracts the lesion area; based on the grayscale change of the lesion area and non-lesion area in the anastomosis surgical area in preoperative and postoperative intestinal images, as well as the smoothness of the lesion area's edge, the completeness of lesion resection is obtained, and combined with the stretching degree of the non-lesion area during surgery, the anastomosis tightness is obtained; the anastomosis tightness is assessed based on the anastomosis tightness. This invention quantifies the histological and geometric changes directly caused by the surgical actions of resection and anastomosis, more realistically reflecting the biomechanical seal of the anastomosis and improving the reliability of the assessment results.

Description

Technical Field

[0001] This invention relates to the field of surgical assessment technology, specifically to an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system. Background Technology

[0002] Ileosigmoid anastomosis is a key surgical procedure for treating specific intestinal diseases such as slow-transit constipation. Its core principle lies in resecting the diseased intestinal segment and then anastomosing the ileum to the sigmoid colon to restore the continuity of the digestive tract and restore intestinal function. With the development of minimally invasive surgical techniques, laparoscopy has become the preferred method for performing this surgery. A laparoscopic camera and surgical instruments are inserted through an incision in the patient's abdomen. The laparoscopic camera, with its built-in light source, captures images of the digestive system. These images are then enhanced and pre-processed with the assistance of artificial intelligence (AI), and transmitted via fiber optics to a subsequent signal processing system for real-time display on a dedicated monitor. Using the real-time images provided by the laparoscopy, surgeons can clearly observe the external surfaces of various organs within the abdominal cavity and precisely perform lesion resection and anastomosis. The success of the surgery is highly dependent on the quality of the anastomosis. An incomplete anastomosis can lead to serious complications such as anastomotic leakage and abdominal infection, forcing the patient to undergo a second surgery, which not only exacerbates patient suffering but also wastes medical resources. Therefore, it is essential to assess the ileo-sigmoid anastomosis.

[0003] Current intraoperative assessment methods largely rely on edge detection algorithms to identify and segment the edges of the ileum and sigmoid colon, assessing the tightness of the anastomosis based on the continuity, alignment, or spacing of the edge curves. However, during surgical procedures, when the edges of the ileum and sigmoid colon are brought closer together by instrument retraction, the resulting imaging features are visually highly similar to the state after the anastomosis is completed. This makes it difficult to effectively characterize the existence of a reliable physical anastomotic connection between the two intestinal ends, leading to biased assessment results that fail to accurately reflect the biomechanical seal of the anastomosis and thus insufficient clinical reliability of the assessment results. Summary of the Invention

[0004] To address the technical problem of unreliable assessment results due to the inability of visual morphology to accurately reflect the biomechanical seal of the anastomosis, the present invention aims to provide an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system. The specific technical solution adopted is as follows: This invention proposes an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system, the system comprising: The data acquisition module is used to acquire images of the ileum-sigmoid colon before and after the anastomosis surgery, which are recorded as preoperative intestinal images and postoperative intestinal images, respectively. The lesion extraction module is used to extract the anastomosis area in the preoperative intestinal image based on the degree of grayscale change of pixels at the same position in the preoperative and postoperative intestinal images; and to obtain the lesion feature degree of each pixel in the anastomosis area according to the positional relationship and grayscale change degree of each pixel relative to the center of the area, and to extract the lesion area in the anastomosis area. The anastomosis tightness analysis module is used to obtain the completeness of lesion resection based on the degree of grayscale change in the lesion area and non-lesion area in the anastomosis surgical area in the preoperative and postoperative intestinal images, as well as the smoothness of the edge of the lesion area; and to obtain the anastomosis tightness based on the degree of stretching of the non-lesion area in the anastomosis surgical area during the anastomosis surgery and the completeness of lesion resection. The surgical assessment module is used to evaluate the treatment of constipation in ileo-sigmoid anastomosis based on the tightness of the anastomosis.

[0005] Furthermore, the extraction of the anastomosis surgical area from the preoperative intestinal image includes: Preoperative and postoperative intestinal images were subjected to image difference processing to obtain differential images; The connected region formed by pixels with non-zero difference values ​​in the difference image is denoted as the suspected surgical region; the suspected surgical region with the largest area is selected as the differential surgical region. The region in the differential surgical image that is mapped to the region in the postoperative intestinal image is denoted as the anastomosis surgical region.

