21 results about "Colonoscopy" patented technology

The invention belongs to the technical field of image detection, and discloses an enteroscopy auxiliary diagnosis method and system based on artificial intelligence, and the method comprises the steps: obtaining enteroscopy image data in an enteroscopy process, and synchronously extracting corresponding auxiliary collection information from the enteroscopy image data; caching the enteroscope image data and the auxiliary acquisition information frame by frame and keeping timestamps aligned; performing standardized correction and adaptive enhancement processing on the enteroscope image data after timestamp alignment; a self-adaptive gamma dynamic enhancement mechanism is introduced, and intestinal tract wrinkles are reserved to obtain an enhanced image; lesion positioning and category screening are conducted on the enhanced image through the target detection model, multi-scale feature aggregation and time sequence consistency constraint are conducted in combination with auxiliary collection information, and lesion candidate areas are generated; performing morphological, texture and boundary structure analysis on the lesion candidate region, and extracting lesion morphological features; and the efficiency and the reliability of enteroscopy diagnosis can be improved.

1. Name of the product in this design: Patient pants for colonoscopy. 2. Purpose of this design: To be worn by patients during colonoscopy. 3. The key point of the design of this product lies in its shape. 4. The image or photograph that best illustrates the design's key points: a 3D model. 5. The bottom surface of this product is a part that is not easily seen or cannot be seen during use, so the bottom view is omitted.

1. Name of the product in this design: Disposable colonoscopy pants. 2. Purpose of this design: To be worn during colonoscopy. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The application discloses a method for predicting biological age based on enteroscopy pictures, and belongs to the field of digestive endoscopy image analysis. The method first screens enteroscopy pictures without abnormalities, and completes quality control and edge cutting; then constructs an image package with multiple pictures in a single report, extracts features and weighted aggregation by using a multi-instance learning model based on attention; and converts age prediction into a classification task and introduces a Gaussian soft label to realize high-precision biological age prediction. The application can mine aging-related features from enteroscopy images without obvious abnormalities, does not need additional equipment and invasive operation, has strong generalization, and can be used for risk stratification of enteroscopy-negative people and precise prevention and treatment of colorectal cancer.

The invention discloses a method for assisting in improving Boston scoring precision of AI calculation by using enteroscope retreating speed, and belongs to the crossing field of enteroscopy and artificial intelligence technology. The method mainly comprises the following steps: in an enteroscope retreating stage, starting an AI calculation Boston scoring module and a retreating speed calculation module on the basis of a preset condition, synchronously obtaining scores and retreating speeds, and storing the scores and the retreating speeds in sequence; accumulating the mirror retreating speed to generate a coordinate sequence, and determining the length of the intestinal tract after sorting; dividing the intestinal tract into a plurality of sections and distributing corresponding coordinate sequences; and calculating the average cleanliness of each segment by adopting an integral algorithm in combination with the coordinate difference values in the segments and the corresponding scores, and summarizing to obtain a final score. According to the method, the problem of score weight imbalance caused by regional residence time difference in the prior art is solved, the Boston score accuracy and reliability are improved, the method is adaptive to the intestinal individual difference of patients, and reliable support is provided for intestinal lesion investigation and clinical diagnosis and treatment.

The invention discloses an enteroscopy rectum protection device, and relates to the technical field of medical examination, the enteroscopy rectum protection device comprises a fixing support, and further comprises a smearing assembly, a speed adjusting assembly and a pressurizing assembly, by arranging the smearing assembly, a lubricating agent can be evenly smeared on an enteroscopy body, when the lubricating agent is not evenly smeared, supplementary smearing can be conducted, and the lubricating quality is guaranteed; by arranging the speed adjusting assembly, the use amount of the lubricant can be automatically selected according to actual requirements when the lubricant is smeared, it is guaranteed that observation of a doctor on the illness state is not affected under the condition that the lubricant achieves the lubricating effect, and the use amount of the lubricant is saved; by arranging the two different driving motors, the two different driving motors can be used in a matched mode according to actual requirements, the spraying speed of the lubricating agent is controlled, the spraying or supplementary coating function of the lubricating agent is selected according to the requirements under the condition of independent use, and the use modes are diversified.

