753results about "Gastroscopes" patented technology

The invention relates to a painless gastrointestinal endoscope self-adaptive drug delivery method and system based on multi-source physiological signal fusion, and belongs to the technical field of medical artificial intelligence and automatic control. An artificial intelligence model is utilized to deeply extract features and quantitatively evaluate the sedation-analgesia level of a patient, a pharmacokinetics-pharmacodynamics model constructed by a big data platform is utilized to dynamically predict the drug effect according to the individual features and real-time state of the patient, and the anesthetic infusion rate is automatically and accurately adjusted through a closed-loop control algorithm, so that the patient can be accurately infused. Personalization and self-adaption of drug delivery are achieved, an independent safety monitoring mechanism is set, and real-time intervention is conducted on risk events such as respiratory depression. The problems that traditional anesthesia depends on artificial experience, single parameter monitoring is not comprehensive and individualized dynamic adjustment is lacked can be effectively solved, and the safety, comfort and medical efficiency of painless gastrointestinal endoscopy are remarkably improved.

Systems, devices, and methods for planning an endoscopic tissue acquisition procedure for acquiring tissue from an anatomical target are disclosed. An endoscopic system comprises a steerable elongate instrument and a processor. The steerable elongate instrument can be positioned and navigated in a patient anatomy and acquire tissue from an anatomical target via a biopsy tool associated with the steerable elongate instrument. The processor can receive an image of the anatomical target, apply the received image to a trained machine-learning (ML) model to determine a tissue acquisition plan that includes a recommended biopsy tool and operational parameters for navigating the steerable elongate instrument or maneuvering the recommended biopsy tool. The tissue acquisition plan can be presented to a user, or used to facilitate a robot-assisted tissue acquisition procedure.

The application discloses a multi-marked endoscopic imaging lens for digestive tract, and belongs to the field of biomedical microscopic endoscopic imaging. The endoscopic imaging lens comprises a first lens, a second lens, a third lens, a fourth lens, a fifth lens, a sixth lens and a seventh lens; the first lens focuses laser; the second lens is matched with the first lens to limit a light beam in an effective light aperture of the lens; the third lens corrects chromatic aberration; the fourth lens and the fifth lens are combined to correct aberration; the sixth lens adopts an aspheric lens to correct spherical aberration caused in a collimating and focusing system; and the seventh lens is matched with the sixth lens to correct chromatic aberration. The working spectral range of the microscopic objective lens group is 488-860 nm, the effective light aperture is less than 1.8 mm, the mechanical outer diameter is not greater than 2.6 mm, the numerical aperture at the object side or the tissue is 0.55, the imaging field of view is 450 microns, the magnification is 2.14 times, and the working distance is 84 microns. The effect of matching excitation and fluorescence spectrum of a clinically available fluorescence contrast agent is realized.

The invention provides an intelligent stomach tube based on optical fiber sensing and image monitoring, and the stomach tube comprises a stomach tube body which is internally integrated with an optical fiber and a miniature camera assembly; at least three FBG (Fiber Bragg Grating) sensing nodes which are respectively positioned in the stomach, the esophagus and the throat section are inscribed on the optical fiber and are used for acquiring pressure and temperature signals; the miniature camera assembly is arranged on the inner wall of the throat section and used for collecting images. A demodulation-edge AI processing terminal is arranged outside the body, connected with the sensing nodes and the camera shooting assembly and used for demodulating signals and conducting multi-mode fusion analysis on the basis of pressure signals and image data, real-time judgment of the situation that the catheter enters the airway by mistake, intelligent evaluation of the risk of aspiration before catheter drawing and early warning output when the risk exceeds the standard are achieved. According to the invention, the FBG sensing node and the miniature camera shooting assembly are integrated in the stomach tube, and the in-vitro demodulation-edge AI processing terminal is combined, so that precise and automatic monitoring and early warning of the whole process from tube indwelling to tube drawing evaluation are realized, and the safety and the medical quality of a patient are fundamentally improved.

