97 results about "G i endoscopy" patented technology

The invention discloses an intelligent bronchial endoscope focus detection method, computer equipment and a storage medium. The intelligent bronchial endoscope focus detection method comprises the steps that real, reliable and diversified bronchial endoscope examination images are collected; through data preprocessing, labeling and data division, a bronchial focus detection data set is constructed; an efficient bronchial focus detection network is constructed, and improvement is carried out through multiple attention mechanisms and a convolution module; designing a loss function and training the network to obtain an optimized bronchial focus detection model; and performing focus detection on the acquired image in the real-time bronchoscopy video, and displaying a result. Based on the deep learning technology, the deep neural network model is trained to carry out precise focus type detection on the bronchial endoscope image, real-time bronchial lesion prompt information is provided for endoscope operators, the lesion omission problem during bronchial lesion examination is effectively relieved, the bronchoscopy process is standardized, the endoscope examination quality is improved, and the bronchial lesion detection efficiency is improved. And the workload of operators is reduced.

The invention discloses a method and a device for solving direction perception disorder caused by a rotating mirror, and solves the problem that an adjacent tissue structure outside a part is difficult to determine after endoscopic examination rotation in a similar upper digestive tract wall internal lesion. The method comprises the following steps: acquiring pose information of an endoscope in an electromagnetic navigation system of a lumen target position and a corresponding image in the lumen as a reference pose; obtaining a track pose of the endoscope after the view field is adjusted in the electromagnetic navigation system and a corresponding intraluminal image, and determining an Euler angle of each track point according to the track pose; obtaining a track pose of the endoscope after the view field is adjusted in the electromagnetic navigation system and a corresponding intraluminal image, and determining an Euler angle of each track point according to the track pose; performing three-dimensional reconstruction on the lumen and the adjacent tissue thereof according to the lumen image map, and performing corresponding rotation according to the rotating mirror angle and the corresponding image in the lumen to obtain the rotated lumen and the adjacent tissue thereof; according to the invention, after the endoscope rotates to the optimal visual field, the adjacent tissues outside the endoscope can be clearly known.

The invention belongs to the technical field of endoscopic examination, and discloses an automatic adjusting device for endoscopic examination, which comprises an endoscope main body module, an image acquisition and processing module, a surgical instrument identification module, an automatic focusing module, a visual angle automatic adjusting module, a central control module and an interaction module, the automation function of the system reduces the dependence on assistants, and the operating room resource allocation problem is obviously improved especially under the condition of complex operations or insufficient manpower. Operation images and endoscope adjustment data recorded by the system can be used for postoperative analysis and teaching, and important support is provided for medical training. And by reducing the operation time and the error risk, the system improves the intraoperative safety of the patient, and further promotes the development of the endoscopic operation. Through organic combination of a wide-angle lens, an artificial intelligence recognition algorithm, automatic focusing and a visual angle adjustment technology, an efficient and intelligent automatic solution is provided for endoscopic examination, and multiple key problems in the prior art are solved.

The invention relates to the technical field of medical instruments, in particular to an oral cavity closing prevention device for digestive endoscopy. Comprising a circular tube, an inflation device and a drainage tube, an elastic piece is attached to the exterior of the inflation device, longitudinal supporting mechanisms are rotatably arranged at the two ends of the elastic piece and used for opening the oral cavity and the lower jaw of a patient, and telescopic plates are slidably arranged between the supporting mechanisms and the circular tube; a connecting structure used for applying pressure to the expansion assembly is arranged between the longitudinal supporting mechanism and the transverse supporting mechanism, and a filling area is formed between every two adjacent supporting mechanisms. The movable plate is used for applying pressure to the air bags in the transverse supporting plate, the air bags expand and extend outwards firstly, and when the air bags on the two sides make contact, the connecting baffle is matched with the movable plate to indirectly apply pressure to the transverse supporting plate through the air bags, so that the transverse supporting plate expands the mouth of a patient in the transverse direction, and the longitudinal supporting plate and the transverse supporting plate are prevented from moving at the same time; and the comfort of the mouth in the transverse direction is improved.

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.

