6873 results about "Endoscopy" patented technology

The invention discloses a robust polyp segmentation method based on improved SAM-Med2D, and the method comprises the following steps: S1, generating a record file for a given data set; s2, constructing an SAM-Med2D model, and keeping the aspect ratio of a non-square image; s3, extracting multi-scale features of the image through a double-branch encoder; s4, in a mask decoder, carrying out fusion processing on the multi-scale features; s5, generating a preliminary segmentation result based on the fusion feature and the prompt code; s6, constructing a lightweight reverse attention refinement module; s7, carrying out loss calculation and parameter optimization on the SAM-Med2D model; and S8, polyp segmentation of the current image is ended, the next image is entered, and the steps from S1 to S7 are repeatedly executed. According to the method, the ViT-CNN double-branch structure and the reverse attention mechanism are fused, so that high-precision and low-calculation-overhead robust segmentation of the polyp area in a complex endoscope scene is realized.

The invention discloses a Transform-CNN medical image segmentation method and system based on multi-scale fusion semantic enhancement, and relates to the technical field of image segmentation, and the method comprises the steps: collecting medical image data, and constructing a medical image data set; constructing a medical image segmentation network model; training the medical image segmentation network model through the medical image data set; and inputting real-time acquired data into the trained medical image segmentation network model to obtain a medical image segmentation result. According to the invention, double encoders, LGDA modules and the like are adopted to capture multi-scale global features of kidney tumors and enhance representation, and the LGDA module is used for adapting to size and form changes of the kidney tumors; the MLCF module is used for supplementing information of the main encoder; the PSE module captures multi-scale global semantic information and integrates local context information, local features are fused through the SAM module, and kidney tumor positioning in an endoscope image is achieved.

To provide an endoscope system for calculating a region of a subject with a high degree of recognition precision while performing endoscopic observation, and to provide an operation method thereof.SOLUTION: An endoscope system 10 includes an endoscope 11, an air supply device 16, and a processor. The processor controls emission of illumination light for illuminating a subject S and measurement light for measuring a distance between a plurality of places of the subject S and the endoscope 11. The measurement light is emitted with a first air supply amount, the subject S is imaged by emitting or turning off the illumination light with a light amount suppressed with respect to the measurement light, and a region of the subject S is calculated from acquired first distance information. The measurement light is emitted with a second air supply amount, the subject S is imaged by emitting or turning off the illumination light with a light amount suppressed with respect to the measurement light, and a region of the subject S is calculated from acquired second distance information.SELECTED DRAWING: Figure 7

The invention provides a front end assembly, an endoscope and an endoscope hydraulic control system, and belongs to the technical field of endoscopes. The front end assembly comprises a front end base, a camera module and a pressure measuring mechanism, the camera module and the pressure measuring mechanism are both installed on the front end base, the pressure measuring mechanism comprises a piezochromic layer, the piezochromic layer is located at the circumferential position of the camera module, the piezochromic layer is made of a piezochromic material, and at least part of the piezochromic layer is located in an image acquisition area of the camera module. The front end seat is provided with the pressure measuring mechanism, and the pressure measuring mechanism is used for detecting the pressure around the front end assembly, so that the accuracy of pressure adjustment in a body cavity is improved, the hysteresis of pressure adjustment in the body cavity is reduced, the amplitude of pressure fluctuation in the body cavity is reduced, and the surgical risk is reduced; the pressure information in the body cavity is judged by observing the color information of the piezochromic layer in the image information collected by the camera module, an operator can adjust the pressure in the body cavity in time, and the overall operation is simple and convenient.

The invention relates to an endoscope image reflection restoration method based on detection network and filtering fusion, and belongs to the technical field of medical image computer processing. The method aims at improving detection and removal of specular reflection in an endoscope image, a variant of TransUnet is adopted in the detection stage, and U-Net and Transform architectures are combined; the method comprises Atrous spatial pyramid pooling (ASPP), information bottleneck (IB) and a convolutional block attention module (CBAM). The enhancement functions improve the identifiability of specular highlight and solve the problem of weak generalization in endoscope data concentration. In the removal stage, the invention designs an enhanced median filtering module for removing specular reflection. The module first applies Gaussian blur to the repaired region and then calculates color information from the non-reflective region. According to the method, mirror reflection is effectively eliminated from the endoscope image, clearer and more accurate visual information is provided for clinicians, and improvement of diagnosis precision is facilitated.