The invention provides a Y-shaped collaborative operation device for a digestive endoscope and an optical fiber clamping-three-dimensional force sensing method, and relates to the technical field of optical fiber sensing detection. The Y-shaped expanding opening and closing assembly is fixedly connected with the tail end of the main endoscope arm and used for expanding the two corresponding second channels to be opened and closed in a Y shape; the two sub-operation arms penetrate through the two second channels corresponding to the sub-operation arms and extend to the outer portion of the Y-shaped expanding opening and closing assembly, and the sub-operation arms are provided with a plurality of third channels arranged in the circumferential direction; the second driving guide wire penetrates through the third channel from the front end of the sub-operation arm and is fixedly connected with the tail end of the sub-operation arm, and the bending direction of the sub-operation arm is adjusted by controlling stretching and retracting of the second driving guide wire. And the clamping-three-dimensional force sensing operation assembly is fixedly connected with the tail end of the sub-operation arm and is used for sensing the three-dimensional force and / or the clamping force generated when the clamping-three-dimensional force sensing operation assembly interacts with the digestive tract tissue.

Provided are a split-type mask, a respiratory monitoring system, and a method of using the same, which are suitable for endoscopic examinations. The split-type mask includes a nasal mask body, an oral mask body, and a connector, wherein the nasal mask body and the oral mask body are connected by the connector. The nasal mask body is formed with an oxygen tube interface for connecting an external oxygen supply device to supply oxygen to the nasal mask body; the oral mask body is formed with an endoscope inspection port for passing an endoscopic examination device such as a gastroscope. The nasal mask body also includes a nasal pressure sensor and a nasal aspirator interface, respectively used to monitor the pressure within the nasal mask body and to aspirate aerosols within the nasal mask body, and / or the oral mask body also includes an oral pressure sensor and an oral aspirator interface, respectively used to monitor the pressure within the oral mask body and to aspirate aerosols within the oral mask body. The nasal mask body and the oral mask body are respectively adapted to fit the wearer's face without being connected to each other.

The invention relates to the technical field of guiding devices, in particular to a nasal jejunum nutrition tube imbedding guiding device which is used for guiding the process of imbedding a flexible nasal jejunum tube into a human body. The image acquisition device acquires a picture in the direction of the advancing direction of the insertion end of the nasal jejunum tube; the bag body is arranged in a manner of extending close to the insertion end of the nasal jejunum tube; during use, the bag body does not generate binding force on the nasal jejunum tube in a low-expansion state, the shape of the nasal jejunum tube is not limited by the bag body, when the bag body is in a high-expansion state, the bag body generates binding force on the nasal jejunum tube to enable the nasal jejunum tube to be bent, and the image acquisition device comprises a camera arranged in the insertion end of the nasal jejunum tube. The insertion end of the nasointestinal tube is provided with a closing part for preventing the camera from falling off, and the problem that the throat and the pylorus cannot pass through the nasointestinal tube quickly and smoothly in the existing nasointestinal tube indwelling process can be solved by improving the existing endoscope guiding technology.

The invention belongs to the technical field of medical instruments, and discloses a digestive endoscopy diseased region accurate positioning and marking device which comprises a controller, an endoscope hose is fixedly connected to the bottom of the controller, and an instrument insertion opening is formed in the right side of the controller. Through the arrangement of the sleeve, the dye tube, the pressurization air bag and the baffle, after an operator observes a diseased region through the endoscope hose, the operator only needs to align the endoscope hose to the diseased region, and by pressing the pressurization air bag, air in the pressurization air bag enters the dye tube through the inner hose; the baffle can be pushed to rotate outwards under the action of air pressure, meanwhile, methylene blue in the dye tube is sprayed out under the action of air flow, a diseased region is marked, the methylene blue can be absorbed by normal mucous membrane cells, and diseased tissue shows dyeing difference due to abnormal cell function and poor absorption capacity, so that the diseased region is marked. Therefore, the effect of accurate positioning is achieved.

The invention discloses a device and system for conducting electric field treatment on the digestive tract, the device for conducting electric field treatment on the digestive tract comprises a slender catheter, a supporting body located at the far end of the catheter, an electrode array film and a pulse generator, the electrode array film and the pulse generator are arranged on the supporting body, and the output end of the pulse generator is coupled with an electrode pair on the electrode array film. A sequence pulse wave output by the pulse generator comprises a plurality of groups of nanosecond pulse strings, and the time interval between the adjacent nanosecond pulse strings is 1us-10000 us; the nanosecond pulse string is composed of a plurality of nanosecond pulse pairs, and the time interval between every two adjacent nanosecond pulse pairs ranges from 50 ns to 10000 ns; the nanosecond pulse pair comprises positive pulses and negative pulses which appear alternately, the pulse width of the positive pulses and the pulse width of the negative pulses are 10-1000 ns, and the time interval is 10-1000 ns. The cell membrane permeability and the cell death efficiency can be remarkably improved, and the limitation of the traditional IRE technology is broken through.