The invention relates to the technical field of brain-computer interfaces, in particular to a brain-controlled enteroscope operating system based on mixed reality. According to the system, an endoscope real-time image is obtained through a head-mounted display visual induction module, and a visual stimulation signal is generated on a display interface based on a preset visual induction stimulation normal form. An electroencephalogram signal generated by the target object for the visual stimulation signal is acquired through an electroencephalogram signal acquisition module, and operation intention information of the target object is determined based on the electroencephalogram signal through an electroencephalogram signal analysis module. The main control module is used for generating the corresponding enteroscope control instruction based on the operation intention information, and the enteroscope auxiliary manipulator module is used for executing the corresponding enteroscope control operation based on the enteroscope control instruction, so that the accuracy and the safety of the enteroscope operation are improved.

The utility model discloses a portable rectal cancer enteroscopy auxiliary device, which belongs to the field of medical instruments and comprises a back supporting plate, two connecting rods are rotatably connected to one side of the back supporting plate, a reinforcing rod is fixedly connected between the two connecting rods, two ends of the reinforcing rod are rotatably connected with supporting rods, and the supporting rods are fixedly connected with the back supporting plate. According to the auxiliary device, in non-painless enteroscopy, a patient is prone to moving due to intestinal tract stimulation and discomfort, examination is disturbed, and pain is aggravated, when the auxiliary device is used, the patient places the thigh supporting plate below the thigh, the soft anti-skid face of the thigh supporting plate is attached to the leg, then the back leans against the back supporting plate, and the thigh supporting plate is fixed to the back supporting plate. The length of the first magic tape and the second magic tape is adjusted according to the stature, the body and the thighs are fixed by means of viscidity, safety is guaranteed, shaking is prevented, finally, a medical worker pushes a limiting block to be clamped into a limiting hole, the posture is locked, the patient is prevented from greatly moving due to discomfort, and it is ensured that examination is conducted smoothly.

The application discloses a marker group for intestinal cancer screening and diagnosis and application thereof, and belongs to the field of molecular biological technology. The marker group comprises at least four polypeptides shown in sequences SEQ ID NO. 1-35. The marker group constructed by the application has more excellent sensitivity and specificity when used for auxiliary diagnosis and early screening of intestinal cancer. The selected discrimination peak set (marker group) is superior to the FIT home screening kit (sensitivity and specificity are 73.8% and 94.9% respectively) recommended for NHS (the British National Health Service) at present, the detection kit based on lncRNA (sensitivity and specificity are 82.9% and 72.9% respectively), and the CT colonoscopy technology (sensitivity and specificity are 84% and 85% respectively).

This invention discloses a forward traction-assisted colonoscopy advancement robot, comprising a colonoscopy body, which includes an endoscope tip, an endoscope bend, and an endoscope insertion part connected in sequence. It also includes: a continuous external sheath system sleeved on the outside of the endoscope bend; a traction drive system for traction of the continuous external sheath system forward; and a colonoscopy fixation system for fixing or releasing the endoscope insertion part. The continuous external sheath system includes a slider pair and a continuous external sheath. The slider pair includes an inner slider and an outer slider that slide against each other. The inner slider is fixedly connected to the endoscope tip; the outer slider is fixedly connected to the front end of the continuous external sheath; and the inner and outer sliders slide relative to each other under the drive of the traction drive system. This invention achieves a forward-driven endoscope advancement method, solving the problem of endoscope knotting in existing colonoscopy advancement methods and reducing pain for the patient during examination.

