Digestive tract detection system based on artificial intelligence

Abstract

The invention relates to the technical field of digestive tract detection, and discloses an artificial intelligence-based digestive tract detection system, which comprises a data acquisition unit, a preprocessing unit, a feature extraction unit, an anomaly detection unit and a result display unit, and focuses on an endoscopic image, the endoscopic image is accurately preprocessed and converted into a grey-scale image, and the grey-scale image is normalized, so that the data complexity is reduced, the texture is highlighted, and the detection accuracy is improved. Subsequent analysis is facilitated; texture features are effectively extracted, subtle changes are quantitatively presented, lesions are accurately recognized, abnormity is scientifically judged and displayed according to threshold values, and automatic and standardized detection is achieved. Meanwhile, physiological indexes are introduced, multi-dimensional data are integrated, and the digestive tract function is comprehensively reflected; the indexes are finely processed, individual and dynamic changes are considered, and abnormal fluctuations are captured to early warn diseases; abnormalities are accurately detected, images and index results are cooperatively displayed, and medical care is helped to comprehensively judge. Omnibearing deep detection is achieved, early screening accuracy is improved, comprehensive diagnosis is efficient, clinical applicability is wide, and diagnosis and treatment intelligentization and precision are promoted.

Description

Technical Field

[0001] This invention relates to the field of digestive tract detection technology, and more specifically to a digestive tract detection system based on artificial intelligence. Background Technology

[0002] With the improvement of people's living standards and changes in dietary structure, the incidence of digestive tract diseases has been rising year by year, posing a serious threat to human health. Traditional digestive tract examination methods mainly rely on doctors' experience and visual observation of endoscopic images. At the same time, the monitoring of physiological indicators is also relatively fragmented and lacks systematic integration, which has gradually exposed many limitations in dealing with increasingly complex digestive health problems.

[0003] In gastrointestinal endoscopy, endoscopic images contain a wealth of information about the morphology, color, and texture of the digestive tract mucosa, serving as crucial evidence for diagnosing gastrointestinal lesions. However, raw endoscopic images are large in volume and complex in information, and their quality varies greatly due to factors such as lighting conditions and the imaging characteristics of endoscopic equipment. This poses a significant challenge to physicians in accurately identifying lesion features. Prolonged observation of the endoscopic screen can easily lead to visual fatigue, potentially causing physicians to miss subtle yet crucial signs of disease, resulting in diagnostic delays.

[0004] For monitoring digestive tract physiological indicators, such as gastric acid concentration and intestinal motility frequency, these indicators are closely related to the normal function of the digestive tract and the occurrence and development of diseases. Previous detection methods often measured these physiological indicators in isolation at specific time periods, making it difficult to capture their dynamic changes over time. Furthermore, there are differences in baseline physiological states among individuals, and relying solely on fixed normal ranges to determine abnormalities lacks precision and cannot meet the need for early and accurate diagnosis of digestive tract diseases. Summary of the Invention

[0005] The purpose of this invention is to provide an artificial intelligence-based digestive tract detection system, which solves the technical problems mentioned in the background art.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] An artificial intelligence-based digestive tract detection system includes:

[0008] The data acquisition unit is used to acquire key data related to the digestive tract, including but not limited to: endoscopic image data and physiological indicator data of the digestive tract;

[0009] The preprocessing unit is used to preprocess key data;

[0010] The feature extraction unit is used to perform feature extraction processing on key data and extract endoscopic image texture features and digestive tract physiological indicators.

[0011] The abnormality detection unit is used to perform digestive tract abnormality monitoring and analysis based on the results obtained by the feature extraction unit, and to determine whether the endoscopic images are abnormal and whether the physiological indicators are abnormal based on the analysis results, and to generate corresponding digestive tract abnormality signals from the abnormal results.

[0012] The results display unit is used to show the corresponding gastrointestinal abnormality signals obtained by the abnormality detection unit to relevant personnel.

