Crohn's disease diagnosis auxiliary system based on flexible endoscope

Abstract

The present invention discloses a Crohn's disease diagnosis auxiliary system based on a flexible endoscope, comprising: a database for storing sample sets of various parts of the intestine under different pressure states; an image acquisition module for acquiring images of the intestine under natural pressure states, and acquiring images of the intestine under different pressure states according to preset rules; an auxiliary analysis module for comparing the images acquired by the image acquisition module with sample sets of corresponding pressure states in the database, and outputting a judgment result; the preset rule is to judge whether to acquire images of the intestine under different pressure states based on the results of the auxiliary analysis module's analysis of the images under natural pressure states; by acquiring images under different pressure states, analyzing and comparing the images under different pressure states with the corresponding samples in the database, and making a comprehensive judgment, the accuracy of Crohn's disease diagnosis can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Crohn's disease diagnosis systems, and in particular to a Crohn's disease diagnosis auxiliary system based on a flexible endoscope. Background Art

[0002] Crohn's disease is an inflammatory intestinal disease of unknown etiology that most commonly occurs in the terminal ileum and right colon. This disease, along with chronic nonspecific ulcerative colitis, is collectively referred to as inflammatory bowel disease (IBD). Crohn's disease is characterized by granulomatous inflammatory lesions combined with fibrosis and ulcers, resulting in ulcers, cobblestone-like changes, and intestinal stenosis in the digestive tract. Because Crohn's disease can occur anywhere in the digestive tract, symptoms vary. Consequently, clinical testing and diagnosis require consideration, making it relatively complex.

[0003] The most reliable examination method for Crohn's disease is colonoscopy. Colonoscopic evaluation of the severity of Crohn's disease is of great significance. A Crohn's disease endoscopic severity evaluation system has also been established clinically. However, most of these systems still rely on clinical qualitative and coarse-grained quantification stages, and are greatly influenced by the subjective influence of doctors and have poor consistency. In this study, based on the computer's precise modeling and objective, effective and fast information processing capabilities, artificial intelligence technology was used to analyze colonoscopic images to achieve effective analysis of Crohn's disease. On the one hand, the computer was used to quantify the endoscopic severity of Crohn's disease and objectively evaluate the individual's condition; on the other hand, artificial intelligence technology was used to improve the existing scoring system to make the disease assessment more comprehensive, accurate and reasonable, thereby further optimizing the treatment plan.

[0004] The existing Crohn's disease diagnosis system mainly relies on image information collected by endoscopes for analysis and judgment. However, due to the diversity and complexity of Crohn's disease lesions, there is a risk of misjudgment in the analysis and judgment of image information. If each part is examined more carefully, it will cause discomfort to the patient and take a long time, which is not conducive to practical application and promotion. Summary of the Invention

[0005] The purpose of the present invention is to provide a Crohn's disease diagnosis auxiliary system based on a flexible endoscope to solve the following technical problems:

[0006] How to improve the accuracy of Crohn's disease diagnosis based on system applicability.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] Crohn's disease diagnostic auxiliary system based on flexible endoscope, including:

[0009] A database for storing sample sets of various parts of the intestine under different pressure conditions;

[0010] Image acquisition module, used to obtain images of the intestine under natural pressure state, and

[0011] Acquire images of the intestine under different pressure conditions according to preset rules;

[0012] An auxiliary analysis module is used to compare the images acquired by the image acquisition module with the sample sets of corresponding pressure states in the database and output the judgment results;

[0013] The preset rule is to determine whether to obtain images of the intestine under different pressure states based on the results of the auxiliary analysis module analyzing the images under the natural pressure state.

[0014] In some embodiments of the present invention, the process of the image acquisition module acquiring an image is as follows:

[0015] S100, obtaining image information of the intestine at the current position under normal pressure state and sending it to the auxiliary analysis module;

[0016] S200, the auxiliary analysis module recognizes the received image information, and compares and analyzes the recognized content with the sample set of the natural state of the intestine in the database to generate the probability of lesions;

[0017] S300: Determine whether to acquire images of the intestine under different pressure states based on the lesion probability:

[0018] If the lesion probability is less than the preset value, it is determined that there is no Crohn's lesion at this location;

[0019] If the lesion probability is greater than a preset value, an image of the intestinal pressure change at the current position is obtained, and the corresponding key frame images under different pressure states are obtained based on the image.

[0020] In some embodiments of the present invention, a location recording module is further included;

[0021] The part recording module is used to record the diagnosed part according to the pre-input of the physician;

[0022] The auxiliary analysis module selects a sample set corresponding to the part according to the part recorded by the part recording module.

