347 results about "Gastroscopes" patented technology

The invention relates to the technical field of medical technology assistance, in particular to an artificial intelligence diagnosis method for gastric cancer under a narrow-band imaging amplificationgastroscope, which comprises the following steps: S1, constructing a mini-UNet neural network model; S2, constructing a UNet + + image segmentation neural network model, and obtaining an area ratio Rabnormal of an image feature difference region; S3, adopting a generative adversarial network (GAN) technology to obtain a microvascular morphological diagram and a microstructure morphological diagram of the feature abnormal region; S4, identifying the microvessel form dissimilarity degree and the microstructure form dissimilarity degree in the microvessel form diagram and the microstructure formdiagram by the neural network model ResNet50; and S5, carrying out identification and judgment by using the random forest model obtained by training to obtain final judgment of cancer or non-cancer,and identifying the canceration position range of the image, which is judged to be cancer, as the identified image feature difference region Pabnormal. The sensitivity and specificity of the kit to cancer and non-cancer recognition reach about 93.4% and 90.7% respectively, a clinician can be effectively assisted in discriminating and diagnosing cancer and non-cancer, and a canceration position range is given.

The invention relates to the technical field of medical image processing, in particular to a gastric early cancer auxiliary diagnosis method based on a deep learning multi-model fusion technology, which comprises the following steps: S1, constructing multiple models; s2, collecting gastroscope images, forming continuous serialized image frames, identifying the light source mode of the current image frame by utilizing the image classification model 1, entering the step S3 to mark the position of a focus by the target detection model 2 when the current image frame is identified as a white lightmode, and marking the high-risk focus by utilizing the image classification model 3; and when the image frame is identified as the dyeing amplification mode, entering the step S4 in which a segment model group can extract the boundary range, the microvessel form and the micro-tissue structure feature map in the image frame in real time, and outputting whether canceration occurs or not, the credibility and the differentiation type by the decision-making model 7. A plurality of deep learning models are constructed according to different tasks, a parallel cascade model fusion technology is adopted, and a full-process intelligent auxiliary diagnosis function is provided in the stomach early cancer screening process of endoscopists.

The invention relates to a bimodal stomach disease classification method and device based on texts and pictures, and belongs to the technical field of medical text and image bimodal intelligent process. The method comprises the following steps: inputting a medical record report into a pre-trained text extraction network to obtain a text feature vector of the medical record report; inputting the gastroscope picture into a pre-trained picture extraction network to obtain a picture feature vector of the gastroscope picture; and performing feature fusion on the text feature vector and the picture feature vector, and inputting the fused feature vector into a pre-trained classifier to obtain a classification result of the stomach disease. The problem that the efficiency of manual stomach disease diagnosis is low can be solved. The stomach diseases are automatically classified, and the stomach disease diagnosis effect is improved. Besides, stomach disease classification is carried out by combining the text feature vector and the picture feature vector, and compared with independent use of texts or pictures, the classification accuracy is higher.

The invention discloses a method for analyzing serum metabolomics on the basis of an LC-MS (liquid chromatogram-mass spectrograph) serum metabolomics technology. According to the method, serum is analyzed by constructing a serum metabolomics analysis model, and a model construction method comprises the following steps: collecting a healthy serum sample and an infected serum sample; performing LC-MS detection on the samples to obtain an original metabolic fingerprint; and preprocessing the fingerprint, sequentially performing PCA (principal component analysis) and PLS-DA (partial least squares-discriminant analysis) on an obtained two-dimensional matrix to obtain a PLS-DA model, verifying the obtained model, and if the model does not have over-fitting risks, finishing the model construction. By adopting the method disclosed by the invention, a serum metabolomics analytic technology is applied to early screening of esophageal cancer for the first time, high risk populations of the esophageal cancer can be quickly and conveniently screened out, the screening range of the esophageal cancer is reduced, the efficiency of screening the whole population of a high incidence area of the esophageal cancer is effectively improved, the screening cost is greatly reduced, and the pain caused by invasive endoscopy to part of the population is effectively avoided, so that the method has important economic and social benefits and is convenient to popularize and apply.