[0006] Furthermore, obtaining the lesion feature degree of each pixel within the anastomosis surgical area includes: The absolute value of the difference value of each pixel in the difference image is used as the absolute difference value of pixels with the same pixel coordinates in the preoperative intestinal image; the pixel with the largest absolute difference value in the preoperative intestinal image is selected and recorded as the lesion point; Select any pixel within the anastomosis surgical area and record it as an example point. Draw a ray passing through the example point with the lesion point as the endpoint. Record the last intersection of the ray with the edge of the anastomosis surgical area as the boundary analysis point of the example point. The ratio of the distance from the lesion point to the example point to the distance from the lesion point to the boundary analysis point is used as the core proximity of the example point. The lesion characteristic degree of the example point is obtained based on the proximity of the absolute difference value of the example point to the core.

[0007] Furthermore, the method for obtaining the edge smoothness includes: For edge pixels in the lesion area, select any edge pixel as the analysis point, and use the distance from the analysis point to the line segment connecting its two adjacent edge pixels as the fluctuation distance of the analysis point. Calculate the absolute value of the difference in the fluctuation distance between every two adjacent edge pixels on the edge of the lesion area, and sum all the absolute values ​​of the difference as the edge smoothness.

[0008] Furthermore, obtaining the completeness of lesion resection includes: The mean values ​​of the lesion feature degree of all pixels in the lesion area and the non-lesion area of ​​the anastomosis surgical area are calculated respectively and denoted as the first feature degree and the second feature degree respectively. The completeness of lesion resection is obtained based on the first feature degree, the second feature degree, and the edge smoothness.

[0009] Furthermore, obtaining the fit tightness includes: Obtain the area ratio of the lesion region in the anastomosis surgical area, denoted as tissue stretchability; perform negative correlation mapping on the tissue stretchability, and normalize the product of the mapping result and the completeness of lesion resection to obtain the anastomosis tightness.

[0010] Furthermore, the second characteristic degree and the edge smoothness are both negatively correlated with the completeness of lesion resection, while the first characteristic degree is positively correlated with the completeness of lesion resection.

[0011] Furthermore, the lesion area extracted from the anastomosis surgical area includes: Using the lesion point as the initial growth point, region growth is performed on the pixels within the anastomosis surgical area based on the lesion feature degree to obtain the lesion area.

[0012] Furthermore, the preoperative intestinal images and the postoperative intestinal images correspond one-to-one with each other in terms of pixels.

[0013] Furthermore, the area of ​​the suspected surgical region is the number of pixels within the suspected surgical region.

[0014] The present invention has the following beneficial effects: Firstly, effective anastomosis means that tissue is removed and reconstructed, resulting in significant changes in grayscale before and after the operation. In contrast, the morphological changes caused by traction result in minor changes in grayscale. By analyzing the degree of grayscale changes before and after the operation, we can identify the substantial and structural changes brought about by the surgical operation and obtain the anastomosis area.

[0015] Secondly, by combining the degree of grayscale change and spatial location, the probability of pixels representing lesion tissue characteristics is analyzed to obtain lesion feature degree, which can accurately identify lesion areas in complex backgrounds and effectively suppress misjudgments caused by traction. By analyzing the degree of grayscale change of lesion areas and non-lesion areas before and after surgery, and combining it with the smoothness of the edges that indicate the difficulty of lesion tissue resection, the integrity of lesion tissue resection is analyzed to obtain lesion resection integrity. Assessing the health and activity of the tissues around the anastomosis is key to its long-term sealing.

[0016] Thirdly, severe stretching of non-lesion tissue may lead to incomplete anastomosis. By combining the degree of stretching of non-lesion areas with the completeness of lesion resection, the tightness of the anastomosis can be analyzed from multiple dimensions, making the assessment results more comprehensive and closer to the actual biomechanical state, thus significantly improving the credibility of the assessment results.

[0017] In summary, by quantifying the histological and geometric changes directly caused by surgical actions of resection and anastomosis, the quality of the anastomosis can be accurately analyzed. This not only solves the problem of distinguishing between traction and anastomosis, but also elevates the assessment dimension from a single alignment of the intestinal cut edges to the level of anastomosis quality. This can more realistically reflect the biomechanical seal of the anastomosis and improve the reliability of the assessment results. Attached Figure Description

[0018] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a system structure diagram of an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of a computer device for evaluating constipation treatment using AI-assisted laparoscopic ileosigmoid anastomosis, as provided in one embodiment of the present invention. Detailed Implementation

[0020] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0022] The following description, in conjunction with the accompanying drawings, details the specific scheme of the AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system provided by the present invention.