The invention discloses an intelligent bronchus lumen part identification method, electronic equipment and a storage medium, and the method comprises the steps: collecting each bronchus lumen part image under real bronchus endoscopy, and carrying out the data labeling, data preprocessing and data division, so as to construct a bronchus lumen part identification data set; designing and constructing a feature extraction backbone network and a loss function; training the network by using the training data set to obtain a trained bronchial lumen part identification model; and classifying and identifying the acquired images in the real-time bronchial endoscopy video, and displaying an identification result. On the basis of the deep learning technology, automatic identification of the bronchus lumen part is achieved, real-time bronchoscope position information is provided for bronchoscope operators, operation errors such as false detection and missing detection caused by manual inspection are effectively relieved, the bronchoscope inspection process is standardized, the endoscopic inspection quality is improved, and the operation efficiency is improved. And the workload of operators is effectively reduced.

The application relates to the technical field of medical equipment, in particular to a multifunctional control device for assisting endoscope interventional treatment, which comprises a foot pedal device, a cluster control box, a holding device and a signal line, the cluster control box is connected with the foot pedal device through the signal line, a plurality of holding devices are connected with the cluster control box, a control panel center is installed in the cluster control box, the holding device comprises a fixed base, a sliding push base, a sliding block body, a half-ring supporting body and a buckle cover body, the sliding push base is slidingly installed on the fixed base, a module fixing assembly is arranged at the right end of the fixed base, L-shaped limiting edge plates are symmetrically arranged at the two sides of the sliding push base, the sliding block body is slidingly installed on the sliding push base through the limiting edge plates, the application can make a plurality of endoscope examination operation modules be concentrated together, manual control is completely replaced by foot pedal electric control through mode function switching, and the task amount of hands is reduced.

In the endoscopic examination support apparatus, three three-dimensional model generation means generates a three-dimensional model of a luminal organ in which an endoscope camera is placed, based on endoscopic images acquired by imaging an interior of the luminal organ with the endoscope camera. The unobserved area detection means detects an area estimated not to be observed by the endoscope camera, as an unobserved area, based on the three-dimensional model. The display image generation means generates a display image including information indicating an observation achievement degree for each of a plurality of sites of the luminal organ, based on the detection result of the unobserved area. The endoscopic examination support apparatus may be used to support user's decision making.

Systems and methods for objective evaluation of a stool sample to determine whether a patient's lower gastrointestinal tract is sufficiently clean to undergo a successful gastrointestinal visualization procedure with favorable visualization. A method includes collecting a stool sample from a patient and assessing the stool sample to determine whether an intestine of the patient is sufficiently clean for the patient to undergo a successful lower gastrointestinal tract visualization procedure.

The invention provides a defoaming agent for digestive endoscopy as well as a preparation method and a use method thereof, and belongs to the technical field of medicines. The defoaming agent comprises 1%-10% of organic silicone oil and 90%-99% of polyethylene glycol; the preparation method comprises the following steps: weighing the organic silicone oil and the polyethylene glycol according to a set proportion, and respectively heating to 75-85 DEG C to form a hot melt; carrying out isothermal mixing on the two components to obtain a mixed hot melt, and carrying out intermittent shearing and stirring in a wall breaking machine to obtain an emulsified melt; flatly spreading the emulsified molten liquid in a pre-cooled container, sealing a cover, and freezing to obtain a white waxy sheet block; and crushing and sieving the white waxy sheet blocks to obtain white organic silicone oil dry milk powder, namely the defoaming agent. The method comprises the following steps: adding water into a defoaming agent and uniformly mixing to prepare a silicone oil emulsion before digestive endoscopy; the composition is orally taken or sprayed on an examined part. The dry emulsion type defoaming agent provided by the invention is simple in formula, free of additives, free of any potential safety risk, safe and reliable, good in stability and excellent in defoaming effect.