An esophageal intubation system includes a main tube with a tapered body, proximal and distal ends and a bore extending between and open at the ends. The main tube is inserted into the oropharynx and its distal end extends into the upper esophagus in order to provide a conduit for esophagoscopes, gastroscopes and related diagnostic and treatment equipment. A first auxiliary tube assembly delivers O₂ close to the larynx. A second ancillary tube assembly samples CO₂ from the larynx region. An esophageal intubation method includes the steps of moderately sedating a patient, placing a main esophageal tube in the oropharynx and partway into the upper esophagus, passing an esophagoscope or a gastroscope through the main tube and into the esophagus or stomach while minimizing the gag reflex, delivering O₂ and sampling CO₂ from the pharynx region.

The invention discloses a method for constructing a serum metabonomics analysis model. The construction method comprises the following steps: collecting a healthy serum sample and an ill serum sample; performing LC-MS detection on the samples, thereby obtaining original metabolic fingerprints; preprocessing the fingerprints, sequentially performing principal component analysis and partial least square discriminant analysis on a two-dimensional matrix, thereby obtaining a PLS-DA model; and verifying the obtained PLS-DA model, wherein if the overfitting risk does not exist, the model construction is finished. According to the method disclosed by the invention, the serum metabonomics analysis technology is applied to early screening of an esophagus cancer, the high-risk population of the esophagus cancer can be rapidly and conveniently screened by virtue of model construction, the esophagus cancer screening range is widened, the entire population screening efficiency in the high incidence area of esophagus cancer is effectively improved, the screening cost is greatly reduced, pain of partial population caused by an invasive gastroscope is effectively avoided, and the method has significant economic and social benefits and is worthy of popularization and application.

The invention relates to the field of the medical endoscope (gastroscopy and colonoscopy) inspection technology, in particular to accurate measurement of the size of a nidus under an endoscope. An open jaw of measurable biopsy forceps is introduced as a reference substance.The length between the two ends of the open jaw of the biopsy forceps outside a body is measured in advance. The jaw of the biopsy forceps is placed on the same plane as the nidus. The distance from the plane where the jaw of the biopsy forceps is located to a lens of the endoscope is made to be equal to the distance from the plane where the nidus is located to the lens of the endoscope. The pixel value between the two ends of the jaw of the biopsy forceps under the endoscope and the pixel value of the radial line of the nidus are measured through software, and then the physical size of the radial line of the nidus can be calculated.

A method for diagnosing a gastric lesion from endoscopic images is provided. The method comprises: acquiring a plurality of gastric lesion images; generating a dataset by linking the plurality of gastric lesion images with patient information; preprocessing the dataset in a way that is applicable to a deep learning algorithm; and building an artificial neural network by training the artificial neural network by using the preprocessed dataset as input and gastric lesion classification results as output.

The invention discloses a microvascular distortion degree quantification method for gastric mucosa dyeing amplification imaging. The method comprises an image segmentation method, a blood vessel center line extraction method and a surface density method. The image segmentation method is used for extracting a clear area and a microvessel whole image in the gastroscope image; the blood vessel center line extraction method is used for extracting the center line of each microvessel and calculating the perimeter of the microvessel corresponding to a pixel point on the center line; according to the surface density method, calculating the surface density by projecting the perimeter of the microvessel to the minimum circumscribed cubic surface of the microvessel; and finally, weighting the surface densities of different surfaces of the minimum microvessel circumscribed cube to obtain a microvessel distortion degree coefficient, and then judging the microvessel distortion degree grade according to the distortion degree coefficient.

The invention discloses a gastric mucosa cleanliness evaluation method and system based on deep learning. The method comprises the following steps: acquiring a gastroscope video frame in real time; performing cleanliness evaluation frame by frame based on a pre-constructed gastric mucosa cleanliness evaluation model; wherein a method for creating the gastric mucosa cleanliness evaluation model comprises the following steps of acquiring a gastroscope training image set; marking and scoring each training image according to a preset gastroscope cleanliness evaluation system; and training the gastric mucosa cleanliness evaluation model based on a deep learning network by adopting the training image set. The gastric mucosa cleanliness can be accurately evaluated, and a positive effect is achieved for diagnosis of gastric diseases and preparation and quality control before endoscopy.

