3388 results about "Endoscopy" patented technology

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 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.

The invention discloses an oral cavity data monitoring and early warning method and system based on deep learning, and the method comprises the steps: solving a problem that the focus recognition is inaccurate because the image collection process of an oral cavity endoscope of a patient is affected by various environment and equipment parameters; according to the method, synchronous binding of collected images and equipment parameters and intelligent image preprocessing are proposed, historical time sequence images and variation trend features are combined, lesion space and time features are extracted through combination of a lightweight convolutional neural network and a long-short term memory network, feature weighted reasoning is realized by using a context awareness attention fusion network, and the focus space and time features are extracted. According to the method, the model parameters and the risk threshold value can be dynamically adjusted, the focus recognition accuracy and the early warning individuation are improved, and clinical grading treatment and intelligent health management are effectively assisted.

The invention discloses an insertion tube and a manufacturing method thereof, an insertion part and an endoscope, and relates to the technical field of medical instruments, the insertion tube comprises an insertion body and an elastic tube, a first reinforcing layer and a second reinforcing layer are arranged in the insertion body, the second reinforcing layer is arranged outside the first reinforcing layer in a surrounding mode, and the first reinforcing layer is provided with a concave part. The first reinforcing layer and the second reinforcing layer can form double limiting and wrapping supporting on the elastic pipe, the concave shape of the concave part of the first reinforcing layer is utilized to be attached to the outer wall outline of the elastic pipe, and the outer side of the second reinforcing layer is matched for enclosing and restraining, so that the installation stability of the elastic pipe in the first channel can be greatly improved; bending moment generated by self-gravity, external force and the like of the elastic tube is effectively counteracted, the elastic tube is prevented from being bent under the action of self-gravity, external force and the like, the whole insertion tube is prevented from deforming along with bending of the elastic tube, and the form stability of the insertion tube in the cavity in the propelling process is guaranteed. And the straightness of a traction rope transmission path and the accurate conduction of a control instruction are ensured.

The present application relates to a kind of snare cutting knives for endoscope, including proximal handle, tube body assembly, cutting assembly and limiting component;Proximal handle is equipped with limiting sliding slot;The proximal end of tube body assembly is connected with proximal handle, and the distal end of tube body assembly is equipped with insulating protection tube;Cutting assembly includes cutting ring and cutting head, and cutting head is set to the distal end of cutting ring;Limiting component includes sliding part and limiting control wire, sliding part is slidably arranged in limiting sliding slot, and the proximal end of limiting control wire is fixedly connected with sliding part, and sliding part is used to drive limiting control wire axial movement;When limiting control wire moves to the distal end of insulating protection tube, cutting head and insulating protection tube abut each other and are fixed;When limiting control wire exits insulating protection tube, cutting head can continue to move relative to insulating protection tube.

The invention discloses a sealing structure, a negative pressure suction sheath and an endoscope assembly, and belongs to the technical field of medical instruments. The sealing structure is used for the negative pressure suction sheath and comprises a first cover body detachably connected with the near end of a sheath base of the negative pressure suction sheath, a first through hole is formed in the middle of the first cover body, and a first air hole is formed in the radial outer side of the first through hole; the second cover body is arranged on the outer side of the first cover body in a sleeving mode and detachably connected with a sheath base of the negative pressure suction sheath, a second through hole is formed in the middle of the second cover body, and a second air hole is formed in the radial outer side of the second through hole; the second cover body and the first cover body are in sliding fit, and the overlapping opening degree of the first air hole and the second air hole is adjusted through relative sliding; the second cover body axially limits the first cover body and provides support when the endoscope is inserted, so that the first cover body is prevented from collapsing. The sealing structure is used for the negative-pressure suction sheath, the branch switch is prevented from additionally occupying the operation space, and the operation safety is improved.

The invention provides a real-time processing method for endoscopic image blood vessel enhancement and microcirculation evaluation, which comprises the following steps of: processing an original endoscopic image, and locally enhancing a brightness channel through a contrast-limited adaptive histogram equalization technology; self-adaptive frequency domain-space domain decomposition is realized based on local texture complexity analysis; performing multi-scale Hessian matrix blood vessel detection on the low-frequency component; applying a directional Gabor filter bank to the high-frequency component; spatial-temporal feature fusion is realized through multi-resolution pyramid optical flow calculation; synchronously completing blood vessel probability prediction, blood vessel diameter estimation and blood flow direction prediction by using a lightweight multi-task deep learning network; the blood flow velocity is analyzed and calculated based on a speckle mode, the perfusion density is subjected to accelerated statistics through an integrogram, and vascular morphological parameters are extracted by adopting an improved skeleton algorithm. According to the invention, an enhanced blood vessel visualization effect and a real-time microcirculation quantitative evaluation function can be provided, and the overall improvement of the endoscope image processing quality and efficiency is realized.