This specification describes systems and methods for performing endoscopy, obtaining medical images for inflammatory bowel disease (IBD) and scoring severity of IBD in patients. The methods and systems are configured for using machine learning to determine measurements of various characteristics related to IBD. The methods and systems may also obtain and incorporate electronic health data of patients along with endoscopic data to use for scoring purposes.

The invention discloses an endoscope with a built-in grabbing mechanism, and relates to the technical field of medical instruments. According to the technical scheme, the device comprises a clamp assembly, a driving outer pipe and a driving inner wire; the grabbing mechanism further comprises a grabbing mechanism shell, a first moving seat and a second moving seat, wherein the first moving seat and the second moving seat are arranged in the grabbing mechanism shell. The near end of the driving outer tube is connected with the first moving seat, and the near end of the driving inner wire is connected with the second moving seat; when the second moving seat is fixed relative to the grabbing mechanism shell, the first moving seat moves towards the far end direction relative to the grabbing mechanism shell so as to control the clamp assembly to execute the clamping action. According to the invention, the clamping action is carried out while forward extension is carried out, so that high-precision operation is facilitated, and tissues can be accurately clamped; and moreover, the grabbing mechanism is integrated in the endoscope handle, so that accurate single-hand control is facilitated, meanwhile, the clamping action is controlled in a button mode, the human engineering is met, and operation is convenient.

To provide an optical system capable of enhancing coupling of light from a light source to an optical fiber, particularly an optical system that can be incorporated into medical instruments such as endoscopes.SOLUTION: There is provided an optical system. The optical system comprises a lens including an input surface for receiving light from at least one light source and an output surface through which the light exits the lens, the lens further including a peripheral surface extending between the input surface and the output surface and configured to direct, via total internal reflection, at least a portion of the light incident thereon through the output surface to an output focal point. The optical system can further comprise a tapered light pipe optically coupled to the lens and a light guide (e.g., one or more optical fibers) that is optically coupled to the tapered light pipe. The lens directs the received light to an output focal point that is disposed within the tapered light pipe.SELECTED DRAWING: Figure 3A

The invention relates to the technical field of oral medical treatment, in particular to an oral disease analysis method and system based on AI intelligent recognition. Comprising the following steps that oral cavity three-dimensional surface data are obtained through an oral scanning module integrated with a dental chair, and the oral scanning module adopts a structured light coding and multi-view fusion algorithm; an oral soft tissue high-definition image is collected through an endoscope module, and an AI analysis unit is arranged in an endoscope to recognize mucous membrane lesion features in real time; calling CBCT image data of the patient, and aligning a three-dimensional image with oral scanning data through a spatial registration algorithm; the mouth scanning data, the endoscope image and the CBCT data are subjected to multi-modal fusion by adopting a dynamic weight fusion mechanism. According to the scheme, the problem of accurate registration of cross-modal data, the lack of a dynamic quality evaluation mechanism of heterogeneous data and the real-time collaboration bottleneck of dispersed equipment can be solved.

The utility model provides a traction wheel driving assembly and an endoscope, relates to the technical field of endoscopes, and solves the problems that in the prior art, an assembly structure of a traction wheel and a shifting part is complex, and the cost is high. The traction wheel driving assembly adopted by the endoscope comprises a mounting shell, a traction wheel and a turntable, the mounting shell is provided with a mounting hole; the traction wheel is rotatably arranged on one side of the mounting shell and is provided with a positioning hole; the rotating disc is rotationally buckled to the mounting shell, and a positioning column is arranged at one end of the rotating disc, penetrates through the mounting hole and is matched with the positioning hole in a rotation stopping and inserting mode. According to the utility model, the turntable is rotationally connected to the mounting shell in a buckling manner, and the positioning columns arranged on the turntable are inserted into the positioning holes in the traction wheel to realize rotation stopping connection, so that torque is transmitted to the turntable. A rotating shaft does not need to be arranged, so that the connecting structure and the assembling complexity of the traction wheel and the rotating disc are simplified.