[0023] In some embodiments of the present invention, a lesion type analysis module is further included;

[0024] The lesion type analysis module is used to determine the lesion type based on the comparison results between images of the same part of the intestine under different pressure states.

[0025] In some embodiments of the present invention, the lesion type analysis module operates as follows:

[0026] SS100, obtain the area S of the lesion area in the natural state min ,and

[0027] The area of ​​the lesion area at the maximum pressure state S max ;

[0028] SS200, through the formula Obtain the yield ratio of the lesion site;

[0029] SS300, determine the lesion type based on the yield ratio.

[0030] In some embodiments of the present invention, the final diagnosis result is determined by comparing the result output by the auxiliary analysis module with the result output by the lesion type analysis module.

[0031] The steps for determining the final diagnosis result are:

[0032] If the lesion type corresponding to the output result of the auxiliary analysis module is consistent with the lesion type determined by the lesion type analysis module, the diagnosis result is that the patient is ill and is of the lesion type;

[0033] If the lesion type corresponding to the output result of the auxiliary analysis module is inconsistent with the lesion type determined by the lesion type analysis module, the diagnostic physician will determine whether the patient is ill and the lesion type.

[0034] In some embodiments of the present invention, the image acquisition module includes an endoscope body and an elastic sleeve sleeved on a detection end of the endoscope body;

[0035] The elastic sleeve rhythmically changes its deployment range.

[0036] In some embodiments of the present invention, an annular groove is provided at one end of the elastic sleeve close to the detection, and the annular groove separates the elastic sleeve into a fixed layer and an expanded layer;

[0037] The fixing layer is connected to the endoscope body;

[0038] The annular groove is evenly provided with a plurality of inflatable air bags;

[0039] The elastic sleeve is provided with a ventilation channel;

[0040] The plurality of inflatable air bags are inflated and deflated through the ventilation holes.

[0041] In some embodiments of the present invention, the outer surface of the elastic sleeve is evenly provided with drag reducing grooves, and one end of the drag reducing groove extends to the end of the elastic sleeve close to the detection end.

[0042] (1) The present invention can obtain a better viewing angle and a clearer image by acquiring images under different pressure states. On the other hand, the images under different pressure states are analyzed and compared with samples under different pressure states in the database, and a comprehensive judgment is made based on the analysis and judgment process under multiple states, which can improve the accuracy of Crohn's disease diagnosis. In addition, since the system analyzes the lesion location in real time, when the possible existence of a lesion is detected, the risk lesion location point is immediately further inspected, avoiding the physical and time inconvenience caused to the patient by multiple inspections, thereby ensuring the applicability of the system.

[0043] (2) The present invention sets a part recording module and filters the relevant sample set of the corresponding part in the database according to the part currently recorded in the part recording module, thereby avoiding the heavy workload and more misjudgment problems caused by a large number of sample sets, and judging whether there is a lesion and the type of lesion more quickly and accurately.

[0044] (3) The present invention sets up a lesion type analysis module, and can preliminarily determine the lesion type of the location point based on the comparison between images under different pressure states of the same part of the intestine, which can assist doctors in diagnosis and improve the applicability of the system.

[0045] (4) The present invention can obtain images of the intestine under different pressure states through the specific structural setting of the elastic sleeve. The drag-reducing groove can reduce the resistance when the endoscope enters the human body, thereby reducing the discomfort caused to the patient during the intestinal examination process. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention will be further described below with reference to the accompanying drawings.

[0047] Figure 1 This is a schematic diagram of a module of a flexible endoscope-based Crohn's disease diagnosis assistance system provided by the present invention;

[0048] Figure 2 It is a logic diagram of the process of image acquisition by the image acquisition module in the system of the present invention;

[0049] Figure 3 This is a schematic diagram of the overall structure of the image acquisition module of the present invention in a folded state;

[0050] Figure 4 This is a schematic diagram of the overall structure of the image acquisition module of the present invention in the unfolded state;

[0051] Figure 5 This is a cross-sectional view of the overall structure of the image acquisition module of the present invention in a folded state;

[0052] Figure 6It is a cross-sectional view of the overall structure of the image acquisition module of the present invention in the unfolded state.