The invention relates to a stomach tube track monitoring system and device, and the system comprises a track collection module which is used for obtaining the moving track of the insertion end of a stomach tube based on a real-time position; the trajectory analysis module is used for obtaining a real-time deviation between the target trajectory and the moving trajectory, and determining a deviation position and an adjustment angle according to the real-time deviation; the trajectory topological graph construction module is used for constructing a trajectory point cloud set according to the moving trajectory and determining an abnormal point set according to a trajectory topological graph group based on a continuous coherence mechanism; the real-time risk early warning module is used for synchronizing the moving track to a pre-obtained trachea-esophagus model and performing real-time risk early warning according to the position of the abnormal point set in the trachea-esophagus model; and the potential risk early warning module is used for inputting the real-time position into a preset trajectory prediction model to obtain a prediction trajectory at the next moment, and performing potential risk early warning according to the deviation between the prediction trajectory and the target trajectory.

This invention generally relates to a method for performing an endoscopic procedure. According to some aspects of the invention, the method comprises placing an endoscope shaft within a body cavity at a desired examination point, the endoscope shaft having a proximal end, mid shaft and a distal end, the distal end terminating in an endoscope tip, wherein the endoscope tip is proximal to the desired examination point, positioning a segment of a longitudinally opened overtube over the endoscope mid shaft, wherein the overtube including a longitudinal reclosable seam along an entire length of the overtube, an inner surface, an outer surface, a proximal end and a distal end, a positioning ring adjacent the distal end on the outer surface, at least one sealing band on the inner surface, and an independently positionable occlusion catheter terminating in an asymmetrical occlusion balloon; at least one handle at the proximal end and on the outer surface for grasping and manipulation of the overtube within the body cavity. The method further comprises closing the seam of the segment of the overtube positioned over the endoscope mid shaft to form a longitudinally closed overtube and move the closed overtube over the endoscope shaft as guide within the body cavity and repeat the closing and moving till the overtube reaches the desired examination point, inflating the positioning ring to create a seal between the outer surface of the overtube and a body cavity proximal to the endoscope tip, wherein when inflated the positioning ring expanded asymmetrically around the overtube, inflating the at least one sealing band to create a seal between the internal surface of the overtube and endoscope shaft, passing the independently positionable occlusion catheter terminating in the asymmetrical occlusion balloon through a passageway along the overtube to enter the body cavity at the end of the overtube, manipulating the independently positionable occlusion catheter to a selected point within the body cavity distal to the endoscope tip, inflating the occlusion catheter balloon to create seal between the occlusion catheter balloon and the body cavity, and creating a sealed examination compartment between the positioning ring, the asymmetrical occlusion balloon and the sealing band surrounding the distal end of the endoscope shaft.

The invention provides an objective image module and an endoscope, and relates to the technical field of endoscopes. The objective image module is provided with an optical axis and comprises a front fixed lens assembly, a rear fixed lens assembly, a movable lens assembly, a guide assembly and a driving assembly, and the front fixed lens assembly, the movable lens assembly and the rear fixed lens assembly are sequentially arranged on the optical axis. The guide assembly is in sliding fit with the movable lens assembly and used for limiting the sliding direction of the movable lens assembly so that the sliding direction can be parallel to the optical axis direction. The driving assembly comprises a permanent magnet and an electromagnet, and the permanent magnet is connected with the movable lens assembly; when the electromagnet is powered on, driving magnetic force is formed between the electromagnet and the permanent magnet, and the driving magnetic force can drive the movable lens assembly to move in the optical axis direction. The position of the movable lens can be accurately controlled, and the occupied internal space of the head end part is reduced.