[0013] As a further aspect of the present invention, the preprocessing method is as follows:

[0014] Step Y1: Endoscopic image data preprocessing:

[0015] Step Y1.1: Convert each endoscopic image into a grayscale image, as follows:

[0016] Select an endoscopic image;

[0017] Obtain the RGB values ​​of each pixel in the endoscopic image and record them as RGB. k ={R k G k B k} values, k = 1, 2, ... v, v represents the total number of pixels in the endoscopic image, R k G represents the value of the R channel at the k-th pixel. k B represents the value of the G channel at the k-th pixel. k This represents the value of the B channel at the k-th pixel;

[0018] Subsequently passed: H k =0.299×R k +0.587×G k +0.114×B k ;

[0019] Calculate the gray value H of the k-th pixel in the endoscopic image. k ;

[0020] Step Y1.2: Select an endoscopic image and extract the maximum and minimum grayscale values ​​from each pixel in the image, and label them as H respectively. max and H min ;

[0021] Subsequently passed:

[0022] Calculate the normalized gray value H1 at each pixel.k ;

[0023] Step Y2, Preprocessing of physiological index data:

[0024] Step Y2.1: Select a physiological indicator;

[0025] The physiological index data is labeled as P. r r = 1, 2, ..., t, where t is the number of times each physiological indicator value is collected at multiple collection time points within a specified period;

[0026] Step Y2.2, followed by: Calculate the average value (PP) of this physiological indicator data;

[0027] Simultaneously through: Calculate the standard deviation (BP) of this physiological indicator data;

[0028] Step Y2.3: Set the voltage value P r By combining PP and BP, the physiological index P was analyzed. r Outliers in;

[0029] Specifically: If P r -PP>3×BP, then the corresponding physiological index data P r Mark as an outlier;

[0030] Step Y2.4: Extract the maximum and minimum values ​​of the physiological indicator from this type of physiological indicator data, and label them as P. max and P min ;

[0031] Step Y2.5, Pass: Calculate the normalized value P1 of the corresponding physiological indicator value in this type of physiological indicator data. r .

[0032] As a further aspect of the present invention, the method for extracting texture features from endoscopic images is as follows:

[0033] Step T1.1: Take each pixel in the endoscopic image as the center pixel, and at the same time obtain the pixels surrounding the center pixel and adjacent to the center pixel as the neighboring pixels. Then, form a pixel domain based on the center pixel and the neighboring pixels.

[0034] Step T1.2: Within a pixel domain, obtain the grayscale value of the center pixel and the grayscale values ​​of the neighboring pixels, and label them as H0 respectively. k and HL k，u u = 0, 1, 2, ..., c-1, where c represents the number of neighboring pixels;

[0035] Step T1.3, Pass:

[0036] Calculate the binary mode value LBP for this pixel domain. k ;

[0037] Among them, 2 u These are weighting coefficients used to convert binary numbers into decimal numbers to represent binary pattern values;

[0038] Step T1.4: Extract all binary pattern values ​​(LBP) from all pixel domains in the endoscopic image. k ;

[0039] Subsequently, based on the frequency of occurrence of different binary pattern values, the LBP histogram of the endoscopic image was obtained and labeled as Z = [z0, z1, ..., z]. w-1 ], where w is the number of different binary pattern values;

[0040] Then proceed as follows:

[0041] Calculate the average LBP value ZP of the endoscopic image;

[0042] In the formula, d = 0, 1, 2, ..., w-1, where d represents the binary pattern value, and z d This represents the number of pixels with a value of d in binary mode.

[0043] Simultaneously through:

[0044] The dispersion value ZB of LBP in the endoscopic image was calculated.

[0045] As a further aspect of the present invention, the method for extracting digestive tract physiological indicator features is as follows:

[0046] Step T2.1: Select a physiological indicator and extract the physiological indicator P collected at two adjacent collection time points. r and P r-1 ;

[0047] Step T2.2, Pass:

[0048] Calculate the corresponding physiological indicator change rate E r .

[0049] As a further aspect of the present invention, the physiological indicators include gastric acid concentration and intestinal peristalsis frequency.

[0050] As a further aspect of the present invention, the anomaly monitoring and analysis method is as follows:

[0051] Step J1, Detection of endoscopic image anomalies:

[0052] Step J1.1: Extract the pre-set LBP mean threshold ZPy and LBP dispersion threshold ZBy;

[0053] Step J1.2: Simultaneously extract the allowable deviation value ZPc of the pre-set LBP mean threshold and the allowable deviation value ZBc of the LBP dispersion threshold;

[0054] Step J1.3: Next, compare the results between |ZP-ZPy| and ZPc, and between |ZB-ZBy| and ZBc, to determine whether the endoscopic image is abnormal.