The invention discloses a portable endoscope transfer device for bedside emergency endoscope examination, and relates to the technical field of medical instruments, the portable endoscope transfer device comprises a transfer box, a box door is hinged to the transfer box, an inflation structure is arranged in the transfer box, the inflation structure comprises a protection air bag, a placement groove is formed in the protection air bag, and the protection air bag is provided with an air inlet. A containing groove is formed in the outer side of the protective air bag and can contain an endoscope, a fixing frame is fixedly connected to the outer side of the protective air bag, the fixing frame is placed in the transfer box, a plurality of anti-collision corners are fixedly connected to the corners of the fixing frame, and the anti-collision corners are filled with non-Newtonian fluid; the fixing frame and the endoscope in the fixing frame are stably lifted by a certain height by driving the lifting structure, so that the operation end of the endoscope is more easily grabbed by medical staff. Therefore, laborious groping and fetching of objects in a deep box body are avoided, the device is particularly suitable for being used in an emergency and quick-response bedside inspection scene, and the user experience and the operation efficiency are improved.

The balloon structure comprises a main catheter and a one-way valve arranged on one side of the main catheter, an auxiliary catheter is arranged on one side of the main catheter, the auxiliary catheter is detachably connected with the main catheter through a connecting mechanism, a hollow gooseneck pipe is arranged on one side of the auxiliary catheter, and the hollow gooseneck pipe is detachably connected with the main catheter through a connecting mechanism. A bag body structure is arranged on one side of the auxiliary catheter; the bag body structure comprises a hollow bag body, the bottom face of the hollow bag body is arranged on the outer surface of the auxiliary catheter, multiple sets of water inlet pipes are further arranged on one side of the auxiliary catheter and communicated with the hollow bag body, and an adjusting ring is further arranged on one side of the hollow bag body and slidably arranged on the auxiliary catheter. The angle of the hollow bag body can be adjusted according to the bending angle of the digestive tract, the hollow bag body can be conveniently guided in, meanwhile, expansion of the hollow bag body is guided, the sealing performance of the hollow bag body on plugging of the digestive tract is improved, overall installation and operation are convenient, and medical staff can conveniently use the hollow bag body.

The present application relates to the technical field of image processing, in particular to a colonoscopy coverage evaluation method and system based on three-dimensional reconstruction, a storage medium and a computer device, comprising the following steps: S01, screening information frame image: input the examination image into the trained classification neural network, perform information frame screening, if the screening result meets the requirements, enter S02, otherwise, issue a warning; S02, colonoscope depth prediction: input the information frame screened in step S01 into the trained depth prediction neural network, obtain a depth map D; S03, colonoscope pose estimation: input the RGB-D data output by step S02 into the trained pose estimation network, output the pose P of the endoscope; S04, reconstruct the three-dimensional model of the colon; S05, calculate the coverage, reconstruct the three-dimensional model of the intestinal tract according to the endoscopic images in the examination process, and calculate the coverage, when the coverage is less than 90%, issue a warning to avoid missed diagnosis and improve the examination efficiency.

The invention discloses a dirt recovery device for emergency endoscopic examination, and particularly relates to the field of medical apparatus and instruments, the dirt recovery device comprises a conical vomit bag made of a medical grade anti-leakage PE + TPU composite film; a penetrating opening is reserved in the bottom of the vomit bag, the bottom of the vomit bag is connected with a hose through the penetrating opening, and the hose is a medical-grade transparent telescopic corrugated pipe. A disposable vomit bag is placed in the conical barrel, the vomit bag is completely unfolded to be full through manual stretching or slight air blowing, it is ensured that the bottom and the side wall of the vomit bag are completely attached to the inner wall of the conical barrel, and no wrinkles are left; then the outer side of the lantern ring is sleeved with the redundant part on the upper portion of the vomit bag, the periphery of the lantern ring is completely wrapped, finally, the covering ring is aligned to the top of the lantern ring to be inserted and fixed, the edge of an upper opening of the vomit bag is clamped and locked, the effects of supporting, positioning and wrinkle preventing of the vomit bag are achieved, and vomit is prevented from being blocked by wrinkles of the vomit bag.