One or more processors select a model from among a plurality of types of machine learning models according to a region whose image is being picked up by an endoscope, generate notification information of a type of the model selected, receive an instruction signal for switching the model, measure a time interval from a selection of the model to a reception of the instruction signal, select a model selected immediately previously when the time interval is less than a first predetermined time, and select a model scheduled to be selected immediately subsequently when the time interval is equal to or greater than a second predetermined time.

The device comprises a light source generator, a light source adjusting mechanism, a light source conveying pipe and a detection head, the light source adjusting mechanism comprises a mounting cylinder, a shaping sector ring light absorption part and a folding sector ring light absorption part, and the mounting cylinder is provided with a light-transmitting round hole penetrating front and back; an annular cavity is formed in the cylinder wall of the mounting cylinder with the center point of the light-transmitting round hole as the center of a circular ring, the multiple sets of shaping fan ring light absorption pieces are distributed in the annular cavity in the circumferential direction, and a set of folding fan ring light absorption pieces are arranged between every two adjacent sets of shaping fan ring light absorption pieces. The side wall of the folding sector ring light absorption piece is attached to the side wall of the shaping sector ring light absorption piece and is connected with the shaping sector ring light absorption piece in a front-back sliding mode along the attaching face, and the shaping sector ring light absorption piece is arranged in the annular cavity in a front-back sliding mode in the direction of the left-right symmetry line of the shaping sector ring light absorption piece. And the transverse unfolding area of the folding fan ring light absorption parts is adjusted along with the adjustment of the distance between the two adjacent groups of shaping fan ring light absorption parts.

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

The application provides a multifunctional catheter, comprising a catheter main body and a distal tube with a multi-cavity tube structure. The distal tube comprises a soft end at the proximal end and a functional end at the distal end. The catheter main body and the soft end are provided with a working cavity and a lens cavity. The functional end is further provided with a through hole communicating with the lens cavity. The lens cavity is a circular tube cavity structure extending along the catheter main body and the soft end. The inner wall of the lens cavity is provided with a plurality of accommodation grooves for accommodating photosensitive chips in a lens assembly. The catheter provided by the application can form a space for accommodating photosensitive chips through the plurality of accommodation grooves in the lens cavity, and the lens assembly can be installed without increasing the diameter of the lens cavity, thereby reducing the overall diameter of the catheter to adapt to the more complex bile duct environment relative to the digestive tract.

An endoscope add-on assembly adapted to be attached to a target endoscope. The endoscope add-on assembly includes an ultrasound imaging head, an ultrasound imaging sub-assembly, and a needle guide ramp. The ultrasound imaging head defines an imaging slice plane. The ultrasound imaging sub-assembly is configured to selectively engage the ultrasound imaging head. The ultrasound imaging sub-assembly includes a retaining element configured to secure the ultrasound imaging sub-assembly to the target endoscope. The needle guide ramp is configured to direct a motion of a needle of the target endoscope. The needle guide ramp is configured to align the needle of the target endoscope within the imaging slice plane when the endoscope add-on assembly is attached to the target endoscope.

The invention relates to an intelligent target detection method and system for a gastroscope image, and the method comprises the steps: carrying out the multispectral decomposition of an obtained gastroscope image, and generating a standardized image in combination with a dynamic domain adaptation strategy; based on the standardized image, adopting a multi-scale geometric perception feature extraction network to extract fusion features; carrying out anatomical position sensing processing on the fusion features to generate position sensing features with anatomical region identification capability; on the basis of the position sensing features, morphologically-guided multi-task target detection and classification are executed, and a multi-task detection result is obtained; the multiple tasks comprise focus detection, focus boundary segmentation and focus type classification; aiming at a multi-task detection result of continuous image frames in the gastroscopy process, applying a time sequence consistency constraint, and generating a space-time optimization result; and constructing an uncertainty perception mechanism based on a space-time optimization result, and outputting a calibrated target detection result. The precision of gastroscope image detection can be improved.

