224 results about "Capsule Endoscopes" patented technology

The invention provides a splicing method and a splicing device for a magnetic control capsule endoscope image of a digestive tract. The method comprises the following steps: screening out a candidate lesion area image sequence from an original alimentary canal image sequence collected by a magnetic control capsule endoscope; preprocessing the candidate lesion area image sequence to obtain a preprocessed candidate lesion area image sequence; performing feature extraction on the preprocessed candidate lesion area image sequence based on an OfficientLoFTR improved model, further performing feature matching on the preprocessed candidate lesion area image sequence to obtain matched feature point pairs, and performing image registration processing on each image of the preprocessed candidate lesion area image sequence according to the matched feature point pairs to obtain a pre-processed candidate lesion area image sequence; the improved model can improve the accuracy of feature detection and matching, a good foundation is laid for subsequent image registration and image fusion, image registration can be carried out by combining global homography transformation and local thin plate spline transformation, and the problem of non-rigid deformation is solved.

The invention provides a capsule endoscope intestinal panoramic image splicing method and device, a computer readable storage medium and computer equipment. The method comprises the following steps: performing feature matching on an original intestinal tract image set acquired by a capsule endoscope to obtain a feature point set of each image of the original intestinal tract image set; performing polar coordinate expansion on each original intestinal image to obtain a rectangular intestinal image and a new feature point set corresponding to the feature point set in the rectangular intestinal image; calculating the displacement difference of each new feature point according to the coordinates of each new feature point of the new feature point sets of the two adjacent frames of rectangular intestinal tract images; cutting according to the displacement difference to obtain a stepping region image between two adjacent frames of original intestinal tract images; performing polar coordinate expansion on the stepping area image to obtain a newly added image segment; and splicing the newly added image segments in sequence to obtain an intestinal panoramic image. According to the method, a more accurate real stepping distance is obtained through calculation, and the smoothness and continuity of the image splicing position can be improved.

The invention provides a feature point matching method for digestive tract capsule endoscope images. The method comprises the following steps: after preprocessing, converting each image into a grayscale image, sequentially rotating each grayscale image from an initial angle according to different angles, carrying out feature point identification on the image after each rotation, and taking a subsequent feature point set with the maximum number of feature points as a feature point set; feature point matching is carried out on the feature point sets of the two adjacent frames of grayscale images, and part of matched feature points in the matched feature point sets are removed according to feature point position threshold conditions, feature point density threshold conditions and feature point brightness threshold conditions; and according to a geometric consistency condition and a confidence threshold condition, removing a part of matched feature points in the preliminary matched feature point set to obtain a final matched feature point set. According to the method, more feature points can be obtained, the distribution uniformity of the feature points is improved, and the quality of the feature points is improved.

Methods of enhancing visualization of a body lumen. A device including a capsule endoscope and a plurality of struts attached thereto may be positioned into the body lumen. The plurality of struts of the device may self-expand within the body lumen from a constrained configuration to an expanded configuration in which the plurality of struts extend both radially and axially away from a camera lens of the capsule endoscope so as to form a frame around the camera lens in the expanded configuration. The camera lens may image through the frame into the body lumen. At least a portion of the frame or a material constraining the struts of the frame may dissolve to allow passage of the device from the body lumen.

The utility model belongs to the technical field of medical instruments and equipment, and discloses a cover plate assembly, a minicell and a capsule endoscope, the cover plate assembly comprises a cover plate, a pole structure and a sealing ring, the cover plate is used for sealing an opening and is in sealing fit with the side wall of the opening, so that sealing is formed between the cover plate and a shell; a sealing ring accommodating groove is formed in the peripheral side wall of the pole structure; the sealing ring is arranged on the peripheral side wall of the pole structure, is accommodated in the sealing ring accommodating groove and is in sealing fit with the sealing ring accommodating groove, so that the sealing performance between the sealing ring and the pole structure is enhanced, the position of the sealing ring relative to the pole structure is fixed, the assembly is convenient, and the service life is prolonged. The outer peripheral side wall of the sealing ring is in sealing fit with the inner peripheral side wall of the cover plate, so that the inner side and the outer side of the sealing ring can form good sealing with the pole structure and the cover plate respectively, liquid leakage is avoided, meanwhile, a traditional glass sealing structure is replaced by the sealing ring, and the machining and precision control difficulty can be reduced.