The invention discloses a gastroscope tube fixing device for the digestive department. The device comprises a top plate, an arc-shaped plate is mounted on one side edge of the top plate, a baffle is mounted in the middle of the top end of the top plate, one end of the baffle extends to the upper part in the arc-shaped structure of the arc-shaped plate, fixing strips are installed at the ends, awayfrom the top plate, of the arc-shaped plates, one side edge of each fixing strip is provided with a magic tape, sleeve rods I are symmetrically mounted on one side edge, far from the arc-shaped plate, of the top plate, threaded rods are mounted at the bottoms of the sleeve rods I, the tops of the threaded rods extend into the sleeve rods I, mounting grooves are formed in the bottom ends of the interiors of the sleeve rods I correspondingly, threaded sleeves matched with the threaded rods are mounted in the mounting grooves correspondingly, first gears are mounted at the bottoms of the threaded sleeves correspondingly, and the threaded sleeves and the first gears are arranged on the outer sides of the threaded rods in a sleeving mode correspondingly.

The invention provides a gastrointestinal disease model construction method and a diagnosis system. The diagnosis system comprises an image acquisition unit, an image labeling unit, an image databaseconstruction unit, an image recognition unit and a data output unit, wherein the image database construction unit comprises a normal image feature library and a focus image feature library, and the image recognition unit comprises a focus type recognition model. Firstly, a normal image feature library of a normal gastroscope image and a plurality of lesion image feature libraries of a lesion gastroscope image are constructed; a focus type identification model is used; color feature and texture feature fusion is carried out on a gastroscope image to be detected, matching and recognition are carried out on the gastroscope image to be detected, a normal image feature library and a focus image feature library in sequence, whether the gastroscope image to be detected contains focuses or not andfocus types are output, and therefore the focuses with various stomach types can be recognized rapidly and accurately.

Provided is a gastroscopy apparatus used for a digestive system department. The gastroscopy apparatus comprises a flexible hose. The flexible hose is formed by an outer pipe and an inner pipe. The inner pipe is in the outer pipe. A fiberscope is arranged in the inner pipe. The fiberscope can pass through the inner pipe. The periphery of the bottom end of the outer pipe is fixedly provided with four air bags. The top end of the outer pipe is fixedly connected with a gas-filling device. The four air bags uniformly distribute with the center of the outer pipe as the center. The air bags are communicated with the internal of the outer pipe. The bottom end of the inner pipe is internally fixedly provided with a plurality of vertical sleeves. The bottom end of the sleeve is open and is flushed with the bottom end face of the inner pipe. The plurality of sleeves uniformly distribute with the center of the inner pipe as the center. The middle part of the top end of the sleeve is provided with a hole. Inner walls on two sides of the top end of the sleeve are respectively fixedly connected with the top ends of vertical spring pieces which are in a tightened state. The bottom ends of the two spring pieces are fixedly connected through a string. Inner walls on the bottom end on two sides of the sleeve are respectively fixedly provided with limiting blocks. After the air bag is aerated and expands, the air bag can contact with inner wall of an esophagus, so the position of the fiberscope is fixed and a lesion site can be observed.

The invention provides a helicobacter pylori auxiliary detection system and detection device. The system comprises a data receiving unit, an image feature extraction model, a region recognition model, a data processing unit and a helicobacter pylori recognition model. The data receiving unit is used for receiving information data and a plurality of gastroscope images of a to-be-tested person; the image feature extraction model is used for performing feature extraction on each gastroscope image to obtain expression features of each gastroscope image; the region recognition model is used for performing intragastric region recognition on each gastroscope image to obtain an intragastric region corresponding to each gastroscope image; the data processing unit is used for calculating a first feature value of the to-be-tested person according to the expression features of each gastroscope image and the corresponding intragastric region, and is also used for calculating a second feature value of the to-be-tested person according to the information data; and the helicobacter pylori recognition model is used for recognizing helicobacter pylori according to the first feature value and the second feature value of the to-be-tested person. The system and the device can accurately detect helicobacter pylori and are high in safety.

