24 results about "Capsule endoscopy" patented technology

The invention discloses an artificial intelligence capsule endoscopy system alimentary canal image splicing method and device, a storage medium and equipment. The method comprises the following steps: respectively cutting each original alimentary canal image shot by an artificial intelligence capsule endoscopy system to obtain a circular alimentary canal image, and forming a circular alimentary canal image set; performing rotation correction processing on images with depth-of-field areas in the circular alimentary canal image set to obtain a corrected alimentary canal image set, the images being in the same shooting view angle after the rotation correction processing; performing linear polar coordinate transformation on each image in the corrected alimentary canal image set and expanding the images into rectangular alimentary canal images to form a rectangular alimentary canal image set; and calculating the axial displacement between every two adjacent rectangular digestive tract images, and splicing the rectangular digestive tract images in sequence based on a weighted splicing fusion algorithm to form a panoramic image of the digestive tract. According to the method, image visual angle deviation caused by lens inclination is reduced, and smooth transition between images is realized.

The invention relates to a cross-modal endoscopic polyp collaborative detection method based on comparative learning, and belongs to the technical field of medical image analysis, and the method comprises the following steps: S1, obtaining a capsule endoscopic image, carrying out the preprocessing, and constructing a training set; s2, constructing a semantic contrast learning cross-modal detection network, and training the semantic contrast learning cross-modal detection network by using a training set; and S3, acquiring a capsule endoscopy image, preprocessing the capsule endoscopy image, inputting the preprocessed capsule endoscopy image into the trained semantic contrast learning cross-modal detection network, and performing target detection on polyps in the image. According to the invention, the workload of film reading is effectively reduced, the risk of missing detection is reduced, and a more reliable and more universal artificial intelligence auxiliary solution is provided for early screening of digestive tract diseases.

The invention discloses a capsule endoscopy gastrointestinal tract position real-time positioning system based on multi-modal sensing, which comprises a shell, a partition plate I is arranged on the rear side in the shell, a mounting plate is arranged between the front wall of the shell and the front end of the partition plate I, and the capsule endoscopy gastrointestinal tract position real-time positioning system further comprises a detection mechanism and an adjusting mechanism; the detection mechanism comprises a PH sensor, a pressure sensor and a temperature sensor, the PH sensor is arranged on the front side of the upper end of the mounting plate, the pressure sensor and the temperature sensor are arranged in the middle and on the rear side of the upper end of the mounting plate respectively, and probes arranged at the upper ends of the PH sensor and the temperature sensor are located outside the shell; according to the capsule endoscopy gastrointestinal tract position real-time positioning system based on multi-modal sensing, four types of data including pH, pressure, temperature and three-axis acceleration can be collected, the specific anatomical position of a capsule endoscopy in the gastrointestinal tract can be conveniently recognized and reported in real time subsequently, an intelligent diagnosis report that what you see is what you know is provided for a doctor, the stability of the view field of a lens is ensured, and the real-time positioning of the gastrointestinal tract position of the capsule endoscopy is achieved. And the number of invalid pictures is reduced.

The present invention relates to a computer-implemented method, capable of automatically detecting clinically relevant colonic pleomorphic lesions and blood or hematic traces in colon capsule endoscopy images, by classifying pixels as colonic pleomorphic lesions or blood or hematic traces, using a convolutional image feature extraction step followed by a classification and indexing step of such findings into a set of one or more classes.

This invention discloses a wired dual-modal imaging capsule endoscopy system, belonging to the field of medical device technology. The system includes a capsule module, a transmission and control module, a dual-modal imaging module, and a signal analysis module. The capsule module is used to achieve 360° circumferential scanning imaging of the esophageal mucosa. The transmission and control module ensures stable transmission of optical and electrical signals and precise control of capsule movement. The dual-modal imaging module integrates an optical coherence tomography submodule and a photoacoustic imaging submodule to acquire tissue morphology information and microvascular distribution information, respectively. The signal analysis module processes the dual-modal signals. This invention achieves three-dimensional high-resolution integrated imaging of the esophageal mucosa without the need for exogenous labeling agents, significantly improving the detection accuracy of early esophageal cancer and precancerous lesions.