The invention provides an intelligent auxiliary decision-making system and method for endoscopic examination based on deep learning, and belongs to the field of medical image processing, and the system comprises a data collection module, a manifold mapping module, a manifold attention module, a manifold maintenance generation network module, a disease detection module and a result output module. According to the method, an endoscopic image is regarded as a Riemannian manifold embedded in a high-dimensional space, and curvature features and geodesic features are extracted through a differential geometry theory; designing a manifold attention mechanism, defining an attention weight based on a geodesic distance, and realizing manifold feature propagation and multi-scale feature fusion; the manifold preserving generative adversarial network is utilized to expand training data, and the problem of medical image sample imbalance is solved; an end-to-end architecture is adopted, and a complete clinical application process is formed from data acquisition to result presentation; according to the method, the focus detection accuracy of endoscopic examination is remarkably improved.

The utility model relates to a sorting tray, in particular to a multifunctional sorting tray for endoscopy. Comprising an arrangement disc body, a gastroscope wrapping area, a gastroscope biopsy forceps area, a protruding block, an enteroscope biopsy forceps area, a cloth area, a gastroscope glue area, an enteroscope glue area, a filter paper area, a haemostatic forceps area and the like. A baffle is arranged on the upper side of the arrangement disc body in the circumferential direction, the left portion of the upper side of the arrangement disc body is divided into a front area, a middle area and a rear area, the rear portion of the arrangement disc body is divided into a gastroscope wrapping area, a gastroscope biopsy forceps area and an enteroscope biopsy forceps area from left to right, and a plurality of protruding blocks are arranged on the gastroscope biopsy forceps area and the enteroscope biopsy forceps area on the upper side of the arrangement disc body. The baffles at the gastroscope biopsy forceps area and the enteroscope biopsy forceps area are in an inclined state, and the middle part of the left part of the upper side of the arrangement disc main body is provided with a material distribution area, a gastroscope glue area and an enteroscope glue area from left to right. According to the utility model, the upper side of the sorting tray main body is divided into a plurality of areas, so that medical personnel can quickly find and take required articles, and the working efficiency is improved.

In the endoscopic examination support apparatus, the image acquisition means acquires an endoscopic video captured by an endoscope. The lesion detection means detects a lesion candidate from the endoscopic video. The heat map generation means generates a heat map indicating a possibility of lesion of the lesion candidate in the endoscopic video by a color. The display control means displays a position of a lesion on a frame of the endoscopic video based on the lesion candidate and the heat map.

The present invention relates to an endoscopic examination evaluation system and method based on a video understanding network. The system comprises: a behavior and action recognition module, which is configured to perform, on the basis of a pre-trained video understanding network model based on dual-cascade spatio-temporal attention, scene action recognition on an endoscopic examination video frame image collected by a video acquisition module, so as to obtain scene action recognition data; a cleaning-event recognition module, which is configured to perform association and mapping between a scene to be cleaned and a cleaning action in the scene action recognition data, so as to obtain a cleaning-event recognition data set; and an endoscopic examination recording module, which is configured to determine evaluation parameters of an endoscopic examination process on the basis of the cleaning-event recognition data set. In the present invention, semantic action classification and detection are performed on an endoscopic examination operation and a corresponding video image, and semantic action data and stipulated endoscopic examination action data are used to form comparable data to perform auxiliary prompting and index quantification, thereby promoting the standardization of endoscopic examinations.

An endoscopic examination assistance method includes calculating a remaining time until an examination of an internal organ using an endoscope ends based on a preset examination time for the examination and an elapsed time having elapsed after the examination has started, acquiring current position information indicating a current examination position in the internal organ, and generating and outputting an examination time table including a scheduled examination time for each of a plurality of sections in the internal organ using the remaining time and the current position information.

The utility model relates to the technical field of medical instruments, in particular to a sputum suction laryngeal mask for endoscopic examination. The mask bag is connected with the other end of the main tube, and a through hole used for extracting secretions of sputum is formed in the inner wall of the bottom end of the mask bag; the connector is connected with the other end of the main pipe, and a branch pipe connected with a breathing machine is fixedly connected to the side wall; the liquid extraction connector is arranged on the outer side of the connector, connected with a collecting pipe communicated to the inner side of the mask bag, connected with the one-way valve through a catheter, connected with a sputum aspirator and used for being matched with the one-way valve to inflate the mask bag and extracting sputum gathered on the inner side of the mask bag. Operation can be carried out by inserting the bronchofiberscope from the connector during detection, sputum can be sucked in real time, examination or suction can be carried out under the condition that ventilation of the laryngeal mask is not affected, operation of a doctor is facilitated, and time is saved for emergency treatment of a patient.