The invention relates to the field of integrated optical fiber microscopic endoscopy, in particular to an all-optical-fiber light beam modulation and collection system based on double super lenses and a design method of the all-optical-fiber light beam modulation and collection system. The system comprises a single-mode optical fiber, a coreless optical fiber for beam expansion and two super lenses (a super lens 1 and a super lens 2) with different functions. The super lens 1 is arranged on the end face of the fiber core of the single-mode optical fiber and focuses output exciting light to form extremely small waist spots, and the divergence angle of light beams is increased. The super lens 2 is arranged on the end face of the coreless optical fiber beam expanding area and used for refocusing the exciting light and focusing the collected fluorescence to the focus position of the super lens 1 at the same time, and the fluorescence is incident to the fiber core in parallel through the super lens 1. According to the invention, a double-super-lens system based on a high numerical aperture (NA) is fully utilized, wavefront modulation is carried out, the length of a beam expanding area is adjusted, and the loss of fluorescence in the beam expanding area is reduced, so that the collection efficiency of the fluorescence is remarkably improved, and an innovative solution is provided for the design of a super-lens-based optical fiber optical system.

The invention provides an early-stage esophageal squamous carcinoma detection method and system based on deep learning, and relates to the technical field of image processing, and the method comprises the steps: obtaining an esophageal endoscope image, carrying out the enhancement processing, carrying out the multi-stage decomposition, generating a first image, carrying out the background separation of the first image, generating a region of interest, and carrying out the morphological filtering and edge extraction; generating a binary mask image and performing normalization processing to obtain a standard image; extracting semantic features of the standard image, performing pixel-level classification on the semantic features to obtain a region segmentation result, calculating morphological features and textural features of an esophageal squamous cell carcinoma region, performing classification to obtain an esophageal squamous cell carcinoma classification result, adding the esophageal squamous cell carcinoma classification result as an input feature into a first classification model, and judging esophageal tissues according to a judgment standard to obtain an esophageal squamous cell carcinoma classification result; generating a first judgment result, performing nonlinear mapping and classification to obtain a second judgment result, and performing fine segmentation to obtain an accurate boundary of the early esophageal squamous carcinoma tissue.

The invention discloses a surgical instrument segmentation method based on a double prior guidance network, and the method specifically comprises the steps: constructing a hybrid encoder composed of a visual basic model and a state space model, and carrying out the coding processing of an input surgical endoscope image; the visual basic model is an SAM2-Hira model; the state space model is a MambaVision model; an adapter layer composed of a standard adapter and a Mama enhancement adapter is arranged between the coding layer and the decoding layer, and coding features are processed; setting a multi-context guide decoder, and performing multi-scale feature recovery and mask segmentation; a hybrid encoder, a Mama enhancement adapter and a multi-context guidance decoder form a double-priori guidance network DPG-Net, and high-precision surgical instrument segmentation is realized by using the DPG-Net. Accurate visual support is provided for the surgical robot, and the accuracy and safety of surgical operation are greatly improved.

The invention relates to the field of oral medical diagnosis, and discloses an intraoral image-based AI enhanced real-time occlusion detection system, which comprises a multi-source intraoral image acquisition module for acquiring dynamic oral image data through a high-definition oral endoscope and recording a three-dimensional structure of a tooth surface by combining a laser scanning device, meanwhile, force distribution of an occlusion contact point is collected through a pressure sensor array; the multi-source intraoral image acquisition module comprises a timestamp synchronization unit and is used for performing multi-source synchronization on an oral image frame sequence and occlusal force distribution data by utilizing a unified timestamp; through the multi-source in-port image acquisition module, synchronous acquisition of dynamic images, three-dimensional structure data and bite force distribution is realized, and time sequence consistency of the data is ensured through timestamp marking. Compared with a traditional single data source collection mode, the multi-source collection can comprehensively record dynamic characteristics in the occlusion process, rich and accurate input is provided for subsequent AI analysis, and data missing or collection deviation is avoided.