[0023] Example 1: Please see Figure 1 The diagram illustrates a system block diagram of an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to an embodiment of the present invention. The system includes: a data acquisition module 110, a lesion extraction module 120, an anastomosis tightness analysis module 130, and a surgical assessment module 140.

[0024] The data acquisition module 110 is used to acquire images of the ileum-sigmoid colon before and after the anastomosis surgery, which are recorded as preoperative intestinal images and postoperative intestinal images, respectively.

[0025] Before the start of the ileosigmoid anastomosis procedure and again before the removal of instruments after the procedure, the treatment assessment system recorded images of the ileum, sigmoid colon, and surrounding areas taken from the same angle using a laparoscopy. These were recorded as the original preoperative bowel image and the original postoperative bowel image, respectively. The two images were then processed for grayscale conversion and noise reduction to obtain the preoperative and postoperative bowel images, respectively. The core purpose of taking images from the same angle was to minimize changes in perspective and position, pinpointing the differences between the two images primarily to the surgical procedure itself, rather than significant changes in camera angle.

[0026] Because laparoscopic cameras can shift in a real surgical environment, and breathing or heartbeat can deform internal organs, perfect alignment cannot be guaranteed when taking images from the same angle. This method matches postoperative images with preoperative intestinal images to regenerate postoperative intestinal images. The specific method is as follows: First, feature points in preoperative and postoperative intestinal images are selected using feature detection algorithms such as scale-invariant feature transformation. Second, a correspondence between feature points in the two images is established through feature descriptor alignment and nearest neighbor search strategies, thereby obtaining matching point pairs representing the same anatomical location. Then, based on the matching point pairs, an optimal spatial geometric transformation model is fitted using robust estimation algorithms such as RANSAC, typically an affine transformation or perspective transformation. Finally, the postoperative image is interpolated and resampled using the transformation model, mapping it to the coordinate system of the preoperative intestinal image to generate a spatially aligned registered image, denoted as the postoperative intestinal image. All of the above operations are techniques well-known to those skilled in the art and will not be elaborated further here.

[0027] It should be noted that there is a one-to-one correspondence between the pixels in the preoperative and postoperative intestinal images. In this embodiment of the invention, a weighted average grayscale algorithm is used for grayscale processing, and Gaussian filtering is used for noise reduction. The specific methods are not described here, as they are all techniques well known to those skilled in the art. Other image preprocessing algorithms may also be used in other embodiments of the invention, and are not limited here.

[0028] The lesion extraction module 120 is used to extract the anastomosis area in the preoperative intestinal image based on the degree of grayscale change of pixels at the same position in the preoperative and postoperative intestinal images; and to obtain the lesion feature degree of each pixel in the anastomosis area according to the positional relationship and grayscale change degree of each pixel in the anastomosis area relative to the center of the area, and to extract the lesion area in the anastomosis area.

[0029] Ileosigmoid anastomosis involves resecting the diseased colon and the terminal ileum, then anastomosing the healthy ileal stump to the sigmoid colon stump. The location of the unoperated normal tissue area remains unchanged; its grayscale value remains largely the same in pre- and post-operative images. However, the resection of the diseased portion and suturing of the incision site cause a change in location, resulting in a significant alteration in the grayscale value of this area in pre- and post-operative images. Therefore, the anastomosis area can be determined based on the degree of grayscale change of pixels at the same location in pre- and post-operative intestinal images.

[0030] Diseased tissue is invasive and grows peripherally, causing inflammation in surrounding healthy tissue and forming a complex whole. When surgeons separate the diseased tissue, they trace back to and manipulate around it, making it the center of the surgical area. Therefore, the proximity of the diseased tissue to the center of the anastomosis area is a natural consequence of disease progression and a direct target of surgical strategy. Disease characteristic analysis quantifies the intensity and spatial location of pixel grayscale changes, analyzing the likelihood that pixels represent diseased tissue features, identifying the lesion area truly originating from the primary lesion, and thus achieving precise assessment of the quality and extent of surgical resection.