In the endoscopic examination support apparatus, the video acquisition means acquires an endoscopic video captured by an endoscope. The lesion detection means detects a lesion candidate from the endoscopic video. The heat map generation means generates a heat map which represents a lesion possibility of the lesion candidate included in the endoscopic video by a color. The display control means superimposes and displays an area where the lesion possibility is equal to or higher than a first threshold on the endoscopic video in a first display mode, and superimposes and displays an area where the lesion possibility is equal to or higher than a second threshold on the endoscopic video in a second display mode.

The utility model relates to the field of blanket technology, and disclose a kind of blanket for endoscopic examination, including blanket body, blanket body includes upper blanket and lower blanket, and the central position of lower blanket is provided with opening, and opening separates lower blanket into two blanket surfaces, and the opposite side of two blanket surfaces is provided with connecting piece for connecting two blanket surfaces and closing opening, and the side of the front of two blanket surfaces close to connecting piece is provided with hook surface, and the side of the front of blanket surface away from hook surface is provided with hair surface, and hair surface and hook surface can be bonded fixed.The utility model is divided into three by setting opening, and two blanket surfaces are fixed by connecting piece, when patient is in endoscopic examination, according to the position required when patient is in endoscopic examination, blanket body is covered on patient, and connecting piece is separated, opening is exposed, to provide space for patient endoscopic examination, fully play the role of warm-keeping and privacy protection, reduce the awkward feeling and uncomfortable feeling of patient.

In the endoscopic examination support apparatus, the image acquisition means acquires an endoscopic video captured by an endoscope. The lesion detection means detects a lesion candidate from the endoscopic video. The heat map generation means generates a heat map indicating a possibility of lesion of the lesion candidate in the endoscopic video by a color. The display control means displays a position of a lesion on a frame of the endoscopic video based on the lesion candidate and the heat map.

The invention discloses a method for generating an endoscopic image-text report of a tumor under a digestive tract mucous membrane. The method comprises the following steps: receiving real-time inspection videos of a white light endoscope and an ultrasonic endoscope; carrying out image preprocessing, and screening qualified white light endoscopic images and ultrasonic endoscopic images; identifying an endoscopic image containing a lesion, and carrying out redundancy deletion on the image; lesion segmentation and classification are carried out to obtain pathological properties and lesion features of lesions; identifying an anatomical position through a white light endoscopic image, and determining a lesion anatomical position; performing quality evaluation on the white light endoscopic image and the ultrasonic endoscopic image after redundancy deletion, and selecting a typical image of a lesion; and outputting pathological properties, lesion features, anatomical positions, the typical white light endoscopic image and the ultrasonic endoscopic image of the same lesion to generate a standardized image-text report. According to the method, the standardized image-text report can be automatically generated in the endoscopic examination process of the tumor under the digestive tract mucosa, the report accuracy and consistency are improved, and the writing workload of an endoscopic physician is reduced.

The invention relates to the field of medical technology assistance, and discloses an endoscope report generation method and device based on a multi-modal large model, computing equipment and a storage medium, and the method comprises the following steps: collecting a digestive endoscope examination image, and preprocessing the digestive endoscope examination image; classifying and marking the preprocessed digestive endoscopy images, and constructing a digestive endoscopy multi-modal image-text report database; training a preset initial report model by using the multi-modal image-text report database; and inputting the digestive endoscopy examination image of which the report is to be output into the trained digestive endoscopy report model to generate an output digestive endoscopy report. According to the method, the suspicious focus existing in the digestive endoscopy image is detected and the representative image is collected according to the collected digestive endoscopy image, the image report is formed, the text report for description and diagnosis is generated, finally, the complete, accurate and standard digestive endoscopy report is generated, and the generation efficiency and quality of the endoscopy report are improved.