The invention discloses an image return method and device of an endoscope, a storage medium and a terminal. The method comprises the following steps: acquiring an initial image and a triaxial angular velocity signal of the endoscope; according to the triaxial angular velocity signal, attitude calculation is carried out by using a quaternion differential equation to obtain an attitude quaternion, and the attitude quaternion is updated in real time; performing interpolation on the attitude quaternions at adjacent moments within one frame of exposure time to obtain a row-level quaternion and generate a row-level rotation matrix; and based on the row-level rotation matrix, performing return and compensation on the initial image by using reverse mapping and bilinear interpolation to obtain a return image. The problems of universal joint deadlock and function failure caused by the universal joint deadlock in Euler angle attitude calculation are avoided, line-by-line compensation is carried out through an interpolation algorithm, the jelly effect is eliminated, the problems of large delay, insufficient real-time performance and difficulty in integration in a limited space in post-processing of a traditional software algorithm or an external micro-control unit are avoided, and the method is suitable for being applied to the field of Euler angle attitude calculation. And the imaging requirement of clinical operation of the medical endoscope can be better met.

The invention relates to the technical field of artificial intelligence, and provides a gastric cancer risk quantitative scoring method, system and equipment based on artificial intelligence, and the method comprises the steps: recognizing the image type of each image frame in alimentary canal endoscope image data; for the electronic dyeing image frame, identifying a part contour region and an intestinal contour region of the feature part in the image frame, determining an intestinal epithelial metaplasia grading category of the feature part according to an area proportion of the intestinal contour region in the part contour region, and performing electronic dyeing intestinal scoring on the image data; for the white light image frame, gastroscope part types included in the image frame and focus area types of all gastroscope parts are recognized; performing atrophy scoring on the image data according to the position distribution of the focus area of the atrophy type; performing table state scoring on the image data according to whether the plica enlargement, nodular gastritis and diffuse redness focus areas exist or not; and realizing gastric cancer risk quantitative scoring according to the electronic staining intestinal scoring, the atrophy scoring and the epistatic state scoring.

The invention discloses an internal combustion engine in-cylinder transient self-adaptive exposure control method based on FPGA acceleration, and belongs to the technical field of internal combustion engine endoscopic visualization. In order to solve the technical problem of image overexposure or underexposure caused by violent illumination change in the combustion process in an internal combustion engine cylinder, a real-time exposure detection unit is fused with a camera built-in sensor and an endoscope added sensor to monitor light intensity data; the adaptive exposure control unit accelerated by the FPGA adopts adaptive PID control and fuzzy logic control to generate a parameter adjustment direction, the adaptive PID dynamically adjusts gain based on a machine learning model, and the fuzzy logic outputs a decision according to a fuzzy rule base of brightness, light intensity and errors; the parameter adjusting unit adjusts the aperture size, the shutter speed and the light sensitivity in a linkage mode according to the target and actual gray scale difference value, and millisecond-level multi-parameter exposure control is achieved. Overexposure of a highlight area and loss of details of a low-light area are effectively avoided, and stable and clear images are obtained in the whole combustion process.

The invention discloses an intelligent endoscope system with a multi-mode imaging function, and relates to the technical field of medical equipment, and the intelligent endoscope system comprises an imaging module which comprises a white light imaging subunit, a fluorescence imaging subunit and an infrared thermal imaging subunit; the data preprocessing module comprises noise suppression, SIFT registration and normalization; the image fusion module is used for decomposing four layers in a Laplacian pyramid, and reconstructing after feature weighting; the intelligent analysis module is used for extracting multiple types of features, performing CNN-Transform model reasoning and performing historical case verification; the display control module is used for 4K display, AR labeling and touch operation; and the data storage module is used for AES-256 encryption, DICOM conversion and three-level permission. The diagnosis accuracy is improved through multi-modal fusion, lesions are analyzed and efficiently recognized, operation risks are reduced through operation navigation, safety is guaranteed through data double backup, the system is suitable for multi-cavity diagnosis and treatment, and clinical precise diagnosis and safe operation are assisted.