1. Name of the product in this design: Integrated Light Source Heat Dissipation Unit (Coronoscopy Examination). 2. Purpose of this design: Equipment for medical light source therapy. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The invention relates to the field of medical instrument teaching and training, in particular to a simulated enteroscopy and operation control method and system, which are used for generating a virtual image about an enteroscopy in a simulated intestinal tract and providing real-time visual feedback when a user operates the enteroscopy to examine the simulated intestinal tract; predicting the movement trend of the enteroscope according to the operation characteristics of the user on the enteroscope, and providing an enteroscope operation prompt; and according to the air pressure adjustment operation parameters of the simulated intestinal tract, predicting the air pressure change trend in the simulated intestinal tract, and providing an air pressure adjustment operation early warning prompt. According to the method, visual image navigation guidance can be provided for the user in real time in the simulated enteroscopy training period, prompting can be accurately carried out according to the actual operation condition of the user, the user can obtain all-around information interaction in the training period, it is ensured that the user obtains accurate and timely reminding feedback in the simulated training period, and the training effectiveness is improved.

A method for detecting colonoscopy lesions based on texture perception and fine-grained feature compensation is proposed. The acquired colonoscopy images are input into a backbone network to extract multi-level features. Texture features are mined from feature C2 and compared with feature C... m Semantic feature integration in C m Background information is suppressed, fine-grained texture features are captured and enhanced; features C3 to C m Each feature is convolved separately, and then fused with the enhanced features to obtain m-2 fused features; feature C is then... m Features are obtained through attention mechanisms and spatial pyramid pooling; the obtained features are fused in a multi-scale manner from top to bottom and from bottom to top, and a pyramid-decomposable attention module is introduced in at least one of the fusion processes to balance the channel information in the skip links and capture the interaction between channels. Based on the multi-scale fusion results, high-precision target detection is achieved.

The utility model relates to enteroscope training model technical field, specifically for a kind of simulation enteroscope training simulation structure, including hollow outer frame, lower digestive tract model is provided with in outer frame by fixed structure;Lower digestive tract model includes successively connected large intestine model and small intestine model, the end of large intestine model is connected with outer frame by simulation anus;The lower digestive tract model of the utility model is made based on real human CT scanning data reconstruction model, and cooperate with the fixed structure of real human pelvic bone and ligament tissue composition, can highly simulate human lower digestive tract structure and enteroscope operating feeling;By being connected with external power supply, the utility model can realize the conductive function when endoscopic operating instrument, complete operation such as electrocision;The utility model can also set up training module inside lower digestive tract model, to simulate different diseases, greatly expand training range, can be applicable to the demand of different levels of physicians for different kinds of enteroscope training simulation.

The present application belongs to the technical field of medical data processing, and discloses a rectal cancer neoadjuvant therapy efficacy prediction method and system based on multi-modal knowledge decomposition. The present application provides a multi-modal data fusion algorithm based on multi-modal knowledge decomposition, which decomposes multi-modal data into multiple independent modal knowledge, reduces redundant information, and does not lose important inter-modal complementary information. The present application simultaneously uses unsupervised clustering and supervised CNN algorithm. Compared with the traditional method of only using unsupervised random selection or image selection method based on information entropy, the present application can reduce the interference of noise data on picture screening, so as to select representative colonoscopy pictures and CT pictures.

This invention provides an artificial intelligence-based method and system for assessing the integrity of colonoscopy observation. The method includes: dividing a sequence of colonoscopy withdrawal video frames into pixel blocks; extracting multi-scale features from each pixel block of the image frame to obtain local texture, global structure, and global context semantic feature maps; stacking semantic feature maps of the same scale in the temporal dimension of the video frame sequence, and extracting spatial and temporal features from the stacked features at each scale; multiplying the spatial and temporal features at each scale sequentially with the corresponding semantic feature maps to obtain enhanced feature maps; upsampling the enhanced feature maps of the global context semantic feature map and the global structure semantic feature map, and adding them to the enhanced feature map of the local texture semantic feature map; inputting the fused feature map into a multi-task head to output the clear mucosal region mask, the wrinkled region mask, the clarity classification result, and the intestinal segment location recognition result of the image frame; and quantifying and scoring the integrity of colonoscopy observation based on the above recognition results.