[0055] If both |ZP-ZPy|>ZPc and |ZB-ZBy|>ZBc are true, then the endoscopic image is determined to be abnormal, and a digestive tract abnormality signal 1 is generated accordingly; otherwise, a digestive tract abnormality signal 1 is not generated.

[0056] Step J2, Detection of abnormal physiological indicators:

[0057] Step J2.1: Extract the rate of change threshold Ey pre-set based on the corresponding physiological indicators;

[0058] Step J2.2: Simultaneously extract the allowable deviation value Ec of the pre-set rate of change threshold;

[0059] Step J2.3, then |E r The comparison between -Ey| and Ec determines whether physiological indicators are abnormal.

[0060] If |E r If -Ey|>Ec is true, then the relevant physiological indicators are determined to be abnormal, and a second abnormal signal for the digestive tract is generated accordingly; otherwise, a second abnormal signal for the digestive tract is not generated.

[0061] The beneficial effects of this invention are:

[0062] This invention can acquire key data including endoscopic images of the digestive tract and physiological indicators such as gastric acid concentration and intestinal motility frequency. For different types of data, such as endoscopic images and physiological indicators, corresponding preprocessing procedures are set up to ensure the data is more standardized and accurate before entering subsequent analysis stages, thus improving the reliability and precision of the entire detection system. For example, endoscopic images are preprocessed by converting them to grayscale and normalizing them; physiological indicators are processed by calculating the average value, standard deviation, analyzing outliers, and normalizing, which can better remove interfering factors from the original data and highlight effective features.

[0063] This invention constructs a pixel domain, calculates binary pattern values ​​based on the center pixel and neighboring pixels, and then obtains an LBP histogram. Furthermore, it calculates the average LBP value and the dispersion value. This method can extract the texture features of endoscopic images in a more detailed and quantitative way, providing a strong basis for accurately judging whether endoscopic images are abnormal and helping to accurately detect abnormalities such as possible lesions in endoscopic images.

[0064] This invention, by calculating the rate of change of physiological indicators at adjacent collection time points, can capture the dynamic changes of physiological indicators over time. This is of great importance for understanding the stability of digestive tract physiological functions and timely detecting potential physiological abnormalities, and facilitates subsequent judgment on whether the corresponding physiological indicators are abnormal based on the rate of change.

[0065] This invention establishes corresponding abnormality detection mechanisms for endoscopic images and physiological indicators. Based on the extracted features, such as the average LBP value and dispersion value of endoscopic images, and the rate of change of physiological indicators, they are compared with pre-set thresholds and their allowable deviation values. This enables a more scientific and rigorous determination of whether endoscopic images and physiological indicators are abnormal, thereby accurately generating corresponding gastrointestinal abnormality signals and achieving effective monitoring of gastrointestinal abnormalities. This helps to detect related problems such as gastrointestinal diseases as early as possible.

[0066] This invention includes a result display unit that can visually display the abnormal signals of the digestive tract obtained by the abnormality detection unit to relevant personnel, so that relevant medical staff, researchers and others can know the test results in a timely manner, and then make further diagnostic, treatment or research decisions based on the abnormality.

[0067] In summary, this digestive tract detection system, through the coordinated operation of multiple components, helps to improve the comprehensiveness and accuracy of digestive tract detection, as well as the ability to warn of abnormalities, and has positive significance for the early detection and diagnosis of digestive tract-related diseases. Attached Figure Description

[0068] The invention will now be further described with reference to the accompanying drawings.

[0069] Figure 1 This is a system block diagram of a digestive tract detection system based on artificial intelligence according to the present invention. Detailed Implementation

[0070] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0071] Example 1

[0072] Please see Figure 1 As shown, the present invention is a digestive tract detection system based on artificial intelligence, comprising:

[0073] The data acquisition unit is used to acquire key data related to the digestive tract, including endoscopic image data of the digestive tract.