The invention relates to the technical field of endoscopes, and provides a spectral image processing method for a three-dimensional endoscope. The method comprises the following steps: synchronously acquiring single-band spectral images returned by multiple sensors of the endoscope; after the single-band spectral image is corrected, a two-dimensional spectral image is generated by combining multi-level fusion of the spectral weight; constructing a three-dimensional point cloud coordinate set through parallax calculation; mapping the two-dimensional spectrum fusion image to a three-dimensional point cloud based on a back projection sub-pixel mapping algorithm to obtain a three-dimensional spectrum point cloud; and performing Poisson fusion driven inter-block splicing fusion on the three-dimensional spectrum point cloud, and outputting an interactive three-dimensional navigation model. The technical problem that image details are lost and three-dimensional reconstruction is inaccurate due to the fact that spectral image fusion precision is insufficient in an existing three-dimensional endoscope image processing method is solved, registration and reconstruction of high-precision three-dimensional spectral point clouds are achieved through multi-modal image collaborative correction and optimization fusion, and the image fusion precision is improved. And the accuracy and the real-time performance of navigation in the endoscope are improved.

The invention relates to the field of medical artificial intelligence, in particular to a laryngeal cancer early intelligent diagnosis system and method based on multi-modal deep learning, and the system comprises a multi-modal data collection module, a cross-modal feature extraction module, a cross-modal attention network module, an expert-level knowledge distillation network module, and a focus evolution prediction and diagnosis decision and visualization module. Endoscope images, acoustic features and clinical data are collected, a system extracts high-dimensional feature vectors, a cross-modal attention network is used for feature fusion, an expert-level knowledge distillation network is combined with pathology and expert experience, neural network learning is guided, a lesion evolution prediction module tracks lesion changes, risk prediction is generated, and finally, the lesion evolution prediction module is used for predicting the lesion change. And the diagnosis decision and visualization module generates a diagnosis result and explanation. The system improves the early detection rate of laryngeal cancer through multi-modal data fusion.

An endoscopic imaging system for use in a light deficient environment includes an imaging device having a tube, one or more image sensors, and a lens assembly including at least one optical elements that corresponds to the one or more image sensors. The endoscopic system includes a display for a user to visualize a scene and an image signal processing controller. The endoscopic system includes a light engine having an illumination source generating one or more pulses of electromagnetic radiation and a lumen transmitting one or more pulses of electromagnetic radiation to a distal tip of an endoscope.

The invention discloses an endoscope image processing method based on oxyhemoglobin saturation and multiple central wavelengths, and relates to the field of medical image processing.The method comprises the steps that a first initial image signal, a second initial image signal, a third initial image signal and a fourth initial image signal are obtained; calculating oxyhemoglobin concentration information of the target part according to the second initial image signal and the third initial image signal; calculating deoxidized hemoglobin concentration information of the target part according to the second initial image signal and the fourth initial image signal; calculating the oxyhemoglobin saturation of the target part according to the oxyhemoglobin concentration information and the deoxidized hemoglobin concentration information; performing brightness enhancement on the second initial image signal based on the oxyhemoglobin saturation to obtain a second enhanced image signal; and generating a target image according to the second enhanced image signal, the first initial image signal and the third initial image signal, wherein the target image is used for identifying the bleeding position of the target part.

The invention discloses a medical endoscope with an extinction anti-pollution structure, and relates to the technical field of endoscopes, the medical endoscope comprises an endoscope main body, the front end of the endoscope main body is provided with a camera module, and the periphery of the camera module is provided with an illumination light source for illumination, an outer sleeve and an extinction structural member; a hollow observation opening is formed in the center of the endoscope body in a penetrating mode, a light blocking sinking table used for blocking front direct light beams emitted by the illumination light source is arranged outside the hollow observation opening in a surrounding mode, and a deflection bevel edge used for diffraction deflection of light rays emitted by the illumination light source is further arranged outside the light blocking sinking table. Through the synergistic effect of physical shielding of the light blocking sinking table and diffraction deflection of the deflection bevel edge, front-side direct stray light of the illumination light source is cut off from the source, side-emitting and oblique-emitting light rays are deflected in a targeted mode, light spot and light fog pollution caused by diffuse reflection of the front end of a transparent guide sheath or a catheter is remarkably eliminated, and the imaging definition is remarkably improved.