[0031] The anastomosis tightness analysis module 130 is used to obtain the completeness of lesion resection based on the degree of grayscale change in the lesion area and non-lesion area in the anastomosis surgical area in the preoperative and postoperative intestinal images, as well as the smoothness of the edge of the lesion area; and to obtain the anastomosis tightness based on the degree of stretching of the non-lesion area in the anastomosis surgical area and the completeness of lesion resection.

[0032] The main purpose of ileosigmoid anastomosis surgery is to completely remove the diseased tissue and anastomose the ileal ends with the sigmoid colon ends to ensure intestinal continuity. Therefore, the tightness of the anastomosis can be assessed by examining the extent of lesion removal and the degree of anastomosis.

[0033] Complete removal of the lesion tissue results in the original lesion site appearing as entirely different tissue in postoperative intestinal imaging, leading to significant changes in grayscale levels before and after surgery. Simultaneously, it avoids unnecessary damage to surrounding normal tissue; that is, the appearance of normal tissue subjected to slight traction or wiping shows minimal change before and after surgery, resulting in minimal grayscale changes in non-lesion tissue. The shape of the lesion tissue significantly influences the ease of its removal. Irregular edges of the lesion tissue often increase the difficulty of removal, making complete removal difficult. Therefore, by combining the degree of grayscale change and edge smoothness of the lesion and non-lesion areas before and after surgery, the completeness of lesion tissue removal can be analyzed to determine the completeness of lesion removal.

[0034] After the diseased tissue is removed, the normal ileum and sigmoid colon ends are stretched and anastomosed to compensate for the discontinuity caused by the removal of the diseased tissue. Excessive stretching of the normal tissue can lead to incomplete anastomosis. Incomplete removal of the diseased tissue at the intestinal end results in poor blood supply; if poorly supplied tissue is forcibly anastomosed, it will gradually necrose, forming a defect at the anastomosis site and causing leakage. Therefore, analyzing the degree of stretching in the non-disease area during anastomosis surgery in relation to the completeness of lesion removal allows for a more comprehensive assessment that closely approximates the actual biomechanical state, significantly improving the reliability of the assessment results.

[0035] Surgical assessment module 140 is used to assess the treatment of constipation in ileo-sigmoid anastomosis based on the tightness of the anastomosis.

[0036] The greater the anastomosis tightness, the greater the likelihood of a successful ileo-sigmoid colon anastomosis. The anastomosis tightness is uploaded to the treatment assessment system to help doctors evaluate the success of the anastomosis and arrange subsequent treatments.

[0037] The anastomosis tightness of this scheme is based on objective feature results generated by big data analysis. It does not directly provide diagnostic conclusions, but rather provides doctors with objective quantitative data references, enabling them to focus more quickly on the pathological features of the anastomosis and improve their efficiency in judging the quality of the anastomosis surgery.

[0038] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the anastomosis surgical region includes: performing image difference processing on preoperative intestinal images and postoperative intestinal images to obtain a difference image; denoteing the connected region composed of pixels with non-zero difference values ​​in the difference image as the suspected surgical region; selecting the suspected surgical region with the largest area as the difference surgical region; and mapping the difference surgical region in the difference image to the region in the postoperative intestinal image as the anastomosis surgical region.

[0039] It should be noted that the difference value of each pixel in the differential image is the difference in grayscale value between the corresponding pixel in the postoperative and preoperative intestinal images. The position of normal tissue areas that have not undergone surgery remains unchanged, and the difference value in this area is theoretically zero. However, partial resection of the lesion and suturing of the incision will cause a change in position, significantly altering the grayscale value of this area, making the difference value non-zero. Therefore, the difference value of pixels within the suspected surgical area is not zero. Noise, such as instrument reflections and interference from minute blood flow, will also cause changes in grayscale values ​​before and after surgery. However, noise is usually dispersed and covers a small area, while the actual surgical area, such as lesion resection, is typically a continuous and large area. Therefore, the largest suspected surgical area can be selected as the anastomosis area.

[0040] In one implementation of this embodiment, the number of pixels within a region is used as the region area.