An image processing method and a data set collection method is disclosed. The image processing method includes: making a high-resolution high-definition image interact with a calibrated blur kernel to obtain a blurred image; injecting calibrated noise to form a first noise image; degrading, by using a downsampling method, the first noise image into a low-resolution image; performing lossy compression on the low-resolution image to obtain a compressed image; adding into the compressed image random noise points that simulate a transmission process, to form a second noise image; and performing lossy compression on the second noise image to obtain a low-definition image, where the high-definition image is an image that is formed by means of photographing an organ in a body using a capsule endoscope, and the calibrated blur kernel and calibrated noise are results that are obtained by means of fitting a photographing process of the high-definition image.

The invention relates to the technical field of medical instruments, in particular to a capsule endoscopy focus automatic identification and positioning system. The system comprises an image acquisition module, an intelligent analysis module and a space positioning module. The image acquisition module receives an alimentary canal image sequence captured by the capsule endoscopy; the intelligent analysis module is integrated with a pre-trained deep convolutional neural network, analyzes the image frame by frame, and outputs a pixel-level segmentation mask identifying the contour and type of the focus; and the spatial positioning module estimates the pose of the capsule endoscopy and constructs a topological map of the inner wall of the digestive tract by analyzing the motion of feature points in the image sequence and combining a visual odometer and a graph optimization SLAM algorithm, and finally maps the recognized focus to specific coordinates of the map. According to the invention, automatic identification and accurate positioning of the nidus of the digestive tract are realized.

The present disclosure provides a digestive cavity inner wall three-dimensional model reconstruction method and apparatus, a device, and a medium. The method comprises: acquiring an image set collected by a capsule endoscope inside a digestive cavity; determining, in the image set, a plurality of first image frames formed under the influence of digestive cavity wall peristalsis, and determining a folded area in each first image frame; restoring the folded area in each first image frame into a smooth area to obtain a plurality of processed first image frames; and obtaining a digestive cavity three-dimensional model on the basis of the plurality of processed first image frames. The folded areas in the plurality of first image frames, influenced by digestive cavity wall peristalsis, in the image set are restored into the smooth areas, so that more stable images are obtained; and three-dimensional model construction is performed on the basis of these stable images, facilitating the construction of more accurate digestive cavity models, helping doctors to determine the lesions of patients more accurately, and improving the medical treatment efficiency and satisfaction of the patients.

The utility model discloses a capsule endoscope convenient for on-off control, which comprises a capsule shell, and a battery, a circuit board, a chip, an antenna, a lens module and an LED (light-emitting diode) are arranged in the capsule shell; the device further comprises an infrared photoresistor, an infrared laser light source, an ultraviolet photoresistor and an ultraviolet laser light source. The LED, the infrared photoresistor and the ultraviolet photoresistor are all installed on the lens module, and the infrared photoresistor and the ultraviolet photoresistor are connected with the chip and controlled by the chip. The infrared laser light source and the ultraviolet laser light source are positioned outside the capsule shell; the infrared laser light source is matched with an infrared photoresistor; and the ultraviolet laser light source is matched with the ultraviolet photoresistor. On and off of the capsule endoscope are achieved through irradiation of the infrared laser light source and the ultraviolet laser light source, the capsule endoscope can be matched with a single-lens capsule endoscope and a double-lens capsule endoscope, contact between the capsule endoscope and the outside is reduced under the condition that the size and the shell integrity of the capsule endoscope are not changed, and regular inspection tour and electric quantity checking of the capsule endoscope are facilitated.

A system for imaging one or more particular structures in the stomach within a workspace is provided. In one embodiment, the system comprises: a) an active capsule endoscope positionable in the stomach, comprising a camera, an inertial measurement unit, and a permanent magnet; the driving unit comprises a Hall sensor array located at the bottom of the working space and a plurality of magnetic field generators used for generating expected magnetic fields; and c) a control unit.

The invention discloses an automatic medical report generation method and system based on a capsule endoscope, and the method comprises the steps: obtaining a capsule endoscope video, and removing redundant frames of the capsule endoscope video, and obtaining a plurality of representative frames; inputting each representative frame into a preset detection model, determining an initial key frame and a classification result, and performing fine reduction on the initial key frame by using the classification result to obtain a plurality of target key frames; inputting each target key frame into a preset multi-modal model, extracting a corresponding first visual feature, splicing the first visual feature and the text feature to obtain an initial text description, performing iterative prediction on the initial text description until a first iteration termination condition is met, and outputting a target text description; and inputting the target text description into the large language model, predicting the first word segmentation sequence step by step by using an autoregression method until a second iteration termination condition is met, and generating a corresponding structured medical report based on the second word segmentation sequence. The diagnosis report can be automatically generated.