This invention relates to an automatic localization method, computer device, and system for ulcer fragments in intestinal capsule endoscopy videos. It establishes an automatic ulcer fragment localization network based on initial temporal boundary specifications, combined with policy gradients and evaluation. The network is trained using query image-reference video pairs. The network is input into the trained network and outputs ulcer fragments in the reference video associated with the query image. A computer device is implemented based on this method. The system uses an input unit to input query image-reference video pairs, a localization unit to execute the method and locate the ulcer fragments, and an output unit to output the results. This invention uses an image of an ulcer lesion of interest from an intestinal capsule endoscopy as the query image and a long intestinal capsule endoscopy video as the reference video. It analyzes the video using reinforcement learning, refines the temporal boundary through sequential decisions using start and end markers, and accurately locates fragments related to the query image, thus completing the video relocalization task.

The application provides a WCE image scene classification method and device based on reinforcement learning and equipment, and relates to the technical field of computer analysis of medical images, and the method comprises the following steps: performing feature extraction on each current image frame in all current capsule endoscopy images to obtain a current image frame feature sequence; inputting all current image frame feature sequences into a preset recurrent neural network model to obtain a first probability prediction result of each current image frame; performing image processing on a secondary classification image frame to obtain a processed image frame, performing image enhancement on the processed image frame according to a target action to obtain an enhanced image frame; inputting the enhanced image frame into the preset recurrent neural network model to obtain a second probability prediction result of each enhanced image frame; and determining a target prediction result according to the first probability prediction result and the second probability prediction result. The application can reduce the reading time of WCE, reduce the work burden and improve the classification accuracy.

The invention discloses an intestinal tract state recognition method and system based on online detection, and relates to the technical field of online detection, and the method comprises the steps: collecting a current internal image of an intestinal tract based on an intelligent capsule endoscopy, and determining an abnormal region of the inner side wall of the intestinal tract according to the detection of the current internal image; the multiple intestinal environment characteristics are determined according to the excrement data of the user, the state of the intestinal tract is determined according to the multiple intestinal environment characteristics, the abnormal area of the inner side wall of the intestinal tract and the form change amount of the intestinal tract, and the recognition accuracy of the state of the intestinal tract is improved. Therefore, multiple disease types are determined according to the medical record information of the user, and multiple intestinal maintenance schemes are determined according to the multiple disease types, the state of the intestinal tract and the age of the user; according to the embodiment of the invention, the optimal intestinal care scheme is determined according to the plurality of intestinal care schemes and the living habits of the user, and the optimal intestinal care scheme is loaded to the mobile phone of the user, so that the accuracy of the optimal intestinal care scheme is improved, and the corresponding reminding event is generated.

The invention relates to an intestinal capsule endoscopy video ulcer fragment automatic positioning method, computer equipment and a system. The method comprises the following steps: establishing an ulcer fragment automatic positioning network based on an initial time boundary specification and in combination with a strategy gradient and evaluation; training an ulcer fragment automatic positioning network by querying an image-reference video pair; inputting the query image-reference video pair into the trained ulcer fragment automatic positioning network, and outputting an ulcer fragment associated with the query image in the reference video; implementing a computer device based on the method; the system inputs a query image-reference video pair through an input unit, a positioning unit executes a method and positions an ulcer fragment, and the ulcer fragment is output by an output unit. According to the method, an interested intestinal capsule endoscopy ulcer lesion image is taken as a query image, an intestinal capsule endoscopy long video is taken as a reference video, the video is analyzed based on reinforcement learning, a time boundary is refined through sequential decisions of starting and ending identifiers, segments related to the query image are accurately positioned, and a video repositioning task is completed.

The invention discloses an in-vitro controlled in-vivo miniature intelligent terminal system and an image acquisition method, the system comprises an attitude control module, a position control module, a capsule endoscopy module and a main control module, the attitude control module comprises an attitude control coil and a coil support frame, and the attitude control coil surrounds the coil support frame; the position control module comprises a stator coil, a stator core and a stator support, the stator coil is wound on the stator core, the stator core is fixed on the stator support, and a hollow space is formed between the coil support frame and the stator support; the capsule endoscopy module reaches a target area after being swallowed by the target object, and the target area of the target object is located in a hollow space; the main control module is electrically connected with the posture control module, the position control module and the capsule endoscopy module and used for controlling currents in the posture control module and the position control module so as to drive the capsule endoscopy module to collect images of the target area. According to the scheme, the image acquisition integrity and accuracy can be improved.