[0041] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining lesion feature degree includes: taking the absolute value of the difference value of each pixel in the difference image as the absolute difference value of pixels with the same pixel coordinates in the preoperative intestinal image; selecting the pixel with the largest absolute difference value in the preoperative intestinal image and recording it as the lesion point; randomly selecting a pixel in the anastomosis surgical area and recording it as the example point, drawing a ray passing through the example point with the lesion point as the endpoint, and recording the last intersection point of the ray with the edge of the anastomosis surgical area as the boundary analysis point of the example point; taking the ratio of the distance from the lesion point to the example point to the distance from the lesion point to the boundary analysis point as the core proximity of the example point; and obtaining the lesion feature degree of the example point based on the absolute difference value and the core proximity of the example point.

[0042] It's important to note that lesion tissue exhibits the greatest visual difference from normal tissue, resulting in the most dramatic grayscale changes after its removal. Pixels with larger difference values ​​are more likely to belong to lesion tissue, thus allowing us to select the lesion point most likely to be the core of the lesion. A ray defines a unique path from the lesion center to the surgical boundary, with the final intersection representing the farthest point reachable by the surgery along the ray direction. A smaller core proximity means the example point is closer to the lesion center, increasing the likelihood that it belongs to the lesion tissue, effectively eliminating the influence of absolute distance. Conversely, a larger absolute difference means the example point better matches the dramatic grayscale changes of lesion tissue before and after surgery, further increasing the likelihood that it belongs to the lesion tissue. Therefore, core proximity is negatively correlated with lesion characteristic, while absolute difference is positively correlated with lesion characteristic.

[0043] In this embodiment of the invention, the ratio of the absolute difference value of the example point to the maximum absolute difference value among all pixels in the anastomosis surgical area is calculated and denoted as the drastic change of the example point; the product of the difference between the constant 1 and the core proximity and the drastic change is used as the lesion characteristic degree of the example point. Since the core proximity ranges from 0 to 1, a negative correlation mapping is achieved by subtracting the core proximity from the constant 1.

[0044] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the lesion region includes: using the lesion point as the initial growth point, performing region growth on the pixels within the anastomosis surgical area based on the lesion feature degree to obtain the lesion region.

[0045] It should be noted that, in one implementation of this invention, lesion points are used as growth points for region growth. Pixels within a preset neighborhood of the growth point whose lesion feature degree is greater than or equal to a preset lesion threshold are used as new growth points for region growth. Region growth stops when the lesion feature degree of all pixels within the preset neighborhood of all new growth points is less than the preset lesion threshold, thus obtaining the lesion region. The preset lesion threshold is set to 0.7, and the preset neighborhood is eight neighborhoods.

[0046] In other embodiments of the present invention, the connected region formed by pixels with lesion feature degree greater than a preset lesion threshold in the anastomosis surgical area can also be recorded as a suspected lesion area. The mean value of lesion feature degree of all pixels in each suspected lesion area is calculated, and the suspected lesion area corresponding to the maximum mean value is selected as the lesion area.

[0047] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the edge smoothness includes: for edge pixels of the lesion region, arbitrarily selecting one edge pixel as the analysis point, and taking the distance from the analysis point to the line segment connecting its two adjacent edge pixels as the fluctuation distance of the analysis point; calculating the absolute value of the difference between the fluctuation distances of every two adjacent edge pixels on the edge of the lesion region, and summing all the absolute values ​​of the difference as the edge smoothness. It should be noted that the fluctuation distance measures the degree of concavity and convexity of the analysis point relative to its adjacent edge pixels. The smaller the difference in the fluctuation distance between adjacent edge pixels on the edge of the lesion region, the smaller the degree of edge change, that is, the smoother the edge of the lesion region.

[0048] In another embodiment of the present invention, the curvature of each edge pixel on the edge of the lesion region is calculated, and the standard deviation of all curvatures is used as the edge smoothness. It should be noted that the smaller the standard deviation, the smoother the edge of the lesion region.

[0049] In other embodiments of the present invention, an erosion operation is performed on the lesion area, followed by an expansion operation of the same degree. The area of ​​the lesion area before and after the opening operation is obtained, and the difference between the two area areas is used as the degree of edge smoothness. The area is measured by the number of pixels within the area. It should be noted that smooth areas suffer less area loss, while rough areas are smoothed out after the expansion operation, resulting in a larger area loss. Therefore, the smaller the area difference, the smoother the edge of the lesion area.

[0050] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the completeness of lesion resection includes: calculating the mean value of the lesion feature degree of all pixels in the lesion area and the non-lesion area in the anastomosis surgical area, respectively, and recording them as the first feature degree and the second feature degree in sequence; and obtaining the completeness of lesion resection based on the first feature degree, the second feature degree and the edge smoothness.