The invention belongs to the technical field of endoscopic surgical instruments, and provides a foreign matter taking device under an endoscope. The device comprises a shearing mechanism and a clamping mechanism, the shearing mechanism is parallel to the clamping mechanism, a pulling-out mechanism is arranged between the shearing mechanism and the clamping mechanism, the two ends of the pulling-out mechanism are connected with the shearing mechanism and the clamping mechanism respectively, the pulling-out mechanism comprises a first elastic body and a limiting column, and the limiting column is a column body with a protruding part on the side face; one end of the limiting column is fixed to the shearing mechanism, the other end of the limiting column makes contact with the limiting hole, the pulling-out mechanism further comprises a connecting column provided with threads, the connecting column is provided with a limiting block, and the clamping mechanism is provided with a first limiting hole matched with the section of the limiting column and a second limiting hole matched with the limiting block of the connecting column. Foreign matters penetrating the septum and the like can be pulled out perpendicular to the shearing plane, and secondary injury to a patient caused by force towards the mouth side is avoided; and the clamping part is subjected to special structural design, so that different types of foreign matters can be clamped.

The present disclosure relates to systems and methods for driving medical instruments. Certain aspects relate to systems and techniques for driving medical instruments having an inner body and an outer body. In one aspect, a system includes a medical instrument including an outer body and an inner body configured to be driven through a lumen in the outer body. The system can also include a set of one or more instrument manipulators configured to control movement of the outer body and the inner body, and a set of one or more processors configured to: receive a change drive mode command; and change a drive mode of the medical instrument from a paired drive mode to an unpaired drive mode in response to receiving the change drive mode command.

The invention discloses a guiding sheath tube and a biliopancreatic endoscope system. The guiding sheath tube comprises a sheath tube handle, an intervention sheath tube and a connecting piece, and the sheath tube handle is connected to the far end of an insertion tube fitting; the intervention sheathing canal is connected to the far end of the sheathing canal handle; the connecting piece comprises a deformation section, the near end and the far end of the connecting piece are connected to the side walls of the same sides of the operation main body and the sheathing canal handle respectively, so that at least the deformation section and at least partial pipe section of the insertion pipe fitting are arranged side by side, and when the insertion pipe fitting moves, the deformation section moves synchronously; and the deformation section is formed by sequentially connecting a plurality of sections of cross shaft universal joints. In the matching process of the biliopancreatic endoscope and the guide sheathing canal, the coaxiality of the biliopancreatic endoscope and the guide sheathing canal can be sufficiently guaranteed, so that the matching between the biliopancreatic endoscope and the guide sheathing canal is flexible and accurate, and finally the operation convenience and the use reliability of operators are improved.

A medical system (10) includes an insertion device (12) including a handle (22), an insertion portion (24) having at least one lumen, a port (38) fluidly coupled to the lumen, and a connection portion (18). The medical system also includes a medical device (14) including a handle (50), an insertion portion (52), and a connection portion (20) configured to be coupled to the connection portion of the insertion device. The connection portion of the medical device is configured to be coupled to the connection portion of the insertion device to form an electronic and physical connection between the insertion device and the medical device.

The invention discloses a tracheal catheter special for upper gastrointestinal endoscopic surgery, which comprises an inner tube, an outer tube capable of sliding up and down with the inner tube is sleeved outside the inner tube, the top end of the outer tube is fixedly connected with the inner tube through a fixing knob, a respirator joint is arranged at the top end of the inner tube, an inner tube water bag is arranged at the bottom of the inner tube, and an outer tube water bag is arranged at the bottom of the inner tube. An inner tube suction hole is formed in one side of the inner tube water bag, and a Murphy hole is formed in the position, located below the inner tube water bag, of the bottom of the inner tube. The problems that in an upper gastrointestinal endoscopic surgery in the prior art, the exposed part of the tracheal catheter affects surgical operation, the cuff of the tracheal catheter compresses a surgical site or affects taking out of a specimen, the tracheal catheter rubs with an endoscope and is prone to disengagement to damage tracheal mucosa, and blood and secretions in the trachea are not sucked thoroughly are solved.

The present invention relates to a system for producing optical radiation to neutralize microorganisms. The system comprises a light source (1) for emitting optical radiation, a storage means (2) having one or more unique identification codes each associated with a respective microorganism, at least one respective wavelength range associated with the microorganism, and a logic control unit (3) configured to select a wavelength range based on the microorganism to be neutralized and to activate the light source (1) such that the optical radiation emitted by the light source (1) has a wavelength within the selected wavelength range, such that, in use of the system, the optical radiation induces optical resonance in the microorganism and causes alteration of the genetic properties of the microorganism.