The utility model discloses an antenna positioning structure, an antenna structure and a double-lens capsule endoscope, and relates to the technical field of capsule endoscopes, and the antenna positioning structure comprises a positioning part which is arranged between two circuit boards and comprises an upper positioning part and a lower positioning part which are respectively clamped with a first circuit board and a second circuit board in a limiting manner, the upper positioning part and the lower positioning part are fixedly connected, and an arc-shaped bulge is arranged on one side, facing the upper positioning part, of the lower positioning part; the supporting part comprises a supporting ring, one end of the supporting ring abuts against the lower positioning part, the inner ring of the supporting ring further abuts against the arc-shaped outer side wall of the arc-shaped protrusion, the other end of the supporting ring extends towards the upper positioning part, and the antenna is arranged on the periphery of the supporting ring used for limiting the antenna in a sleeving mode. The risks of antenna deformation, displacement and the like after antenna assembly can be reduced, the stability of antenna signals is improved, and the capsule assembly difficulty is reduced.

A medical image processing system according to the present invention comprises: a communication unit for receiving photographic images captured by a capsule endoscope; and a processing unit for generating a read image from the photographic images by using results of a lesion model trained through lesion classification, wherein the processing unit applies the photographic images to a pre-trained abnormal lesion classification model so as to classify images including a preset lesion, then re-classifies the classified images into lesion images and normal images, selects a representative image representing the lesion images from the classified lesion images, and generates the selected representative image as the read image.

The invention relates to the technical field of image processing, in particular to a small intestine capsule endoscope target detection method which comprises the following steps: acquiring a small intestine capsule endoscope image; the method comprises the following steps: constructing an improved RT-DETR network, inserting an SCSA module between a backbone network and a neck network of the RT-DETR, and introducing a DFM module behind a three-branch Fusion module of the neck network; and the improved RT-DETR network adopts a Focaler-IoU loss function. According to the method, the problem that the accuracy of recognizing the tumor target by using the small intestine capsule endoscope image through RT-DETR needs to be further improved is solved.

The invention provides a magnetic control capsule endoscope steering control device and method based on a rotation strategy, belongs to the technical field of medical image diagnosis, and utilizes an external permanent magnet to form a rotating magnetic field in an intestinal tract to accurately control the movement of a magnetic control capsule endoscope. The magnetic force and the torque between the permanent magnet and the capsule endoscope are accurately modeled, the complex structure of the intestinal tract and the rotating motion of the endoscope are considered, and a more flexible and safer driving scheme is provided. By optimizing the key driving angles (such as alpha and beta), the capsule endoscope can accurately advance in the intestinal tract, the influence of friction force and static friction force is effectively overcome, it is ensured that the endoscope can smoothly pass through bent and folded areas of the intestinal tract, high safety is achieved, and the potential intestinal injury risk is reduced.

The present invention relates to a capsule endoscope, comprising an outer shell and a capsule core arranged in the outer shell. The capsule core comprises a magnet unit, and the distance between the magnetic force center of the magnet unit and the center of gravity of the capsule endoscope is no greater than a threshold value, thereby ensuring the balance force inside and outside the capsule endoscope, improving the control accuracy of the capsule endoscope, and thereby improving work efficiency and reducing costs.

The utility model provides a control circuit of a capsule endoscope system, which comprises a protection unit and a working unit, two ends of the protection unit are respectively connected with a power supply and the working unit, and the protection unit comprises a fuse, a leakage protection switch, a reactor, a filter and an isolation transformer which are connected in series. The reactor is closer to the power supply than the isolation transformer. According to the control circuit of the capsule endoscope system, the safety of the control circuit can be improved.

The present application relates to the field of medical equipment, and in particular to an endoscopic imaging device, an imaging system, and a method thereof having a diagnostic imaging device. The device comprises: a diagnostic imaging device, an external control device, and an ingestible capsule endoscope. The external control device is used to control the position and / or posture of the capsule endoscope within a target area; the diagnostic imaging device is disposed within the capsule endoscope and is used to perform diagnostic imaging of the target area under the control of the external control device. The endoscopic imaging device and the imaging method thereof provided in the present application utilize a diagnostic imaging device to examine the target area without the need for a tissue biopsy, thereby not only improving the accuracy of the examination of the lesion area, but also reducing the risk of infection in the patient.

The present invention relates to a chair-based capsule endoscope control device and system for controlling a capsule endoscope that is inserted into the human digestive system and acquires images of organs. The present invention provides a capsule endoscope control device that is inserted into the digestive tract of a subject and controls the position or posture of a capsule endoscope equipped with a magnet. The device comprises: a chair for the subject to sit on, comprising a seat portion and a backrest connected to the seat portion; and a magnet controller disposed on the backrest. The magnet controller includes a control magnetic force generator for adjusting the position or posture of the capsule endoscope, wherein the control magnetic force generator is movable in at least one direction.