[0051] It should be noted that the lesion characteristic score is calculated based on the grayscale changes in preoperative and postoperative images. It can represent the grayscale changes of pixels at the same location in preoperative and postoperative intestinal images. The first characteristic score and the second characteristic score reflect the overall grayscale changes in the lesion area and the non-lesion area, respectively. If the first characteristic score is larger and the second characteristic score is smaller, it indicates that the lesion tissue has undergone more significant changes and the normal tissue has undergone less changes, which is more consistent with the characteristics of complete lesion tissue resection, and thus the lesion resection completeness is greater. If the edge smoothness is smaller, the edge of the lesion area is smoother, the lesion area is easier to resect, and the easier it is to be completely removed, thus the lesion resection completeness is greater. Therefore, the second characteristic score and edge smoothness are both negatively correlated with the lesion resection completeness, while the first characteristic score is positively correlated with the lesion resection completeness. In the embodiments of the present invention, the second characteristic score and edge smoothness are negatively correlated, and the product of the two mapping results and the first characteristic score is taken as the lesion resection completeness.

[0052] In this embodiment of the invention, the data to be processed is used as the exponent of an exponential function with the natural constant as the base to achieve a negative correlation mapping of the data to be processed. Alternatively, the negative correlation mapping can be achieved by taking the reciprocal or other methods.

[0053] It is important to note that the non-lesion area refers to the area outside the lesion area within the anastomosis surgical area.

[0054] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the anastomosis tightness includes: obtaining the area ratio of the lesion area in the anastomosis surgical area, denoted as the tissue stretching degree; performing a negative correlation mapping on the tissue stretching degree, and normalizing the product of the mapping result and the completeness of lesion resection to obtain the anastomosis tightness.

[0055] It should be noted that in this embodiment, the area is measured by the number of pixels within the region, and the tissue stretchability is the ratio of the number of pixels in the non-lesion area to the number of pixels in the anastomosis area. A greater tissue stretchability indicates a larger proportion of the lesion area and a smaller proportion of the non-lesion area in the anastomosis area. This results in greater stretching of the intestinal stump during anastomosis, increasing the likelihood of incomplete anastomosis and thus lower anastomosis tightness, reducing the probability of successful ileo-sigmoid colon anastomosis. Conversely, a smaller degree of lesion resection completeness increases the likelihood of defects forming at the anastomosis site, leading to leakage and further reducing anastomosis tightness. Therefore, tissue stretchability is negatively correlated with anastomosis tightness, while lesion resection completeness is positively correlated with anastomosis tightness. In this embodiment, the difference between a constant 1 and the tissue stretchability is calculated, and the product of this difference and lesion resection completeness is normalized to obtain the anastomosis tightness. Since the tissue stretchability ranges from 0 to 1, the difference between the constant 1 and the tissue stretchability can be used to achieve a negative correlation mapping of tissue stretchability.

[0056] It should be noted that the Sigmoid function is used for normalization in this embodiment of the invention, but other normalization methods such as function transformation can also be used, and no limitation is made here.

[0057] This invention is now complete.

[0058] Example 2: Figure 2 This is a schematic diagram of a computer device for evaluating constipation treatment using AI-assisted laparoscopic ileosigmoid anastomosis, as provided in one embodiment of the present invention. Exemplary, such as... Figure 2 As shown, the computer device includes: a memory 201, a processor 202, and a computer program 203 stored in the memory 201 and running on the processor 202, wherein when the processor 202 executes the computer program 203, the computer device can execute any of the aforementioned AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment systems.

[0059] Furthermore, this application also protects an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to perform an AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system provided in this application.

[0060] This embodiment can divide the device into functional modules based on the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0061] It should be understood that the device provided in this embodiment is used to perform the above-described AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system, and therefore can achieve the same effect as the above-described implementation method.

[0062] When using integrated units, the device may include a processing module and a storage module. When applied to a workpiece, the processing module can be used to control and manage the workpiece's operations. The storage module can be used to support the execution of program code by the workpiece.

[0063] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0064] Example 3: This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-mentioned related method steps to realize the AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system provided in the above embodiment.

[0065] In this embodiment, the device and computer-readable storage medium are used to execute the corresponding system provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding system provided above, and will not be repeated here.