The invention belongs to the field of medical equipment and particularly relates to a medical tool, namely a detachable gastroscope cannula with an inflatable airbag, which performs gastroscopic examination and surgery according to the modern medicine. The detachable gastroscope cannula comprises an inner pipe and an outer pipe, wherein the length of the outer pipe is smaller than that of the inner pipe; the front end and the rear end of the inner pipe extend out of the outer pipe; the middle part of the inner pipe protrudes, the outer diameter of the middle protruding part of the inner pipe is greater than those of other pipe sections of the inner pipe, meanwhile, the outer diameter of the middle protruding part of the inner pipe is greater than the inner diameter of the outer pipe, and the outer diameters of the other parts except for the middle protruding part of the inner pipe are smaller than the inner diameter of the outer pipe; the middle protruding part of the inner pipe is sleeved with an inflatable rubber ring; the inflatable rubber ring is fixedly connected with the inner pipe; and the middle protruding part of the inner pipe and the inflatable rubber ring are tightly nested with the outer pipe. According to the detachable gastroscope cannula, the detection rate of an early gastric cancer is improved, the operation efficiency is improved and the postoperative complications are reduced.

The invention discloses a gastroscope cleaning device for the digestive system department, and belongs to the technical field of medical instruments. The device comprises a box body, wherein a cleaning box is fixedly connected to the upper surface of the box body, a header pipe is fixedly mounted at the top of the cleaning box, and an air heater is fixedly mounted at one end of the top of the cleaning box. According to the gastroscope cleaning device for the digestive system department, a lifting mechanism, an annular pipe, a spray head, a Y-shaped pipe, a first water pump, a second water pump, an air heater, a first electromagnetic valve, a second electromagnetic valve and a third electromagnetic valve are matched with a PLC, automatic cleaning is achieved while the cleaning and sterilizing effects are guaranteed, the workload of cleaning personnel is reduced, a phenomenon that the cleaning personnel collides with a lens and related precision devices during cleaning is avoided, after cleaning is completed, drying treatment can be conducted in time, bacterium breeding caused after the lens is contaminated with external air is avoided, and a connecting mechanism is arranged to be matched with the rotary connector, so that the annular pipe is convenient to disassemble and assemble, and later maintenance is facilitated.

The invention discloses a gastroscope tube fixing device in a gastroenterology department. The device comprises a tooth cushion, wherein bearing tooth rods are arranged on a side surface of the toothcushion in an insertion manner; bearing plates are fixedly connected with back-to-back sides of the two bearing tooth rods; vertical push rods are fixedly connected with opposite sides of the two bearing plates; a bearing gear is connected between the two bearing tooth rods in a meshed manner; a hydraulic block is rotationally connected with one end, far away from a ratchet wheel, of a compressionrod; a hydraulic cylinder is connected with a side surface of the hydraulic block in a sliding manner; a deviation rod is rotationally connected with a side surface of the compression rod; a pneumatic rod is rotationally connected with one side, far away from the compression rod, of the deviation rod; an airbag is fixedly connected with the bottom of a pneumatic tube; and a liquid storage tank isfixedly connected with a side surface of the pneumatic tube. By adopting the gastroscope tube fixing device in the gastroenterology department, through cooperation of the tooth cushion and an extrusion rod, effects that a gastroscope is fixed in case of regurgitation of a patient, and in addition, the head of the patient does not need to be fixed from an outer side, can be achieved.

The invention provides a blood vessel segmentation method, a terminal and a computer readable storage medium. The method comprises the steps: obtaining a dark channel of an original image obtained after gastric mucosa is dyed and amplified in advance, and obtaining a first gastric mucosa image; performing first image quality enhancement processing on the original image based on the first gastric mucosa image to obtain a second gastric mucosa image; performing blood vessel segmentation on the second gastric mucosa image to obtain a first blood vessel segmentation image; and repairing the first blood vessel segmentation image to obtain a target blood vessel segmentation image. According to the method, the requirement for the quality of a gastroscope image is not high, the method is not sensitive to the image brightness and the image contrast, a good segmentation effect is achieved, further, the segmented image is repaired, the accuracy of the image is improved, and the situation that a doctor misdiagnoses due to the image quality problem is avoided.