[0074] The preprocessing unit is used to preprocess the endoscopic image data. The preprocessing method is as follows:

[0075] Step Y1.1: Convert each endoscopic image into a grayscale image, as follows:

[0076] Select an endoscopic image;

[0077] Obtain the RGB values ​​of each pixel in the endoscopic image and record them as RGB. k ={R k G k B k} values, k = 1, 2, ... v, v represents the total number of pixels in the endoscopic image, R k G represents the value of the R channel at the k-th pixel. k B represents the value of the G channel at the k-th pixel. k This represents the value of the B channel at the k-th pixel;

[0078] Subsequently passed: H k =0.299×R k +0.587×G k +0.114×B k ;

[0079] Calculate the gray value H of the k-th pixel in the endoscopic image. k ;

[0080] Step Y1.2: Select an endoscopic image and extract the maximum and minimum grayscale values ​​from each pixel in the image, and label them as H respectively. max and H min ;

[0081] Subsequently passed:

[0082] Calculate the normalized gray value H1 at each pixel. k ;

[0083] The feature extraction unit is used to perform feature extraction processing on key data. The feature extraction process involves extracting texture features from endoscopic images.

[0084] Step T1.1: Take each pixel in the endoscopic image as the center pixel, and at the same time obtain the pixels surrounding the center pixel and adjacent to the center pixel as the neighboring pixels. Then, form a pixel domain based on the center pixel and the neighboring pixels.

[0085] Step T1.2: Within a pixel domain, obtain the grayscale value of the center pixel and the grayscale values ​​of the neighboring pixels, and label them as H0 respectively. k and HL k，u u = 0, 1, 2, ..., c-1, where c represents the number of neighboring pixels;

[0086] Step T1.3, Pass:

[0087] Calculate the binary mode value LBP for this pixel domain. k ;

[0088] In this embodiment, 2 u These are weighting coefficients used to convert binary numbers into decimal numbers to represent binary pattern values;

[0089] Step T1.4: Extract all binary pattern values ​​(LBP) from all pixel domains in the endoscopic image. k ;

[0090] Subsequently, based on the frequency of occurrence of different binary pattern values, the LBP histogram of the endoscopic image was obtained and labeled as Z = [z0, z1, ..., z]. w-1 ], where w is the number of different binary pattern values;

[0091] Then proceed as follows:

[0092] Calculate the average LBP value ZP of the endoscopic image;

[0093] In the formula, d = 0, 1, 2, ..., w-1, where d represents the binary pattern value, and z d This represents the number of pixels with a value of d in binary mode.

[0094] Simultaneously through:

[0095] Calculate the dispersion value ZB of LBP in the endoscopic image;

[0096] The anomaly detection unit is used to perform gastrointestinal anomaly monitoring and analysis based on the results obtained from the feature extraction unit. The anomaly monitoring and analysis involves detecting anomalies in endoscopic images, and the method is as follows:

[0097] Step J1.1: Extract the pre-set LBP mean threshold ZPy and LBP dispersion threshold ZBy;

[0098] Step J1.2: Simultaneously extract the allowable deviation value ZPc of the pre-set LBP mean threshold and the allowable deviation value ZBc of the LBP dispersion threshold;

[0099] Step J1.3: Next, compare the results between |ZP-ZPy| and ZPc, and between |ZB-ZBy| and ZBc, to determine whether the endoscopic image is abnormal.

[0100] If both |ZP-ZPy|>ZPc and |ZB-ZBy|>ZBc are true, then the endoscopic image is determined to be abnormal, and a digestive tract abnormality signal is generated accordingly.

[0101] The results display unit is used to show the abnormal signals of the digestive tract obtained by the abnormality detection unit to relevant personnel.