The present application discloses an image stabilization correction method for capsule gastroscopy image acquisition, which relates to the technical field of medical diagnosis, and includes the following steps: image acquisition: taking the original image of the stomach wall through a capsule endoscope; image preprocessing: performing data enhancement processing on the original image, and then performing plane projection processing to obtain a two-dimensional projection plane image; generating a coordinate sequence: extracting a feature point sequence of the two-dimensional projection plane image, and generating a matching feature point pair coordinate sequence; correcting the lens posture: by calculating the lens posture, generating an image data sequence after posture correction, and correcting the lens posture; generating a stable image sequence: by calculating the path of the device, forming a lens space posture control sequence, thereby eliminating images that deviate from the predetermined path, and forming stable and reliable image data. The present application can make the acquired image more stable and reduce the impact of rotation and shaking on the image.

According to aspects of the present disclosure, a system includes at least one processor and at least one memory storing instructions that, when executed by the processor(s), cause the system to: obtain images of a portion of a gastrointestinal tract (GIT) captured by a capsule endoscopy device; for each of the images, provide, by a deep learning neural network, a score classifying the image into each of successive segments of the GIT; classify each image of a subset of the images for which the score meets a confidence criterion into one of the successive segments of the GIT; refine the classification of the images in the subset by processing signals corresponding to the classification of the images in the subset over time; and estimate, among the images in the subset, a transition between two adjacent segments of the GIT based on the refined classification of the images in the subset (1010).

The present disclosure describes a communication system and a communication method for receiving data of a capsule endoscope, the communication system comprising a receiving device and a processing device, the receiving device comprising a plurality of receivers in communication connection with each other, the capsule endoscope processing image data into a plurality of data packet sets, each data packet set comprises at least one data packet and the number information of the data packets, the capsule endoscope sends the plurality of data packet sets to each receiver in sequence, and the receivers receive the plurality of data packet sets in sequence and identify the integrity of the data packets to generate an identification result; the receiver judges the integrity of the data packet set based on the identification result and the quantity information to generate a target instruction and broadcasts the target instruction to other receivers in the processing device and the receiving device, and at least one receiver transmits the data packets to the processing device based on the target instruction to enable the processing device to obtain the complete data packet set. As a result, it is possible to provide a communication system for receiving data of a capsule endoscope, which improves the efficiency of receiving image data.

The invention provides a capsule endoscope image recording system and a data processing method thereof. The recording system comprises an antenna array module and a data recorder host, the antenna array module comprises a plurality of antenna units, and each antenna unit is configured to receive an image radio frequency signal sent by the capsule endoscope. Converting the image radio frequency signal into an image digital signal and detecting the intensity of the image radio frequency signal to generate an intensity digital signal; and the data recorder host is configured to perform weighted fusion processing on the image digital signal and the intensity digital signal of each antenna unit to obtain a comprehensive bit value, and determine a current bit value according to a size relationship between the comprehensive bit value and a threshold value. According to the system, all channel signals are input and weighted, and severe error rate fluctuation and even connection failure during rapid signal fluctuation can be resisted.

The invention relates to a method and device for adaptive leakage reduction of a capsule endoscope processor. Methods and devices for imaging the gastrointestinal tract using a capsule endoscope are provided. According to the method, at least two operating states during a gastrointestinal tract examination using a capsule endoscope are determined, where the at least two operating states comprise a first operating state and a second operating state, and the capsule endoscope comprises one or more capsule processors equipped with reverse bias control. In response to the current operating state being the first operating state or the second operating state, a current body bias of the one or more capsule processors is set to a first body bias or a second body bias, respectively, where the first body bias is different from the second body bias. One or more images are captured using the current body bias of the one or more capsule processors.

A suspension device and a capsule endoscope magnetic control system are provided. The suspension device includes a base, including a pairing portion; a suspension member, at least part of the suspension member is disposed within the base; an intermediate member, which is disposed on an upper end of the suspension member; and an adsorption component, which is disposed above the intermediate member. When the adsorption component has no adsorption force, the intermediate member is pressed against the upper end of the suspension member so that at least part of the suspension member abuts against the pairing portion and the suspension member is locked. When the adsorption component has the adsorption force, the intermediate member is driven to move vertically so that at least part of the suspension member is separated from the pairing portion and a posture of the suspension member is appropriate for adjustment.