The invention belongs to the technical field of flexible robots and particularly discloses a flexible robot made of a composite material. The flexible robot comprises uniformly arrayed unit connectors, each unit connector comprises a polymer composite corrugated pipe and connection clamping rings located at the two ends of the polymer composite corrugated pipe, the polymer composite corrugated pipes are bonded to the connection clamping rings through adhesives, every two adjacent unit connectors are connected by a cross connecting pin, and each cross connecting pin comprises an outer supporting ring; four insertion connecting pins are connected to the outer wall of each outer supporting ring at equal intervals, the connection clamping rings are clamped on the corresponding insertion connecting pins, four tracheal supporting rings are connected to the inner wall of each outer supporting ring at equal intervals, and a wire clamping ring is supported between every four corresponding tracheal supporting rings. According to the scheme, by adding a new material into equipment of the flexible robot, the new material can be used in gastroscope inspection in the medical field. Through use of the composite material, the service life of the equipment is prolonged, and the accuracy of traditional gastroscopes is improved.

The invention belongs to the technical field of medical equipment, and particularly relates to an endogastric biopsy Raman image auxiliary diagnosis method and system based on artificial intelligence. The artificial intelligence technology is applied to gastroscope stimulated Raman scattering endoscopic biopsy tissue image auxiliary diagnosis for the first time, and the method comprises the step: after histopathology image information is obtained by means of the stimulated Raman scattering microimaging technology, adopting the image classification and image omics data analysis based on a deep learning neural network and machine learning, and constructing an endogastric biopsy Raman image auxiliary diagnosis system. The system comprises a stomach tissue Raman image data preprocessing module, a neural network model, an algorithm module for training the neural network model, a neural network fine tuning module and a test module; compared with an existing traditional endoscope diagnosis and treatment system, the system has the advantages that real-time, rapid and intelligent diagnosis support in the endoscope examination process is achieved, and pathologists do not need to conduct explanation.

The invention discloses a novel cleaning nursing device for a digestive gastroscope. The device comprises a support frame, a servo motor and an ultraviolet sterilization lamp, the servo motor is mounted in the right side of the supporting frame, a threaded sleeve is arranged on the outer side of a screw rod, the tail end of the adjusting rod is connected to a mounting plate, a connecting cover isarranged on an outer box, a spray head penetrates through the interior of the connecting cover, an inner box is arranged on the outer side of the bottom of the spray head, a first clamping plate is installed above the bottom of the inner box, a reset spring is connected to the left side of a second clamping plate, a first adjusting block is arranged below the inner box, a hand wheel is installed on the right side of the second adjusting block, an ultraviolet sterilization lamp is arranged in a disinfection box, and a connecting pipe is connected to the rear portion of the disinfection box. According to the novel cleaning nursing device for the digestive gastroscope, the height is convenient to adjust, the device is convenient for people with different heights to use, the gastroscope is convenient to stably clamp, and the gastroscope is convenient to clean in all directions.

The invention discloses an auxiliary device for gastroscopy and belongs to the technical field of medical equipment. The auxiliary device comprises a pair of braces in up-down symmetric distribution,a gastroscope body is arranged on the right sides of the braces, an examination tube is mounted at the upper end of the gastroscope body, a pair of supporting plates in up-down symmetric distributionare arranged between the two braces, multiple positioning columns are fixedly connected at one end, close to the supporting plates, of the braces, multiple positioning grooves matched with the positioning columns are formed in one ends, close to the braces, of the supporting plates, the positioning columns extend into the positioning grooves, and each two positioning grooves are connected througha torsional spring. Expansion supporting of the oral cavity of a patient in the process when the examination tube is inserted into the stomach of the patient can be realized, so that smooth insertionof the examination tube is ensured effectively. In addition, when the examination tube is inserted into the stomach of the patient, the examination tube can be fixed to a certain degree, so that serious disturbance caused to the examination tube by stress reaction of the patient is avoided effectively.