The invention provides a breast endoscopic surgery simulation training system. The breast endoscopic surgery simulation training system comprises a hardware end and a software end, the hardware end comprises a simulation human body model, and the software end is provided with a 3D mesh model corresponding to the simulation human body model; the simulation surgical instrument comprises a simulation electrotome, a simulation endoscope, simulation grasping forceps and a simulation incision protection sleeve, and the software end is provided with an electrotome model, an endoscope model, a grasping forceps model and an incision protection sleeve model which correspond to one another; the pose detection device is used for detecting the current pose of the simulation surgical instrument in real time and sending the current pose to the software end, so that interaction between the simulation surgical instrument and the simulation human body model is mapped to interaction between the instrument model and the 3D mesh model; the software end further comprises a display screen, and the display screen is used for displaying interaction between the instrument model and the 3D mesh model in real time. According to the scheme, breast endoscopic surgery training, teaching and research which are closer to a real surgery scene can be provided, so that the safety and the operation precision in an actual breast endoscopic surgery are improved.

The invention discloses a traction structure, a handle and an endoscope, belongs to the technical field of medical instruments, and aims to solve the technical problems of difficulty in precision control and proneness to errors in a traction wheel assembly process in the prior art. The traction mechanism can be used for but not limited to an endoscope, the endoscope comprises a shell, and the traction mechanism is arranged in the shell. The traction structure comprises a driving lever and a traction wheel, and the driving lever is rotationally arranged on the shell and can rotate around a first axis relative to the shell; one of the traction wheel and the driving lever is provided with an inserting part, the inserting part penetrates through the shell in the first axis direction and is rotationally matched with the shell, and the other one of the traction wheel and the driving lever is provided with a socket part which is rotationally matched with the inserting part in a limiting manner and is buckled with the inserting part. According to the traction structure, the driving lever and the traction wheel are assembled and rotationally limited and connected through the buckling mode of the inserting part and the socket part, the structure is simple, assembling is easy, assembling and disassembling are convenient, and automatic production is facilitated.

The invention discloses an anti-clogging rapid laying construction method for municipal drainage pipelines in a pluvial area, and relates to the technical field of municipal engineering. According to the method, through construction early-stage investigation and pretreatment, a high-pressure jet grouting pile and a steel sheet pile are combined to form a water interception curtain and vacuum well point dewatering is adopted, and a pipeline with a nanometer hydrophobic coating and a flow guide protruding edge is prefabricated; during rapid excavation, rapid hardening concrete is used for supporting, and a prefabricated module foundation with a permeable blind pipe is laid; laser positioning is adopted for hoisting, and double sealing is adopted for interfaces; graded gravel and a curing agent are used for backfilling, and ground penetrating radar is matched for detection; acceptance inspection is combined with a closed water test and an endoscope, and an intelligent monitoring device is installed to be connected into an intelligent system. The problems that construction efficiency is low and pipelines are prone to clogging in rainy areas are solved, the construction period is shortened by 30% or above, the initial clogging rate is reduced by 60%, and the method is suitable for drainage projects in areas with the annual precipitation being 800 mm or above.

The invention relates to the technical field of medical instruments, and discloses an endoscope light guide plug with an air tightness self-checking function, which comprises a plug shell, a sealing ring is fixedly connected to the inner wall of the plug shell, a light guide unit is fixedly connected to the inner wall of the plug shell, an air inlet pipe I penetrates through the outer wall of the plug shell, and an air inlet pipe II penetrates through the outer wall of the plug shell. And an air inlet pipe II penetrates through the inner wall of the plug shell. When the filter plate is replaced through the dismounting mechanism, a knob is rotated to drive a locking rod and a limiting rod to rotate, so that the limiting rod is aligned with a communicating groove, a spring I pulls a guide sheet to move along a sliding groove, and the locking rod is separated from a locking groove, so that the plate can be taken; during installation, the filter plate is placed, the knob is pulled to enable the locking rod to be aligned with the locking groove, the locking rod is clamped after loosening, the knob is rotated to enable the limiting rod and the communicating groove to be staggered and fixed, the filter plate is rapidly disassembled and assembled, cleaning or replacement is convenient, the filter plate is prevented from being blocked to affect a gas path, the gas filtering effect is guaranteed, the maintenance time and cost are reduced, and the long-term use stability of equipment is improved.