[0066] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0068] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system, characterized in that, The system includes: The data acquisition module is used to acquire images of the ileum-sigmoid colon before and after the anastomosis surgery, which are recorded as preoperative intestinal images and postoperative intestinal images, respectively. The lesion extraction module is used to extract the anastomosis area in the preoperative intestinal image based on the degree of grayscale change of pixels at the same position in the preoperative and postoperative intestinal images; and to obtain the lesion feature degree of each pixel in the anastomosis area according to the positional relationship and grayscale change degree of each pixel relative to the center of the area, and to extract the lesion area in the anastomosis area. The anastomosis tightness analysis module is used to obtain the completeness of lesion resection based on the degree of grayscale change in the lesion area and non-lesion area in the anastomosis surgical area in the preoperative and postoperative intestinal images, as well as the smoothness of the edge of the lesion area; and to obtain the anastomosis tightness based on the degree of stretching of the non-lesion area in the anastomosis surgical area during the anastomosis surgery and the completeness of lesion resection. The surgical assessment module is used to evaluate the treatment of constipation in ileo-sigmoid anastomosis based on the tightness of the anastomosis.

2. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 1, characterized in that, The extraction of the anastomosis area from the preoperative intestinal image includes: Preoperative and postoperative intestinal images were subjected to image difference processing to obtain differential images; The connected region formed by pixels with non-zero difference values ​​in the difference image is denoted as the suspected surgical region; the suspected surgical region with the largest area is selected as the differential surgical region. The region in the differential surgical image that is mapped to the postoperative intestinal image is denoted as the anastomosis surgical region.

3. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 2, characterized in that, The acquisition of the lesion feature degree of each pixel in the anastomosis surgical area includes: The absolute value of the difference value of each pixel in the difference image is used as the absolute difference value of pixels with the same pixel coordinates in the preoperative intestinal image; the pixel with the largest absolute difference value in the preoperative intestinal image is selected and recorded as the lesion point; Select any pixel within the anastomosis surgical area and record it as an example point. Draw a ray passing through the example point with the lesion point as the endpoint. Record the last intersection of the ray with the edge of the anastomosis surgical area as the boundary analysis point of the example point. The ratio of the distance from the lesion point to the example point to the distance from the lesion point to the boundary analysis point is used as the core proximity of the example point. The lesion characteristic degree of the example point is obtained based on the proximity of the absolute difference value of the example point to the core.

4. The AI-assisted laparoscopic ileosigmoid colon anastomosis constipation treatment assessment system according to claim 1, characterized in that, The method for obtaining the edge smoothness includes: For edge pixels in the lesion area, select any edge pixel as the analysis point, and use the distance from the analysis point to the line segment connecting its two adjacent edge pixels as the fluctuation distance of the analysis point. Calculate the absolute value of the difference in the fluctuation distance between every two adjacent edge pixels on the edge of the lesion area, and sum all the absolute values ​​of the difference as the edge smoothness.

5. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 1, characterized in that, The process of obtaining the completeness of lesion resection includes: The mean values ​​of the lesion feature degree of all pixels in the lesion area and the non-lesion area of ​​the anastomosis surgical area are calculated respectively and denoted as the first feature degree and the second feature degree respectively. The completeness of lesion resection is obtained based on the first feature degree, the second feature degree, and the edge smoothness.

6. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 1, characterized in that, The process of obtaining the fit tightness includes: Obtain the area ratio of the lesion region in the anastomosis surgical area, denoted as tissue stretchability; perform negative correlation mapping on the tissue stretchability, and normalize the product of the mapping result and the completeness of lesion resection to obtain the anastomosis tightness.

7. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 5, characterized in that, The second characteristic degree and the smoothness of the edge are both negatively correlated with the completeness of lesion resection, while the first characteristic degree is positively correlated with the completeness of lesion resection.

8. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 3, characterized in that, The lesion area extracted from the anastomosis surgical area includes: Using the lesion point as the initial growth point, region growth is performed on the pixels within the anastomosis surgical area based on the lesion feature degree to obtain the lesion area.

9. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 1, characterized in that, The preoperative intestinal images and the postoperative intestinal images correspond one-to-one with each other in terms of pixels.

10. The AI-assisted laparoscopic ileosigmoid anastomosis constipation treatment assessment system according to claim 2, characterized in that, The area of ​​the suspected surgical region is the number of pixels within the suspected surgical region.

Images