The utility model discloses a special restraint device for painless endoscopic examination, which comprises a restraint garment and at least one pair of restraint straps, the restraint garment is a straight-shoulder cardigan strap, a neckline is flush with armpits, the restraint straps are arranged on two sides of a chest, the restraint straps are symmetrically arranged on two sides of an examination bed, one end of each restraint strap is connected with a bed edge handrail, and the other end of each restraint strap is connected with the corresponding restraint strap. The left restraint strap is connected with the right restraint strap, and the right restraint strap is connected with the left restraint strap. The restraint device is used for restraining the painless endoscopic examination patient, the restraint position can be conveniently adjusted according to the examination body position of the patient, and the restraint effect is good.

Provided is an endoscopy assistance device, wherein object detection means detects an object included in an endoscopic image obtained by imaging the inside of the large intestine by means of an endoscopic camera. A position information acquisition means acquires position information indicating the position of the endoscopic camera in the large intestine. A display control means displays a schematic diagram having a shape imitating the intestinal tract of the large intestine and, when a predetermined instruction is given upon detection of the object, the display control means adds a mark to the position of the schematic diagram corresponding to the position of the endoscopic camera indicated by the position information. The endoscopy assistance device can be used to assist decision-making by a user conducting an endoscopy.

The invention relates to an endoscopic examination operation monitoring method and device. The method comprises the steps that in the process that a to-be-evaluated person stretches an endoscope into a preset complete model of a target organ and conducts inspection operation on a preset target, an inspection operation video and the inspection operation duration of the to-be-evaluated person on the preset target are obtained; the preset target comprises at least one of a key part, a lesion marker and an inner wall; a preset lesion marker is arranged on the inner surface of the complete model of the target organ; and generating an endoscopic examination operation monitoring result of the to-be-evaluated person according to the examination operation video and the examination operation duration of the to-be-evaluated person on the preset target. By adopting the method, the problems that an existing endoscope inspection operation monitoring method needs to utilize virtual reality equipment, the cost is high, and popularization is not facilitated can be solved.

The invention discloses an endoscopic magnetic positioning clamp for tumor marking and positioning in laparoscopic surgery, which comprises a clamp main body, the outer contour of the clamp main body is arranged to be matched with a forceps channel of an endoscope, and the clamp main body is partially or completely made of a magnetic material; the chuck is arranged in the clamp body, one end of the chuck is provided with a clamping opening capable of being opened and closed, and the end, provided with the clamping opening, of the chuck is exposed out of the clamp body; one end of the inhaul cable is connected with the chuck in a disconnectable mode, and when the inhaul cable is connected with the chuck, the opening and closing action of the clamping opening is associated with the control action of the inhaul cable, so that the inhaul cable can control the clamping opening of the chuck to be opened or closed. The invention provides an endoscopic magnetic positioning clamp for tumor marking and positioning in a laparoscopic surgery, which can complete marking and positioning of a tumor position by utilizing an endoscopic forceps channel in an endoscopic examination process. And the position of the magnetic positioning clamp can be identified from the outside of the intestinal wall of the abdominal cavity of the patient by using the characteristic of magnetic attraction by using any existing iron surgical instrument.

The application discloses a method for identifying gastric anatomical structure based on magnetic control capsule endoscopy image of deep learning, screening the pictures output by the magnetic control capsule endoscopy detection, classifying according to the anatomical position, expanding the data set, and dividing into a training set and a test set; constructing, training and testing a multi-scale fusion pyramid visual Transformer network and a target detection network with an attention module, after the test, using the multi-scale fusion pyramid visual Transformer network to extract the global features of the image from the gastric magnetic control capsule endoscopy image, and classifying the magnetic control capsule endoscopy image; using the target detection network with the attention module to locate the classified pictures and identify the gastric anatomical structure. The application solves the problem of low resolution of the magnetic control capsule endoscopy examination pictures in the prior art, and can accurately identify the gastric anatomical position, further achieving the purpose of positioning the magnetic control capsule endoscopy in the stomach.