The invention discloses an insertion part, an endoscope and a control system, and relates to the field of medical instruments.The insertion part comprises a camera module, an instrument tube and a marking structure, the camera module is arranged at the far end of the insertion part, the instrument tube is provided with an instrument channel, the instrument channel penetrates through the two opposite ends of the insertion part, and the instrument channel is used for circulating a medium; the marking structure is adjacent to the camera module, and the marking structure is used for marking the flow path of the medium in the field of view of the camera module. The instrument tube is used for injecting a medium, the sheath tube provides a suction environment, the marking structure can present a flowing path of the medium on the camera module, a medical worker can observe the flowing path of the medium through the camera module, and the marking structure visualizes the flowing path of the medium. Furthermore, medical staff can clearly observe the distance between the flowing path and the calculus, the sheathing canal and the endoscope can be rapidly adjusted according to the relative position relation of the flowing path and the calculus, the use efficiency of the endoscope is improved, and the lithotripsy operation time is shortened.

The utility model relates to the field of medical instruments, in particular to an endoscope cleaning device which comprises a sleeve and a handle connected to one end of the sleeve, the sleeve is provided with a main cavity for an endoscope to penetrate through and further provided with an auxiliary cavity, a transmission wire is arranged in the auxiliary cavity, an endoscope wiping block is arranged at the end, penetrating out of the sleeve, of the transmission wire, and the endoscope wiping block is connected with the handle. The other opposite end of the transmission wire is fixedly connected with a transmission structure in the handle, the transmission structure comprises a transmission groove and a positioning column which are matched with each other, and the endoscope wiping block is driven to do rotary progressive movement through relative movement of the transmission groove and the positioning column, so that the endoscope lens is wiped; in the operation process, the lens can be cleaned without taking out the endoscope, and after cleaning is completed, the gear can be adjusted to move the cleaning block to the position where the visual field is not blocked.

The invention discloses an endoscope multi-region semantic perception time domain fusion adaptive white balance algorithm. The algorithm comprises the following steps: acquiring an endoscope image; performing tissue region division on the endoscope image through a lightweight semantic segmentation network to obtain a plurality of region images; converting each regional image from an RGB space to a YCbCr color space, separating a brightness channel Y from chrominance channels Cb and Cr, and calculating a channel mean value of the chrominance channels Cb and Cr; calculating the average offset of the chrominance channels Cb and Cr according to the calculated channel average of the chrominance channels Cb and Cr; performing white point detection on each regional image to obtain an RGB three-channel mean value; combining the calculated mean offset of the chromaticity channels Cb and Cr, the RGB three-channel mean obtained by white point detection of each regional image and a statistical index to form a multi-dimensional regional color feature vector; and fusing historical frame features with the regional color feature vector to obtain a feature vector based on space-time fusion.

A non-transitory machine-readable media may store instructions that, when run by one or more processors, cause the one or more processors to generate stereo endoscopic image data of a medical field and define a medical field volume from the stereo endoscopic image data. The processors may also project a 3D representation of the medical field volume to an extended-reality display device in a remote volume. The 3D representation may include a stereoscopic image and a 3D scene generated from the stereo endoscopic image data. The processors may also generate visual guidance in the remote volume to augment the stereo endoscopic image, map the visual guidance from the remote volume to the medical field volume to generate an augmented image of the medical field volume, and project the augmented image of the medical field volume to a display device viewed by an operator of instruments in the medical field.

Provided are a self-locking apparatus, an endoscope handle, and an endoscope. The self-locking apparatus comprises a driving lever (310), a rotating shaft (320), a traction rope driving member (330), an elastic member (340), and a first limiting assembly. The traction rope driving member (330) is synchronously and rotationally connected to the rotating shaft (320). A sliding stroke is provided between the traction rope driving member (330) and the rotating shaft (320) in an axial direction of the rotating shaft (320). The first limiting assembly comprises a resistance member (351). An axial movement stroke of the rotating shaft (320) comprises a first position and a second position. The elastic member (340) comprises a mounting portion (342) and an arc-shaped elastic portion (341). The self-locking apparatus can effectively avoid the problem in the prior art that teeth and tooth grooves on a driven gear and a driving gear are damaged due to the action of the elastic member on the driven gear. Meanwhile, the resistance corresponding to a unit length deformation generated by the arc-shaped elastic portion (341) of the elastic member (340) is reduced, the movement space for elastic deformation of the arc-shaped elastic portion (341) is increased, and the resistance encountered by the arc-shaped elastic portion (341) during a relatively large elastic deformation is reduced, so that a medical worker can easily and quickly complete state switching control, thereby improving the use convenience of the endoscope.