The invention provides an endoscope imaging system and a hard tube type endoscope, and belongs to the technical field of optical imaging, the endoscope imaging system comprises an objective lens, a relay lens and an ocular lens of an object space telecentric structure, the objective lens comprises a first lens, a second lens, a third lens with positive focal power and a bonding lens group with positive focal power, the second lens is a steering prism, the image side surface and the object side surface of the first lens are aspheric surfaces, the balsaming lens group comprises a fourth lens, a fifth lens and a sixth lens, the fourth lens is a doublet lens, the fifth lens is a triplet lens, the sixth lens is a doublet lens, the relay lens comprises an odd number of rod lens groups which are arranged at intervals, and the rod lens groups are arranged at intervals. The eyepiece comprises a seventh lens, an eighth lens and a ninth lens, and the seventh lens, the eighth lens and the ninth lens are all doublet lenses. By optimizing the structural design of the optical system, the defocusing amount is reduced, seamless switching of visible light and near-infrared light dual-mode imaging can be achieved, and meanwhile high-quality imaging is achieved.

The invention discloses a miniature intelligent terminal intestinal image processing method and device, a storage medium and computer equipment. The method comprises the following steps: preprocessing an original intestinal tract image set acquired by a monocular endoscope, calculating according to the preprocessed intestinal tract image set to obtain a motion calibration scale factor and a texture calibration scale factor, and adaptively fusing to obtain a conversion coefficient from a pixel to an actual size; extracting polyp region key feature points of each image of the preprocessed intestinal image set, constructing a Delaunay triangulation graph according to each polyp region key feature point, and performing non-rigid deformation matching based on a cross-graph convolutional network and an optimal transmission algorithm to obtain a matched feature point set; and sparse 3D reconstruction is carried out according to the matched feature point set to obtain a polyp point cloud, and the polyp size is calculated according to the Euclidean distance between two farthest points in the polyp point cloud and the conversion coefficient. According to the method, the problems of monocular image scale ambiguity and non-rigid deformation can be solved, and the more accurate polyp size can be obtained.

In an endoscope apparatus including a processor, the processor specifies the position of a specific region and sets a reference scale in a picked-up image that is obtained from the image pickup of a subject on which the specific region formed by auxiliary measurement light is formed. Then, the processor extracts a region of interest, determines a measurement portion, calculates a measured value obtained from the measurement of the measurement portion, on the basis of the reference scale, and generates a measured value marker using the measured value. Further, the processor creates a specific image in which the measured value marker is superimposed on the picked-up image.

The invention discloses a multi-modal endoscope image fusion analysis method, and relates to the technical field of medical image navigation, and the method comprises the steps: collecting an original white light image and an original narrow-band image, carrying out the preprocessing, and collecting real-time pose parameters; extracting blood vessel texture features in the preprocessed original white light image and the original narrow-band image, generating a binary semantic mask, calculating a spatial transformation matrix according to the binary semantic mask, and generating preliminary visual deformation field data; and calculating microscopic deformation field data according to a pre-stored biomechanical characteristic database, the preliminary visual deformation field data and the real-time pose parameters, carrying out reverse calculation to obtain physical deformation compensation field data, and carrying out spatial superposition operation on the physical deformation compensation field data and the preliminary visual deformation field data to obtain comprehensive compensation deformation field data. According to the method, real-time quantitative evaluation and abnormal early warning of the reliability of the fusion result are realized through multi-modal fusion quality early warning judgment, and the clinical decision credibility and the operation safety are enhanced.

The invention relates to the technical field of mold detection, and discloses a special working state inner wall detection device for a neutral borosilicate molded bottle mold, which comprises a workbench, an opening and closing mechanism is arranged on the middle side of the top of the workbench, a clamping mechanism is arranged on the top of the workbench, and a six-degree-of-freedom mechanical arm is mounted on the rear side of the top of the workbench. A ceramic probe is arranged on the outer side of the six-degree-of-freedom mechanical arm, and a base fixing seat is fixedly connected to the outer side of the ceramic probe. A real-time image differential analysis module is arranged, a blowing and powder spraying mechanism is used for carrying out pneumatic excitation on a suspected defect area, and a multispectral endoscope module is controlled to respectively collect optical images before and after excitation; by calculating the normalized difference measure of the two images and comparing the normalized difference measure with the preset physical displacement threshold value, the non-solid-phase attachments displaced due to pneumatic excitation and the solid-phase defects with fixed positions can be distinguished, and the technical problem that two abnormal areas with different properties are difficult to effectively classify in the prior art is solved.