The invention relates to the technical field of medical instruments, in particular to a portable visual nasal gastrointestinal nutrition tube indwelling device which comprises an operation handle, an endoscope assembly, a guide wire and a shaping mechanism, and the endoscope assembly is connected to the operation handle, can be controlled by the operation handle and is used for checking conditions in the body of a patient; the endoscope assembly is sleeved with the nasal gastrointestinal nutrition tube when the nasal gastrointestinal nutrition tube is installed. The guide wire is inserted into the endoscope assembly and is used for supporting the endoscope assembly; the shaping mechanism is configured to enable the section shape of the nasal gastrointestinal nutrition tube with the curvature larger than a preset value to be recovered to be round and can also fix the shape of the nasal gastrointestinal nutrition tube with the curvature larger than the preset value. Therefore, on one hand, it can be guaranteed that the section of the nasal gastrointestinal nutrition tube is round and the blocking risk is avoided when the nasal gastrointestinal nutrition tube conveys nutrient solution or medicine, and on the other hand, elastic reset force generated at the bent position of the nasal gastrointestinal nutrition tube can be offset and the nasal gastrointestinal nutrition tube is prevented from continuously jacking mucous membranes and tissues in the human body.

The invention provides a positioning device for an alimentary canal lesion endoscope, and relates to the technical field of alimentary canal endoscopes, the positioning device comprises an endoscope pipeline, an adjusting mechanism facilitating adjustment is arranged on the endoscope pipeline, a supporting mechanism facilitating positioning is arranged on the endoscope pipeline, and the adjusting mechanism comprises a protective hollow column and a mounting column; the supporting mechanism comprises an endoscope probe, a first adjusting pipe and a suction cup, the protective hollow column is slidably mounted at the circumferential end of the endoscope pipeline, and the mounting column is fixedly mounted at the circumferential end of the endoscope pipeline. By arranging the umbrella type supporting structure composed of the first adjusting tube, the second adjusting tube and the universal joint, the actual interior of the digestive tract is not a flat environment, natural wrinkles exist on the stomach wall, the intestinal mucosa fluctuates in a concave-convex mode, and individual differences exist in the forms of the digestive tracts of different patients; the multi-point supporting design of the umbrella type structure enables a plurality of supporting point positions to be respectively attached to mucous membranes at different positions around the focus.

A medical device may comprise a plurality of prongs, each of the prongs having a sensor configured to detect a flow of fluid; and a sleeve disposed radially outward of the plurality of prongs. The sleeve may be configured to move proximally and distally relative to the plurality of prongs to transition the plurality of prongs from a contracted configuration to an expanded configuration.

Endoluminal robotic systems and corresponding methods include subsystems for visualization, navigation, pressure sensing, platform compatibility, and user interfaces. The user interfaces may be implemented by one or more of a console, haptics, image fusion, voice controls, remote support, and multi-system controls.

A system for performing procedures in a body lumen comprises an outer member which comprises a first lumen to receive an endoscope. A system for performing procedures in a body lumen also comprises a first flexible element and a second flexible element. The second flexible element is moveable laterally outwardly to atraumatically contact a side wall of the body lumen to alter a space within the body lumen. A system for performing procedures in a body lumen further comprises an actuator which is positioned at a proximal region of the outer member and operably coupled to the second flexible element to effect movement of the second flexible element between a reduced profile position and an expanded position.

The application discloses a gastroscope in-vivo residence time detection method based on deep learning, relates to the technical field of gastroscope detection, and comprises the following steps: acquiring an in-vivo and in-vitro environment two-classification data set; constructing a two-classification network based on a Vision Transformer; training the two-classification network based on the Vision Transformer by using the in-vivo and in-vitro environment two-classification data set; for a complete gastroscope video frame sequence to be detected for gastroscope in-vivo residence time, extracting a frame as a representative frame every certain number of intervals, feeding all the representative frames into the trained two-classification network based on the Vision Transformer for classification, searching for the last group of in-vivo frame sequence numbers Id_a from in-vitro to in-vivo and the last group of in-vivo frame sequence numbers Id_b from in-vivo to in-vitro, and calculating the gastroscope in-vivo residence time. The application has high automation processing level, does not need additional manual processing in the whole process, can greatly reduce workload and improve time efficiency, and can avoid missing and misreading caused by careless artificial retrospective observation in the traditional method.