The invention discloses an insertion part, an endoscope and a recovery method of a bent tube, and relates to the technical field of medical instruments. The insertion part disclosed by the invention is used for an endoscope. The insertion part comprises a front end assembly, a bent pipe, a lining pipe and an outer sleeve, the front end assembly is installed at the far end of the outer sleeve, the lining pipe and the bent pipe are both arranged in the outer sleeve in a penetrating mode, and the bent pipe is installed between the front end assembly and the lining pipe in a limited mode in the axial direction of the insertion part; at least one of the front end assembly and the lining pipe is detachably connected with the outer sleeve and used for allowing the bent pipe to retreat from the outer sleeve after the front end assembly or the lining pipe is detached from the outer sleeve. The scheme at least can be used for solving the problem that an existing endoscope is high in use cost.

The invention discloses an endoscope cold light source dimming method, system and device and a storage medium, and relates to the technical field of endoscope light source adjustment, and the method comprises the steps: obtaining a current image brightness value; according to the current image brightness value and the target image brightness value, a PID control algorithm is adopted, and a dimming strategy of the cold light source of the endoscope is determined; the dimming strategies sequentially comprise an exposure time dimming strategy, an LED lamp driving current dimming strategy and an electronic gain dimming strategy according to a priority sequence during dimming; and dimming the cold light source of the endoscope according to the dimming strategy. According to the method and the device, the cold light source of the endoscope can be quickly and stably dimmed, and the quality of an endoscope image is ensured.

The invention relates to the technical field of image analysis, in particular to an alimentary canal lesion analysis method and system based on image recognition, based on an endoscope image of an alimentary canal of a patient, the edge intensity of pixel points in the image is evaluated through image analysis, and a suspected lesion area in the image is recognized by adjusting an edge detection threshold value; the non-suspected lesion area and the suspected lesion area are distinguished, and a digestive tract area distinguishing result is obtained. According to the method, the identification process of the suspected lesion area and the non-suspected lesion area is optimized by dynamically adjusting the edge detection threshold value, the shape, size and color of the suspected lesion area are evaluated, and the suspected lesion area is matched with the known lesion type in the database, so that the lesion type identification accuracy is improved; and the image data corresponding to the lesion type is extracted, data support is provided for subsequent medical personnel to confirm the lesion type, and the evaluation of the healthy tissue is refined by analyzing the deviation between the non-suspected lesion area and the normal color data.

Provided is a suture tightening device, including: a first thread take-up wheel, a second thread take-up wheel, and a thread gear support detachably connected to an endoscope handle, wherein the first thread take-up wheel is arranged at a space from the second thread take-up wheel, and the first thread take-up wheel and the second thread take-up wheel are separately in rotatable connection to the thread gear support.

Laser lithotripsy systems and methods with a controlled retropulsion setting to facilitate manipulation, migration, and ablation of a calculi structure are disclosed. An endoscopic lithotripsy system comprises a laser system to provide laser pulses to a calculi structure in an anatomical environment, and a controller circuit to localize the calculi structure. If it is determined that the calculi structure is not at a target location, the laser system emits first laser pulses according to a first laser output setting, which produces a high retropulsion effect to mobilize and reposition the calculi structure to the target location. For calculi structure located at or migrating to the target location, the laser system emits second laser pulses according to a second laser output setting, which produces a lower retropulsion effect than the first laser pulses, but a higher efficiency to ablate or fragment the calculi structure.