The present disclosure relates generally to a simplified transesophageal echocardiography (TEE) probe mid-handle assembly for actuating the pull cables that control the flexion of the distal end of the gastroscope portion of a TEE probe. The assembly includes a containment frame, two control wheels, two coaxial shafts each coupled to one of the control wheels, with an elongated flexible member wrapped around each shaft. The elongated flexible members may be friction belts, timing ladders, pulley cables, timing belts, or drive tapes to translate the rotational motion of the control wheels into linear motion of the gastroscope pull cables. The assembly may also include a brake switch that, when engaged, applies a resistance to rotation of the shafts and control wheels. In some embodiments, control wheels and containment frame are made of molded plastic, and the elongated flexible members are made of elastomeric compounds moulded over Kevlar, nylon, or metal reinforcement members to reduce stretch and increase life.

The invention relates to an intelligent gastroscope image processing device, including a gastroscope device housing; a probe is arranged on one side of the gastroscope device housing; a 3D image display and a split screen touch display are arranged on the front side of the gastroscope device housing; the connected end of the split screen touch display is provided with an image editing unit; a PLCis arranged inside the housing; the PLC is internally provided with a coding classification unit; the input end of the PLC is provided with an image processing system and a data processing system; theinput end of the image processing system is provided with an image pickup module; the image pickup module is internally provided with an A coding unit; and the connection end of the image processingsystem is provided with a first database. The invention can perform color contrast and lesion feature contrast on the photographed picture through the setting of the image processing system, and the setting of a picture search engine can search lesion pictures uploaded on the network, conveniently assisting a doctor to quickly judge the condition, shortening the time for a patient to do the gastroscope and reducing the pain.

The invention discloses a noninvasive helicobacter pylori gene detection primer and kit and a preparation and detection method thereof. The kit comprises a specific primer, a PCR (Polymerase Chain Reaction) amplification method with simple steps is adopted, the sample is subjected to noninvasive collection and manufacture, and pain of patients in the detection process is lightened. The defects in the prior art are overcome; the invention provides a simple, rapid and sensitive noninvasive helicobacter pylori gene detection kit and a preparation and detection method thereof. The method is simple in steps, the kit is a kit for sensitively detecting the helicobacter pylori, invasive sampling by using gastroscope and the like is avoided, the pain of the patients during detection can be reduced, and the time and cost of manpower and material resources are greatly reduced.

The invention relates to a gastroscope video part recognition network structure based on Transformer. On the basis of feature extraction of a convolutional neural network, the relationship between video frames in a time sequence is fused through a Transform structure, so that the accuracy of video recognition is improved. Compared with 2DCNN classification which can only pay attention to information of a single picture, and 3DCNN convolutional network which is relatively high in parameter quantity and can only pay attention to local time channel information, the structure has the advantages that information between frames is aggregated by utilizing an attention structure of transformer, so that the classification result is more accurate, and the classification precision during gastroscope video identification can be effectively improved. The position of the gastroscope is positioned in real time under endoscopic examination, and the category of the alimentary canal part in the video is accurately recognized. The structure assists a doctor in gastroscope shooting and diagnosis, improves the overall gastroscope video shooting quality, carries out sampling for subsequent pathology examination, and has significant significance and actual function requirements.

The invention relates to a multifunctional gastroscope endoscope used for stomach cancer diagnosis. The multifunctional gastroscope endoscope comprises a probe, a connecting tube and a hand grip. Theconnecting tube is arranged at one end of the probe, the hand grip is arranged at one end of the connecting tube, the probe and the hand grip are connected through the connecting tube, water outlet holes are formed around the outer side wall of the probe, a stomach cancer diagnosis device is arranged at the bottom end of the probe, a video probe and an illuminating lamp are arranged between the water outlet holes and the stomach cancer diagnosis device, the illuminating lamp is arranged at the bottom of the video probe, and a microprocessor is arranged in the probe. One cleaning mechanism is designed on the multifunctional gastroscope endoscope so as to solve the problem that when an existing gastroscope endoscope used for stomach cancer diagnosis is used for diagnosing a stomach cancer, foods often gather on the surface of the gastrointestinal mucosa of a patient because of diseases, and as a result great influences are generated when local lesions of the gastrointestinal mucosa are observed and treated under the endoscope.