The present invention relates to the technical field of image processing. The present invention provides an image annotation method, apparatus, device, medium and computer program product. The method includes: determining the spatial pose information of the virtual capsule endoscope based on the positional relationship between the virtual capsule endoscope and the gastric cavity model; the gastric cavity model is created based on historical gastric cavity data; establishing an association relationship between the virtual gastric cavity image and the spatial pose information; comparing the real gastric cavity image with the virtual gastric cavity image, and determining the multi-dimensional spatial data of the real gastric cavity image based on the comparison result and the association relationship; annotating the real gastric cavity image based on the multi-dimensional spatial data to obtain multi-dimensional image annotation information. By annotating multi-dimensional spatial data for gastric cavity images, the present invention reduces the workload of personnel, improves the annotation efficiency of gastric cavity image data, and annotates more comprehensive and accurate data for gastric cavity images, which is beneficial to the accurate construction of gastric cavity analysis-related algorithms.

The present invention provides a magnetic control device and navigation system for a capsule endoscope, comprising a permanent magnet capsule endoscope, a synchronous hybrid magnetic field generator, a five-degree-of-freedom motion mechanism, an electromagnetic coil power supply, and a controller. The synchronous hybrid magnetic field generator comprises a permanent magnet and an electromagnetic coil, wherein the axis of the electromagnetic coil always remains consistent with the direction of the permanent magnet's magnetic poles. The five-degree-of-freedom motion mechanism is mechanically designed so that when the direction of the magnetic field changes, the motor does not rotate accordingly, making power supply more convenient. The electromagnetic coil power supply is cleverly designed to maintain and adjust the electromagnetic coil supply current, thereby controlling the magnitude of the magnetic force generated by the magnetic control device in real time. The present invention utilizes the electromagnetic field generated by the electromagnetic coil, which is synchronous in direction and adjustable in size, in conjunction with the basic magnetic field generated by the permanent magnet. This allows the magnitude of the magnetic force generated by the magnetic control device to be controllably adjusted in any direction, thus breaking away from the limitation of the magnetic field control range and effectively controlling the movement of the capsule endoscope over a wider range.

The present invention discloses a dual-lens capsule endoscope intelligent film reading system and film reading method, the film reading system includes a dual-lens capsule endoscope body, a receiver module and an intelligent film reading module; the intelligent film reading module includes: a permission management module, a case management module, a fast film reading module and a report editing and output module, the fast film reading module: for performing deduplication, abnormal lesion detection and polyp detection and quantitative analysis on the image data stored in the receiver module, and performing dual-lens film reading by means of different frame rate film reading, thumbnail fast preview, thumbnail positioning, forward and backward film reading, frame-by-frame forward and backward film reading and / or lens mode switching. The present invention combines the dual-lens design with the intelligent film reading algorithm, realizes comprehensive monitoring and intelligent analysis of the front and back directions of the body; introduces the deduplication algorithm, abnormal lesion detection algorithm and polyp detection and quantitative analysis algorithm, and significantly improves the efficiency and accuracy of diagnosis.

In accordance with aspects of the present disclosure, a system includes at least one processor and at least one memory storing instructions which, when executed by the processor(s), cause the system to access images of a portion of a gastrointestinal tract (GIT) captured by a capsule endoscopy device; for each of the images, provide, by a deep learning neural network, scores for classifying the image to each of consecutive segments of the GIT; classify each image of a subset of the images, whose scores satisfy a confidence criterion, to one of the consecutive segments of the GIT; refine the classifications of the images in the subset by processing a signal over time corresponding to the classifications of the images in the subset; and estimate, among the images in the subset, a transition (1010) between two adjacent segments of the GIT based on the refined classifications of the images in the subset.

The invention discloses a self-adaptive recognition system for medical capsule endoscope streaming images, and the system comprises a feature extraction module which is used for receiving a real-time image stream obtained in a scanning process, and extracting the features of a current frame image; the feature buffer comprises a feature slot position and an activeness counter, the feature slot position is used for storing stock features of the scanned intestinal tract area image, and the activeness counter is used for recording the activeness of the feature slot position; the updating module is used for updating the activeness of the feature slot position; the gain adjusting module is used for generating a gain weight aiming at the current frame image through bidirectional biological plasticity adjusting logic; the training optimization module is used for injecting the gain weight into a loss calculation loop of the classifier module and correcting physical parameters of a classifier in real time through back propagation; and the classifier module is used for outputting a prediction classification result according to the current frame image features. According to the method, the problem of model performance degradation caused by non-uniform motion states of the capsule endoscope can be relieved, and the prediction accuracy is improved.