The invention discloses a defogging method based on an endoscope image and an endoscope system.The method is applied to a processor of the endoscope system.The method comprises the steps that the endoscope image is obtained; extracting a texture feature, at least one color feature and a global contrast feature of the endoscope image; determining that fog exists in the endoscope image according to the texture feature, the at least one color feature and the global contrast feature; determining the fog concentration of the endoscope image; and according to the fog concentration, carrying out defogging processing on the endoscope image so as to obtain a defogged image. The accuracy of fog detection and fog removal can be improved, automatic fog monitoring and removal are achieved, and the automation degree of the endoscope is improved.

An imaging device for generating imaging data of an object is provided, comprising: an image control engine configured to control at least one image sensor to acquire first image data of the object, having a first image setting, and second image data of the object, having a second image setting, wherein the first image setting and the second image setting differ from each other, a data processor configured to receive the first image data and the second image data and to forward the image data to a 3D engine, wherein the 3D engine is configured to generate at least one depth map of the object based on the image data. Further, an endoscope, a system and a method for imaging an object is provided.

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 invention discloses a tumor image segmentation method and system of a multi-scale feature fusion network based on boundary enhancement, and relates to the technical field of image segmentation, and the method comprises the steps: obtaining a to-be-segmented tumor image; constructing a tumor image segmentation model based on a pyramid visual converter PVTv2 backbone network; training the tumor image segmentation model through the to-be-segmented tumor image and the known tumor image to obtain an optimal tumor image segmentation model; and acquiring a real-time to-be-segmented tumor image and inputting the real-time to-be-segmented tumor image into the optimal tumor image segmentation model to obtain a tumor image segmentation result. Aiming at the endoscope image segmentation of the kidney tumor, the kidney tumor in the endoscope image is efficiently, stably and automatically segmented through the boundary-enhanced multi-scale feature fusion network, clinical doctors are helped to provide accurate tumor area positioning in endoscopy and surgical operations, and compared with the most advanced method, the method has the advantages that the accuracy is high, and the efficiency is high. According to the method, better segmentation capability and stronger generalization capability are obtained.

The invention discloses a lateral transceiving integrated optical fiber ultrasonic endoscope and a preparation method, and belongs to the field of ultrasonic endoscopic imaging. Comprising a double-clad optical fiber, an excitation film, a dielectric mirror and a sensing film. A part of the inner cladding of the optical fiber is etched into a concave spherical surface and coated with an excitation film, excitation light transmitted in the inner cladding is absorbed, and focused ultrasonic waves transmitted in the lateral direction are excited. A part of an inner cladding layer and a fiber core of the optical fiber are etched, and a Fabry-Perot (Fabry-Perot, F-P) cavity is prepared. When an ultrasonic signal laterally transmitted into the ultrasonic endoscope acts on the sensing film of the cavity, the effective refractive index and the F-P cavity length of the sensing film are changed, and the change is demodulated through signal light in the fiber core to complete ultrasonic detection. According to the lateral transmitting-receiving integrated optical fiber ultrasonic endoscope, the inner cladding is etched and coated with the excitation thin film to excite laterally focused ultrasonic waves, an F-P cavity is formed through lateral etching of the optical fiber to achieve lateral ultrasonic detection, and the lateral transmitting-receiving integrated optical fiber ultrasonic endoscope is formed.

The invention relates to the technical field of image focus detection, in particular to a fiber endoscope image focus detection method and system, and the method comprises the following steps: providing a data quality guide interface; capturing narrow-band light images of the endoscope away from a first preset position and a second preset position of the intestinal wall in the axial movement process, calculating brightness gain values of a blue light channel and a green light channel, calculating an asymmetric scattering correction coefficient, and updating indication of color information calibration integrity; tracking the pixel moving speed of the interferent in the view in the propulsion operation process, calculating the relative depth of the interferent, and updating the indication of the validity of the depth data of the interference layer; identifying the image area which is not shielded by the interferent, and updating the indication of the information coverage degree of the background area; triggering an image synthesis operation; performing color compensation on the image information of the image area which is stored in the background canvas and is not shielded by the interferent; reconstructing a clear image; and performing focus detection on the clear image. The method improves the accuracy of focus detection.