[0053] Figure numerals: 1, endoscope body; 2, elastic sleeve; 21, inflatable airbag; 22, fixing layer; 23, deployment layer; 24, drag reduction groove; 25, annular groove; 26, ventilation channel. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0055] See also Figure 1 As shown, the present invention is a Crohn's disease diagnosis auxiliary system based on a flexible endoscope, comprising:

[0056] A database for storing sample sets of various parts of the intestine under different pressure conditions;

[0057] Image acquisition module, used to obtain images of the intestine under natural pressure state, and

[0058] Acquire images of the intestine under different pressure conditions according to preset rules;

[0059] An auxiliary analysis module is used to compare the images acquired by the image acquisition module with the sample sets of corresponding pressure states in the database and output the judgment results;

[0060] The preset rule is to determine whether to obtain images of the intestine under different pressure states based on the results of the auxiliary analysis module's analysis of the images under the natural pressure state.

[0061] The examination process for Crohn's disease requires an endoscope to obtain relatively clear and accurate image information. However, in some cases, the images obtained by the endoscope can only identify the preliminary situation of the lesion location, and generally further examination of the patient is required. Obviously, this will cause inconvenience to the patient and prolong the entire treatment cycle.

[0062] The diagnostic assistance system provided by the present invention includes a database, an image acquisition module and an auxiliary analysis module, wherein the database stores a sample set obtained through machine training, and the sample set is divided into a pathological sample set and a non-lesion sample set of different parts and different pressure states; the auxiliary analysis module can judge the condition of the lesion based on the image information; the image acquisition module can obtain images of the intestine under different pressure states (including natural state), and the image acquisition module will obtain image information according to preset rules.

[0063] Taking a flexible endoscope as an image acquisition module as an example, the flexible endoscope first collects images of the intestine in its natural state and sends them to the auxiliary analysis module for analysis in real time. When the auxiliary analysis module identifies that there is or is likely to be a lesion at that location, the flexible endoscope will apply a certain amount of pressure to the intestine and obtain images under different pressure states. On the one hand, this will enable the flexible endoscope to obtain a better viewing angle and clearer images; on the other hand, different types of lesions react differently when subjected to pressure. For example, for hard tissue and soft tissue, their volume and color will change differently when subjected to pressure. Therefore, the images under different pressure states are analyzed and compared with samples under different pressure states in the database, and a comprehensive judgment is made based on the analysis and judgment process under multiple states, which can improve the accuracy of Crohn's disease diagnosis. In addition, since the system analyzes the lesion location in real time, when a possible lesion is detected, the risk lesion location is immediately further inspected, avoiding the physical and time inconvenience caused to the patient by multiple inspections, thus ensuring the applicability of the system.

[0064] See also Figure 2 As shown, the process of image acquisition module acquiring images is as follows:

[0065] S100, obtaining image information of the intestine at the current position under normal pressure state and sending it to the auxiliary analysis module;

[0066] S200, the auxiliary analysis module recognizes the received image information, and compares and analyzes the recognized content with the sample set of the natural state of the intestine in the database to generate the probability of lesions;

[0067] S300: Determine whether to acquire images of the intestine under different pressure states based on the lesion probability:

[0068] If the lesion probability is less than the preset value, it is determined that there is no Crohn's lesion at this location;

[0069] If the lesion probability is greater than a preset value, an image of the intestinal pressure change at the current position is obtained, and the corresponding key frame images under different pressure states are obtained based on the image.

[0070] As an embodiment of the present invention, this embodiment provides a method for an image acquisition module to acquire images. Specifically, during the preliminary inspection of the intestine in its natural state, image information is collected for analysis. When the analysis shows that the probability of the lesion is extremely small or does not exist, it is determined that there is no Crohn's lesion at this location, and the next location is inspected. When there is a probability of a lesion, the image acquisition module will apply pressure to the location. At the same time, the image information from the start of pressure application to the end of pressure application will be sent to the auxiliary analysis module for analysis. The key frames corresponding to different pressure time points are used as images corresponding to the pressure state. Obviously, this image acquisition method can not only obtain the required image information, but also record the image information of the pressure change process of the lesion location. Therefore, in situations where a doctor needs to make a judgment, the changes in the lesion location recorded by the image information can more effectively help the doctor make a diagnosis, thereby further improving the applicability of the diagnostic system.

[0071] Also includes a location record module;

[0072] The site recording module is used to record the diagnosed site according to the pre-input of the physician;

[0073] The auxiliary analysis module selects a sample set corresponding to the part according to the part recorded by the part recording module.

[0074] Crohn's disease can occur in multiple parts of the body, including the rectum, sigmoid colon, descending colon (including the splenic flexure), transverse colon (including the hepatic flexure), ascending colon, cecum (including the ileocecal valve), and terminal ileum, and the pathological patterns and conditions in each part are different.