[0102] This embodiment converts endoscopic images into grayscale images, accurately calculates the grayscale value of each pixel using a specific formula, and then normalizes the grayscale values. This series of operations effectively reduces the complexity of image data, removes interference caused by redundant color information, and highlights the texture and structural features of the image. This allows subsequent feature extraction and analysis to focus on more critical image information, laying the foundation for accurate detection of endoscopic image abnormalities. A pixel domain is constructed with each pixel as the core, cleverly combining the grayscale values ​​of the central pixel and neighboring pixels to calculate the binary pattern value, thereby statistically generating the LBP histogram and deriving the average LBP value and dispersion value. This method can deeply mine the texture features of endoscopic images, quantifying and presenting subtle and complex texture changes in the image. This gives the system a stronger ability to identify lesion features in endoscopic images, greatly improving the accuracy of endoscopic image abnormality detection and enabling more timely detection of potential gastrointestinal mucosal lesions, such as early polyps and ulcers. Based on pre-set LBP mean threshold, dispersion threshold, and allowable deviation values ​​that have been validated by extensive experimental and clinical data, the system rigorously determines whether endoscopic images are abnormal and generates a digestive tract abnormality signal to display to relevant personnel. This process automates and standardizes the detection process, avoiding missed diagnoses caused by subjectivity in human observation and visual fatigue, ensuring that abnormalities are detected immediately, and providing crucial information for subsequent diagnostic and treatment decisions.

[0103] Example 2

[0104] Please see Figure 1 As shown, as a second embodiment of the present invention, in specific implementation, the technical solution of this embodiment differs from that of embodiment one only in that, in this embodiment...

[0105] Key data also include physiological indicators of the digestive tract;

[0106] The preprocessing unit is also used to preprocess physiological index data. The preprocessing method is as follows:

[0107] Step Y2.1: Select a physiological indicator;

[0108] In this embodiment, the types of physiological indicators include gastric acid concentration and intestinal peristalsis frequency;

[0109] The physiological index data is labeled as P. r r = 1, 2, ..., t, where t is the number of times each physiological indicator value is collected at multiple collection time points within a specified period;

[0110] Step Y2.2, followed by: Calculate the average value (PP) of this physiological indicator data;

[0111] Simultaneously through: Calculate the standard deviation (BP) of this physiological indicator data;

[0112] Step Y2.3: Set the voltage value P r By combining PP and BP, the physiological index P was analyzed. r Outliers in;

[0113] Specifically: If P r -PP>3×BP, then the corresponding physiological index data P r Mark as an outlier;

[0114] Step Y2.4: Extract the maximum and minimum values ​​of the physiological indicator from this type of physiological indicator data, and label them as P. max and P min ;

[0115] Step Y2.5, Pass: Calculate the normalized value P1 of the corresponding physiological indicator value in this type of physiological indicator data. r ;

[0116] Feature extraction processing also includes extracting physiological indicator features:

[0117] Step T2.1: Select a physiological indicator and extract the physiological indicator P collected at two adjacent collection time points. r and P r-1 ;

[0118] Step T2.2, Pass:

[0119] Calculate the corresponding physiological indicator change rate E r ;

[0120] Anomaly monitoring and analysis involves detecting anomalies in physiological indicators, and the methods are as follows:

[0121] Step J2.1: Extract the rate of change threshold Ey pre-set based on the corresponding physiological indicators;

[0122] Step J2.2: Simultaneously extract the allowable deviation value Ec of the pre-set rate of change threshold;

[0123] Step J2.3, then |E r The comparison between -Ey| and Ec determines whether physiological indicators are abnormal.

[0124] If |E r If -Ey|>Ec is true, then the relevant physiological indicators are determined to be abnormal, and a second abnormal signal for the digestive tract is generated.

[0125] The results display unit is also used to show the abnormal signals of the digestive tract obtained by the abnormality detection unit to relevant personnel.

[0126] This embodiment, building upon the endoscopic image data detection of Embodiment 1, introduces physiological indicators of the digestive tract, such as gastric acid concentration and intestinal peristalsis frequency. It achieves multi-dimensional detection, combining images and physiological indicators, moving beyond a single image dimension. This makes the assessment of digestive health more comprehensive and three-dimensional, reflecting the functional state of the digestive tract more holistically and avoiding the omission of functional disorders or early disease signs due to reliance solely on endoscopic images. The physiological indicator data undergoes systematic preprocessing, including calculating the mean and standard deviation, accurately identifying outliers, and normalization. These operations fully consider the individual differences in physiological indicators and their dynamic changes over time, making subsequent feature extraction and anomaly detection based on the rate of change more scientific and reliable. This allows for the accurate capture of subtle abnormal fluctuations in physiological indicators, providing early warnings of potential digestive disease risks, such as gastritis caused by abnormal gastric acid secretion or pre-obstruction symptoms suggested by abnormal intestinal peristalsis. By calculating the rate of change of physiological indicators at adjacent acquisition time points and comparing it with preset thresholds and allowable deviations, it accurately determines whether the physiological indicators are abnormal, generating a second digestive tract abnormality signal. The results display unit shows both signal one and signal two, achieving a collaborative presentation of image and physiological indicator detection results. This allows medical staff to obtain comprehensive information at once, quickly and comprehensively assess the patient's digestive tract condition, and formulate precise treatment plans.