The application discloses an intestinal polypus identification method based on images and multi-modal data, comprising the following steps: acquiring a plurality of microscope pathological images, objective magnification information corresponding to the pathological images, and text information corresponding to the colonoscopy; performing data preprocessing on each frame of acquired pathological images and text information to obtain a training data set; constructing a multi-scale multi-modal feature classification network, training the network using the training data set, and obtaining a trained multi-scale multi-modal feature fusion classification network; collecting microscope pathological images of a patient, acquiring corresponding colonoscopy text information, inputting the data after data preprocessing into the multi-scale multi-modal feature fusion classification network, and obtaining a class prediction of the disease by the model. The application fully fuses pathological images and colonoscopy text information, finally realizes accurate classification and prediction of the disease type, improves the effect and efficiency of multi-modal diagnosis of intestinal diseases, and thus improves the accuracy of diagnosis of the patient.

The application provides a memory bank-based intestinal tract video target detection method and system, and belongs to the technical field of computer vision.The system comprises a memory storage module, which is used for performing feature enhancement on a current image frame by using a memory frame in a memory bank in a target detection stage of the current image frame; a memory updating module, which is used for performing feature similarity and importance analysis on image features of the current image frame and image features of the memory frame in the memory bank, and deciding whether to update the memory bank according to an analysis result; and an optical flow memory auxiliary module, which is used for generating an attention feature map by using an optical flow method to track changes of optical flow key points in a video sequence, and performing image enhancement on the current image frame.The application fully explores time sequence information of a colonoscopy video, enhances main target features of the colonoscopy by using continuity of optical flow, eliminates possible interference in the colonoscopy video, realizes feature enhancement, and improves detection precision.

The invention relates to the technical field of medical image processing and intelligent detection, and discloses an enteroscope image ambiguity detection method based on image recognition. The method comprises the following steps: acquiring multiple frames of enteroscopy images with zero-base pixel indexes at fixed time intervals, averaging three channels of colors, normalizing, and linearly stretching and normalizing gray levels; establishing a two-dimensional discrete frequency domain coordinate for each frame and performing discrete Fourier transform; screening out a high-frequency set through an equivalent centering index and a high-frequency radius threshold value based on one fourth of the diagonal length of the image; calculating high-frequency energy, full-frequency energy and proportions thereof; solving a ratio mean value and a standard deviation in a statistical window, and completing clear and fuzzy judgment by a self-adaptive threshold value; establishing two types of frame indexes; obtaining an amplitude spectrum of the fuzzy frame, performing linear stretching, and generating a pseudo-color heat map; and outputting judgment and performing structured archiving.

This utility model relates to a one-way valve device for a water-air tubing in gastroscopy and colonoscopy, comprising a water tank, a sealing tube at the top of the water tank, a uniformly distributed first sealing plate fixedly connected to the left inner end of the sealing tube, and a uniformly distributed second sealing plate fixedly connected to the right inner end of the sealing tube, and an exhaust assembly provided in the sealing tube. This utility model provides a one-way valve device for a water-air tubing in gastroscopy and colonoscopy, which seals the inside of the sealing tube by the cooperation of the opposing first and second sealing plates. When the water-air tubing is not inserted, the first and second sealing plates are pressed together by their own elasticity, forming a seal. When the water-air tubing is inserted, the first and second sealing plates are pushed apart to form a gap, allowing water to drip into the water tank through the gap, thereby effectively controlling residual water in the water-air tubing and allowing only water to enter the water tank, avoiding external contamination.

The utility model provides reusable safety pants for enteroscopy. The reusable safety pants comprise a safety pants body, a square hole is formed in the rear side of the safety pants body, an outer pad is adhered to the rear side face of the safety pants body and located at the position of the square hole, a sanitary pad is adhered to the inner side of the safety pants body and located at the position of the square hole, and extension cloth is arranged on one side of the sanitary pad. The outer pad and the extension cloth are arranged on the inner side of the safety pants, the extension cloth can be spread before a patient is subjected to enteroscopy, so that the safety pants can be prevented from being polluted, after the enteroscopy, the outer pad and the extension cloth are removed, thrown away and replaced with new outer pad and extension cloth, the service life of the safety pants can be prolonged, the safety pants can be repeatedly used, and the safety pants are convenient to use. And resources are saved.