[0075] As an embodiment of the present invention, the diagnostic assistance system in the present invention also includes a part recording module. The physician inputs the currently examined part according to the part he is examining. At this time, the auxiliary analysis module will filter the relevant sample set of the corresponding part in the database according to the part currently recorded in the part recording module. Obviously, the corresponding analysis can avoid the heavier workload and more misjudgment problems brought by more sample sets. Therefore, the part recording module can help the auxiliary analysis module to determine whether there is a lesion and the type of lesion more quickly and accurately.

[0076] It also includes a lesion type analysis module;

[0077] The lesion type analysis module is used to determine the lesion type based on the comparison results between images of the same part of the intestine under different pressure states.

[0078] The main types of Crohn's disease lesions include ulcers, cobblestone nodules, masses and fistulas, and these lesions react differently to stress.

[0079] Therefore, as an embodiment of the present invention, based on the comparison between images of the same part of the intestine under different pressure states, the type of lesion at that location can be preliminarily determined, which can assist doctors in diagnosis and improve the applicability of the system.

[0080] The steps of the lesion type analysis module are as follows:

[0081] SS100, obtain the area S of the lesion area in the natural state min ,and

[0082] The area of ​​the lesion area at the maximum pressure state S max ;

[0083] SS200, through the formula Obtain the yield ratio of the lesion site;

[0084] SS300, determine the lesion type based on the yield ratio.

[0085] As an implementation method of the present invention, this embodiment provides a specific method for determining the type of lesion. Specifically, the area of ​​the lesion area under the natural state and the maximum pressure state is obtained, and the lesion type corresponding to the lesion position is determined based on the area ratio. Obviously, this method can utilize the different volume changes of different lesion types under stress yielding to preliminarily determine the lesion type, thereby assisting the doctor's diagnosis.

[0086] The final diagnosis result is determined by comparing the output of the auxiliary analysis module with the output of the lesion type analysis module.

[0087] As an embodiment of the present invention, the results output by the auxiliary analysis module are compared with the results output by the lesion type analysis module. The auxiliary analysis module will comprehensively determine whether the patient is sick and the specific type of the disease based on the results of judgment under different pressure states, while the lesion type analysis module will preliminarily judge the lesion type based on the comparison of the lesion location under different pressure states. Obviously, the final judgment result can be obtained based on the comparison of the results of the two.

[0088] The steps to determine the final diagnosis are:

[0089] If the lesion type corresponding to the output result of the auxiliary analysis module is consistent with the lesion type determined by the lesion type analysis module, the diagnosis result is that the patient is ill and is of the lesion type;

[0090] If the lesion type corresponding to the output result of the auxiliary analysis module is inconsistent with the lesion type determined by the lesion type analysis module, the lesion type shall be determined by the diagnostic physician.

[0091] Furthermore, when the results of the two judgments are the same, it means that the result is more accurate, so the judgment result is directly output. When the judgment results are different, it means that there are certain errors in the judgment process, so the diagnosis physician is asked to judge the type of lesion to ensure the accuracy of the judgment.

[0092] See also Figure 3-Figure 6 As shown, the image acquisition module includes an endoscope body 1 and an elastic sleeve 2 sleeved on the detection end of the endoscope body 1;

[0093] The elastic sleeve 2 rhythmically changes its deployment range.

[0094] This embodiment provides a structure for the image acquisition module that can specifically realize its functions. Specifically, the image acquisition module includes an endoscope body 1 and an elastic sleeve 2 that is sleeved on the detection end of the endoscope body 1; the elastic sleeve 2 rhythmically changes its deployment range, so that by squeezing the inner wall of the intestine to a certain extent through the elastic sleeve 2, images of the intestine under different pressure states can be obtained.

[0095] See also Figure 3-Figure 6 As shown, an annular groove 25 is provided at one end of the elastic sleeve 2 close to the detection, and the annular groove 25 separates the elastic sleeve 2 into a fixed layer 22 and an expanded layer 23;

[0096] The fixing layer 22 is connected to the endoscope body 1;

[0097] The annular groove 25 is evenly provided with a plurality of inflatable air bags 21;

[0098] The elastic sleeve 2 is provided with a ventilation channel 26;

[0099] The plurality of inflatable air bags 21 are inflated and deflated through the vent holes 26 .

[0100] Furthermore, this embodiment provides a specific way for the elastic sleeve 2 to change its expanded volume. Specifically, an annular groove 25 is provided at the top of the elastic sleeve 2, and a plurality of inflatable airbags 21 are evenly arranged in the annular groove 25. The plurality of inflatable airbags 21 are connected to the ventilation channel 26. Therefore, the inflatable airbags 21 are inflated and deflated through the ventilation channel 26, so that the inflatable airbags 21 can be expanded and contracted, and then the expansion layer 23 can be driven to expand and retract, thereby realizing the function of the elastic sleeve 2 to rhythmically change its expansion range.