[0127] Example 3

[0128] Please see Figure 1 As shown, as a third embodiment of the present invention, in specific implementation, compared with embodiments one and two, the technical solution of this embodiment is to combine the solutions of embodiments one and two.

[0129] This embodiment organically combines the solutions of Embodiment 1 and Embodiment 2, possessing both the high-precision endoscopic image anomaly detection capability of Embodiment 1 and the comprehensive physiological indicator monitoring function of Embodiment 2. This enables comprehensive and in-depth detection of the digestive tract, from its morphological structure to its physiological function. Whether it's a tiny lesion on the surface of the digestive tract mucosa or a potential abnormality in internal physiological function, the system can accurately capture it, greatly improving the accuracy and comprehensiveness of early screening for digestive tract diseases. By integrating endoscopic image texture feature analysis with dynamic monitoring of multiple physiological indicators, it provides doctors with richer and more valuable diagnostic evidence. Different types of data corroborate and complement each other, making the diagnosis of complex digestive tract diseases more accurate and efficient, reducing the probability of misdiagnosis and missed diagnosis. Especially when facing some atypical symptoms and complex etiologies of digestive tract diseases, it can quickly pinpoint the root cause of the problem, securing the best treatment opportunity for patients. This embodiment combines the strengths of the previous two embodiments and is applicable to various clinical scenarios with different needs. Whether it's initial screening of the digestive tract during routine physical examinations or in-depth examinations for patients with digestive tract discomfort symptoms, it can leverage its advantages to meet diverse medical testing needs and promote the intelligent and precise diagnosis and treatment of digestive tract diseases.

[0130] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0131] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A digestive tract detection system based on artificial intelligence, characterized in that, include: The data acquisition unit is used to acquire key data related to the digestive tract, including but not limited to: endoscopic image data and physiological indicator data of the digestive tract; The preprocessing unit is used to preprocess key data; The feature extraction unit is used to perform feature extraction processing on the preprocessed key data and extract the texture features of the endoscopic image and the physiological indicators of the digestive tract. The abnormality detection unit is used to perform digestive tract abnormality monitoring and analysis based on the results obtained by the feature extraction unit, and to determine whether the endoscopic images are abnormal and whether the physiological indicators are abnormal based on the analysis results, and to generate corresponding digestive tract abnormality signals from the abnormal results. The results display unit is used to show the corresponding gastrointestinal abnormality signals obtained by the abnormality detection unit to relevant personnel.

2. The digestive tract detection system based on artificial intelligence according to claim 1, characterized in that, Endoscopic image data preprocessing is performed as follows: Step Y1.1: Convert each endoscopic image into a grayscale image, as follows: Select an endoscopic image; Obtain the RGB values ​​of each pixel in the endoscopic image and record them as RGB. k ={R k G k B k } values, k = 1, 2, ... v, v represents the total number of pixels in the endoscopic image, R k G represents the value of the R channel at the k-th pixel. k B represents the value of the G channel at the k-th pixel. k This represents the value of the B channel at the k-th pixel; Subsequently passed: H k =0.299×R k +0.587×G k +0.114×B k ; Calculate the gray value H of the k-th pixel in the endoscopic image. k ; Step Y1.2: Select an endoscopic image and extract the maximum and minimum grayscale values ​​from each pixel in the image, and label them as H respectively. max and H min ; Subsequently passed: Calculate the normalized gray value H1 at each pixel. k .