The invention relates to an endoscope, a pressure resistance testing method of the endoscope and an endoscopic system. The endoscope comprises an endoscope shell, a signal interface module, a camera module, a traction steel wire and a lightning protection tube, wherein the camera module is connected with the signal interface module through a transmission signal line; one end of the traction steel wire is connected with a metal structure on the camera module, and the other end is connected with the lightning protection tube; the lightning protection tube and the camera module are arranged in the accommodating space; and the lightning protection tube and the signal interface module are common-grounded. According to the endoscope with the structure, static electricity can be released through the transmission signal line and the traction steel wire under the condition that the static electricity is accumulated to the breakdown voltage of the lightning protection tube, so that the static electricity protection capability of the endoscope is improved by utilizing a limited accommodating space, and meanwhile, the voltage resistance of an insulating material of the endoscope cannot be reduced.

The invention provides an endoscope image stabilization control method, which comprises the following steps of: acquiring an original dithering image sequence and inertial data of an endoscope, fusing the original dithering image sequence and the inertial data, acquiring an initial mixed motion field, performing operation semantic segmentation on the original dithering image sequence, and acquiring a collaborative attention map in combination with a physical motion mechanism. Obtaining a space-time adaptive filtering kernel through the collaborative attention map, filtering the initial mixed motion field according to the space-time adaptive filtering kernel, obtaining a stable motion field, carrying out image deformation and interpolation synthesis processing on the stable motion field, and obtaining a stable image sequence; through the integrated technical scheme of operation semantic segmentation, dynamic image stabilization optimization and accurate jitter suppression, the problem of interference of endoscope jitter on the neurosurgery operation visual field is solved.

The present invention relates to a multispectrum endoscope and an endoscope system comprising same. The multispectrum endoscope of the present invention comprises: a first light source emitting infrared rays having a plurality of wavelengths; a plurality of multimode optical fibers for guiding the infrared rays emitted from the first light source toward a sample; a second light source emitting a visible ray; an optical fiber for guiding the visible ray emitted from the second light source toward the sample; a lens part for receiving a fluorescent signal emitted from the sample and a visible light signal reflected off the sample; and an optical fiber bundle for guiding the fluorescent signal and / or the visible light signal received by the lens part toward a multispectrum photodetector, wherein the optical fiber bundle is disposed so as to be surrounded by the plurality of multimode optical fibers, and the end portion of the multispectrum endoscope emitting the visible ray surrounds at least a portion of the plurality of multimode optical fibers.

According to the method and device for the endoscope to automatically follow the instruments, the electronic equipment and the storage medium, the actual focusing center and the real-time video of the endoscope are firstly obtained, then the real-time video is processed, the current operation stage is recognized, the real-time position information and the weight of each instrument in the real-time video are obtained, and the real-time position information and the weight of each instrument in the real-time video are obtained; the weights of the instruments and the corresponding position information are subjected to weighted fusion, the semantic attention center of the endoscope is obtained, and finally the focus center of the endoscope is adjusted according to the actual focus center and the semantic attention center. According to the technical scheme, the weight and the semantic attention center of each instrument are calculated by fusing the multi-dimensional features of the basic data, and finally, the logic of the focusing center of the endoscope is dynamically adjusted, so that intelligent following in a multi-instrument collaborative scene is realized, the defects of single instrument tracking and lack of semantic adaptation in the prior art are overcome, and the tracking efficiency is improved. And the flexibility and the accuracy of the automatic following instrument of the endoscope are improved.

The present application relates to the technical field of medical three-dimensional reconstruction, and particularly relates to an endoscopic-image-based three-dimensional reconstruction method and apparatus for a pediatric adenoid situation, which method and apparatus can solve, to a certain extent, the problems whereby existing three-dimensional reconstruction methods in the medical field still lack research on three-dimensional reconstruction of adenoid regions, and reconstruction results in existing technology have low completeness and cannot meet clinical requirements. The method comprises: by means of local plane parameter initialization, establishing relationships between corresponding points in different images; by means of local plane parameter optimization, accurately updating local plane parameters of each pixel point in a reference image; on the basis of a filtering strategy using relative depth difference, implementing depth filtering; by means of a spatial grid surface fitting method, restoring missing depth information of some regions in a depth map after the depth filtering, so as to densify a reconstruction result; and by taking into consideration two metrics, i.e., relative depth difference and reprojection error, converting into a point cloud the depth map which has been subjected to surface fitting, so as to reconstruct a three-dimensional model of an adenoid region.