The utility model discloses a child capsule endoscopy recording appearance placing bag, including recording appearance placing bag main part, recording appearance placing bag main part top end is set up indicating lamp display groove, recording appearance placing bag main part top is provided with the flap, and the flap one end is fixed on the back of recording appearance placing bag main part, and the flap other end is pasted with recording appearance placing bag main part front surface through magic tape, and recording appearance placing bag main part front surface is provided with the bed card placing frame, and recording appearance placing bag main part one end is connected with sensor connecting line storage bag through the connecting band, the utility model discloses a recording appearance placing bag main part cooperation indicating lamp display groove is convenient for medical staff to observe the indicating lamp of recording appearance whether normal at night, and setting up the bed card placing frame is convenient for medical staff to carry out the sick child identity identification, avoids the identity identification error and influences capsule endoscopy examination result, and the sensor connecting line storage bag cooperation storage subassembly will be convenient for the quick storage sensor connecting line, avoids its disorder and exposes and influences recording appearance normal use.

The invention discloses a small intestine capsule endoscopy auxiliary method and system based on image processing, and aims to solve the problems that a capsule endoscopy is easy to leak in film reading, polyp and submucous membrane tumor sensitivity is insufficient, and a time sequence is unstable. The method comprises the following steps: generating first prediction and intermediate features through decoding and preprocessing and sliding window time sequence attention in combination with feature memory; extracting a candidate region by using a category activation graph and discriminating by a local refining sub-network, performing weighted fusion according to confidence to form second prediction, performing time sequence smoothing in combination with minimum duration and category transfer constraint, outputting frame-level annotation and statistical visualization, and performing statistical analysis on the frame-level annotation and the statistical visualization. The technical effects of improving polyp and submucosal tumor sensitivity, enhancing focus positioning accuracy and improving radiograph reading efficiency are achieved on the premise of not obviously sacrificing the processing speed.

A system for analyzing images includes memory storing instructions, which when executed by at least one processor, cause the system to access a plurality of video clips of at least a portion of a GIT and for each video clip of the plurality of video clips, provide a score for classifying the video clip to a segment of a plurality of segments of the GIT. The system is also caused to classify each video clip of a subset of the plurality of video clips to one of the plurality of segments of the GIT and detect, in consecutive video clips in the subset, a change from a first classification to a second classification. The system is also caused to classify, among the video clips in the subset, a transition between two adjacent segments of the plurality of segments of the GIT.

A computer-implemented method for estimating adequacy of a capsule endoscopy (CE) procedure includes accessing a plurality of images of at least a portion of a gastrointestinal tract (GIT) captured by a CE imaging device during a CE procedure, accessing a plurality of characteristic metrics associated with the plurality of images, determining an adequacy metric of the CE procedure based on the plurality of characteristic metrics, wherein the adequacy metric provides a measure of whether an imaging coverage provided by the plurality of images is adequate to capture an event of interest in at least the portion of the GIT regardless of whether such an event of interest actually exists in at least the portion of the GIT, and displaying an adequacy indication of the CE procedure based on the adequacy metric.

The utility model discloses a capsule endoscopy, and relates to the technical field of medical instruments. In the capsule endoscopy, a capsule core and a lamp panel cover are fixed in a capsule shell, the capsule shell comprises a capsule rear shell and an optical front cover, one end of the capsule rear shell in the axial direction is an opening, the other end of the capsule rear shell is a closed end, and the optical front cover covers the opening; the inner wall of the capsule rear shell is provided with a first rotation limiting structure which extends from the opening to the closed end in the axial direction, and a plurality of axial limiting blocks are sequentially arranged in the circumferential direction. The capsule core is inserted into the capsule rear shell through the opening in the axial direction and is in insertion fit with the first rotation limiting structure to prevent the capsule core from rotating in the capsule rear shell; the lamp panel cover is arranged at the opening and matched with the axial limiting block, and the capsule core is limited on the two sides in the axial direction. Based on the limiting effect of the capsule rear shell, the assembling efficiency, the assembling precision and the part forming yield can be improved.

The present invention relates to a computer-implemented method capable of automatically detecting small bowel and colonic ulcers and erosions in Crohn's capsule endoscopy image data, by classifying pixels as lesion or non-lesion, using a convolutional image feature extraction step followed by a classification step and indexing such lesions in the set of one or more classes.

A computer-implemented method for estimating a size of a suspected polyp in an image includes accessing an image of in at least a portion of a gastrointestinal tract (GIT) captured by a capsule endoscopy device, wherein the image includes a suspected polyp; receiving an indication to an approximated periphery of the suspected polyp in the image; determining, without human intervention, a 3D measurement of the polyp based on peripheral points in the approximated periphery indication; and estimating a size of the suspected polyp based on the determined 3D measurement.