3. The digestive tract detection system based on artificial intelligence according to claim 1, characterized in that, The preprocessing of physiological indicator data is performed as follows: Step Y2.1: Select a physiological indicator; The physiological index data is labeled as P. r r = 1, 2, ..., t, where t is the number of times each physiological indicator value is collected at multiple collection time points within a specified period; Step Y2.2, followed by: Calculate the average value (PP) of this physiological indicator data; Simultaneously through: Calculate the standard deviation (BP) of this physiological indicator data; Step Y2.3: Set the voltage value P r By combining PP and BP, the physiological index P was analyzed. r Outliers in; Step Y2.4: Extract the maximum and minimum values ​​of the physiological indicator from this type of physiological indicator data, and label them as P. max and P min ; Step Y2.5, Pass: Calculate the normalized value P1 of the corresponding physiological indicator value in this type of physiological indicator data. r .

4. The digestive tract detection system based on artificial intelligence according to claim 3, characterized in that, In step Y2.3, if P r -PP>3×BP, then the corresponding physiological index data P r Mark as an outlier.

5. The digestive tract detection system based on artificial intelligence according to claim 2, characterized in that, The method for extracting texture features from endoscopic images is as follows: Step T1.1: Take each pixel in the endoscopic image as the center pixel, and at the same time obtain the pixels surrounding the center pixel and adjacent to the center pixel as the neighboring pixels. Then, form a pixel domain based on the center pixel and the neighboring pixels. Step T1.2: Within a pixel domain, obtain the grayscale value of the center pixel and the grayscale values ​​of the neighboring pixels, and label them as H0 respectively. k and HL k，u u = 0, 1, 2, ..., c-1, where c represents the number of neighboring pixels; Step T1.3, Pass: Calculate the binary mode value LBP for this pixel domain. k ; Among them, 2 u These are weighting coefficients used to convert binary numbers into decimal numbers to represent binary pattern values; Step T1.4: Extract all binary pattern values ​​(LBP) from all pixel domains in the endoscopic image. k ; Subsequently, based on the frequency of occurrence of different binary pattern values, the LBP histogram of the endoscopic image was obtained and labeled as Z = [z0, z1, ..., z]. w-1 ], where w is the number of different binary pattern values; Then proceed as follows: Calculate the average LBP value ZP of the endoscopic image; In the formula, d = 0, 1, 2, ..., w-1, where d represents the binary pattern value, and z d This represents the number of pixels with a value of d in binary mode. Simultaneously through: The dispersion value ZB of LBP in the endoscopic image was calculated.

6. The digestive tract detection system based on artificial intelligence according to claim 1, characterized in that, The methods for extracting features of digestive tract physiological indicators are as follows: Step T2.1: Select a physiological indicator and extract the physiological indicator P collected at two adjacent collection time points. r and P r-1 ; Step T2.2, Pass: Calculate the corresponding physiological indicator change rate E r .

7. The digestive tract detection system based on artificial intelligence according to claim 5, characterized in that, The method for detecting and analyzing abnormalities in endoscopic images is as follows: Step J1.1: Extract the pre-set LBP mean threshold ZPy and LBP dispersion threshold ZBy; Step J1.2: Simultaneously extract the allowable deviation value ZPc of the pre-set LBP mean threshold and the allowable deviation value ZBc of the LBP dispersion threshold; Step J1.3: Next, compare the results between |ZP-ZPy| and ZPc, and between |ZB-ZBy| and ZBc, to determine whether the endoscopic image is abnormal.

8. The digestive tract detection system based on artificial intelligence according to claim 7, characterized in that, In step J1.3, if both |ZP-ZPy|>ZPc and |ZB-ZBy|>ZBc are true, then the endoscopic image is determined to be abnormal, and a digestive tract abnormality signal 1 is generated accordingly; otherwise, a digestive tract abnormality signal 1 is not generated.

9. The digestive tract detection system based on artificial intelligence according to claim 6, characterized in that, The method for detecting and analyzing abnormal physiological indicators is as follows: Step J2.1: Extract the rate of change threshold Ey pre-set based on the corresponding physiological indicators; Step J2.2: Simultaneously extract the allowable deviation value Ec of the pre-set rate of change threshold; Step J2.3, then |E r The comparison between -Ey| and Ec determines whether physiological indicators are abnormal.

10. A digestive tract detection system based on artificial intelligence according to claim 9, characterized in that, In step J2.3, if |E r If -Ey|>Ec is true, then the relevant physiological indicators are determined to be abnormal, and a second abnormal signal for the digestive tract is generated accordingly; otherwise, a second abnormal signal for the digestive tract is not generated.

Images