[0101] In addition, it should be noted that the air inlet end of the ventilation channel 26 is connected to a pressure detection component and a pressure control component. Through the control and real-time detection of the pressure in the airbag by the two, the time point corresponding to the specified pressure can be obtained, and then image information under different pressure states can be obtained.

[0102] See also Figure 3-Figure 6As shown, the outer surface of the elastic sleeve 2 is evenly provided with drag reducing grooves 24 , and one end of the drag reducing groove 24 extends to the end of the elastic sleeve 2 close to the detection end.

[0103] As an embodiment of the elastic sleeve 2 in the present invention, drag reducing grooves 24 are evenly opened on the outer surface of the elastic sleeve 2, and one end of the drag reducing grooves 24 extends to the end of the elastic sleeve 2 close to the detection end. On the one hand, the structural setting of the drag reducing grooves 24 can reduce the thickness of part of the expansion layer 23, and make better use of the extension and retraction of the expansion layer 23. On the other hand, the drag reducing grooves 24 can reduce the resistance when the endoscope enters the human body, thereby reducing the discomfort caused to the patient during intestinal examination.

[0104] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A Crohn's disease diagnosis auxiliary system based on a flexible endoscope, characterized in that: include: A database for storing sample sets of various parts of the intestine under different pressure conditions; Image acquisition module, used to obtain images of the intestine under natural pressure state, and Acquire images of the intestine under different pressure conditions according to preset rules; An auxiliary analysis module is used to compare the images acquired by the image acquisition module with the sample sets of corresponding pressure states in the database and output the judgment results; The preset rule is to determine whether to acquire images of the intestine under different pressure states based on the results of the auxiliary analysis module's analysis of the image under natural pressure state; The process of the image acquisition module acquiring images is as follows: S100, obtaining image information of the intestine at the current position under natural pressure state and sending it to the auxiliary analysis module; S200, the auxiliary analysis module recognizes the received image information, and compares and analyzes the recognized content with the sample set of the natural state of the intestine in the database to generate the probability of lesions; S300: Determine whether to acquire images of the intestine under different pressure states based on the lesion probability: If the lesion probability is less than the preset value, it is determined that there is no Crohn's lesion at this location; If the lesion probability is greater than a preset value, an image of the intestinal pressure change at the current position is obtained, and the corresponding key frame images under different pressure states are obtained based on the image.

2. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 1, characterized in that: Also includes a location record module; The part recording module is used to record the diagnosed part according to the pre-input of the physician; The auxiliary analysis module selects a sample set corresponding to the part according to the part recorded by the part recording module.

3. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 1, characterized in that: It also includes a lesion type analysis module; The lesion type analysis module is used to determine the lesion type based on the comparison results between images of the same part of the intestine under different pressure states.

4. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 3, characterized in that: The steps of the lesion type analysis module are as follows: SS100, obtain the area of ​​the lesion area in the natural state ,and The area of ​​the lesion under maximum pressure ; SS200, through the formula Obtain the yield ratio of the lesion site; SS300, determine the lesion type based on the yield ratio.

5. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 3, characterized in that: The final diagnosis result is determined by comparing the output of the auxiliary analysis module with the output of the lesion type analysis module.

6. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 5, characterized in that: The steps for determining the final diagnosis result are: If the lesion type corresponding to the output result of the auxiliary analysis module is consistent with the lesion type determined by the lesion type analysis module, the diagnosis result is that the patient is ill and is of the lesion type; If the lesion type corresponding to the output result of the auxiliary analysis module is inconsistent with the lesion type determined by the lesion type analysis module, the diagnostic physician will determine whether the patient is ill and the lesion type.

7. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 1, characterized in that: The image acquisition module includes an endoscope body and an elastic sleeve sleeved on the detection end of the endoscope body; The elastic sleeve rhythmically changes its deployment range.

8. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 7, characterized in that: An annular groove is provided on the end of the elastic sleeve close to the detection, and the annular groove separates the elastic sleeve into a fixed layer and an expanded layer; The fixing layer is connected to the endoscope body; The annular groove is evenly provided with a plurality of inflatable air bags; The elastic sleeve is provided with a ventilation channel; The plurality of inflatable air bags are inflated and deflated through the ventilation holes.

9. The Crohn's disease diagnosis auxiliary system based on flexible endoscope according to claim 7, characterized in that: The outer surface of the elastic sleeve is evenly provided with drag reducing grooves, and one end of the drag reducing groove extends to the end of the elastic sleeve close to the detection end.

Images