This invention discloses a capsule endoscopy image enhancement and restoration method based on degradation competition, belonging to the field of image enhancement and restoration. The method acquires the current capsule endoscopy color image and adjacent frames from the same examination, filters and registers reference frames, and constructs a reference color spectrum and a brightness reference spectrum. It then calls a pre-calibrated physical prior model to estimate the physical illumination field and the reflected light diffusion field; calculates the credibility of degradation due to low illumination, specular reflection, motion blur, and liquid film scattering, and competitively determines the dominant degradation state at the pixel level; it controls the selective participation of restoration terms in joint optimization through dominant restoration flags, auxiliary restoration weights, and restoration gating information; and combines chromaticity constraints, mucosal microstructure direction continuity constraints, uncertainty fusion, and high uncertainty region backoff to obtain an enhanced and restored brightness image. Finally, it updates the color channels according to the brightness ratio and outputs the enhanced and restored capsule endoscopy color image.

This invention relates to a computer-implemented method for automatically characterizing small bowel lesions in capsule endoscopy images, comprising detecting small bowel lesions in medical images by using a convolutional image feature extraction step, followed by an architecture that classifies pixels as lesions or non-lesions into one or more categories.

The embodiment of the invention relates to the field of medical image processing, and discloses a shielding processing method for a capsule endoscopy video, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target video shot by a capsule endoscopy; extracting optical flow features between image frames of the target video; for each image frame in the target video, obtaining a shielding mask of the current image frame according to the current image frame and the optical flow characteristics between the current image frame and the adjacent image frame, the shielding mask being used for representing the shielding condition of each pixel point in the current image frame; and recovering the shielded pixel points in the current image frame according to the shielding mask of the current image frame and the optical flow characteristics between the current image frame and the adjacent image frame to obtain a recovered image frame. The problem of shielding processing of the capsule endoscopy video is solved, non-rigid, variable and unstructured shielding areas in the capsule endoscopy video are removed, and image cleaning in the pre-processing stage is achieved.

The utility model discloses a pushing device for a capsule endoscopy. The pushing device comprises a sleeve body and a connecting part integrally arranged at the bottom of the sleeve body. A plurality of accommodating grooves are formed in the front end of the sleeve body; and a mounting hole is formed in the bottom of the connecting part. According to the device, the capsule endoscopy is placed in the sleeve body in a magnetic attraction mode, the sleeve body is conveyed to the duodenum through the gastroscope, and the risk of gastrointestinal mucosa injury and even perforation is avoided.

The invention discloses a capsule endoscopy hemorrhagic spot identification and analysis method based on near infrared spectrum, and relates to the technical field of hemorrhagic spot identification, a video sequence which is shot by a capsule endoscopy and contains near infrared spectrum information is acquired, and a first frame image is selected as a substrate image; generating a partition map based on the base image, and constructing an index between the partition map and the base image; processing a subsequent frame image through multi-stage scanning, and generating and overlapping a scanning layer which protrudes out of the suspected hemorrhage area; an event recording unit is constructed for the suspected bleeding area in each scanning image and used for collecting image feature data of the suspected bleeding area; fusing the image feature data based on an image fusion process to generate an event chain of the suspected bleeding region; generating and visualizing a structured hemorrhage analysis report by analyzing the event chain and the inspection index; according to the invention, through sequential event chain analysis and near infrared spectrum feature fusion, the specificity, reliability and clinical decision support value of hemorrhagic spot recognition are effectively improved.

The application discloses a kind of based on image processing Small intestine capsule endoscopy auxiliary method and system, to solve the problem that capsule endoscopy reading film is easy to miss, polyp and submucous tumor sensitivity is insufficient and time sequence is unstable, the first prediction and intermediate feature are generated by decoding and preprocessing, sliding window time sequence attention is combined with feature memory, candidate region is extracted using class activation map and is distinguished by local refinement subnetwork, second prediction is formed by confidence weighted fusion, time sequence is smoothed by combining minimum duration and class transition constraint, frame-level labeling and statistical visualization are output, the technical effect that polyp and submucous tumor sensitivity is improved, lesion positioning accuracy is enhanced and reading efficiency is improved under the premise of not significantly sacrificing processing speed is realized.