589 results about "Endoscopic image" 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 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 provides a real-time positioning and puncture track control method and system in a breast duct endoscope operation, and relates to the technical field of medical instruments, and the method comprises the following steps: establishing a real-time coordinate system by collecting an endoscopic image sequence and electromagnetic position data, obtaining lumen three-dimensional depth information by using a light field reconstruction algorithm, and adjusting and calculating stress field distribution by using a grid form. And determining an optimal track based on the puncture safety coefficient, and adjusting compensation parameters in real time by using the optical fiber strain sensing array. Accurate positioning and track control of the puncture instrument in the breast duct endoscope operation are achieved, and operation safety and accuracy are improved.

The invention belongs to the technical field of medical equipment. The endoscopic surgery operation quality real-time quantitative evaluation system comprises an endoscopic camera probe used for collecting endoscopic images and an endoscopic handle used for operation. The displacement sensor is integrated on the endoscope camera probe and is used for detecting the endoscope entering speed; the pressure sensor is integrated on the gas injection pipeline and is used for detecting the intracavity pressure; the force sensor is integrated on the endoscope handle and is used for detecting the tissue traction deformation; the optical coherence layer scanning probe is integrated on the endoscope camera probe and used for detecting the thickness of the submucous membrane, and the processing terminal is used for conducting real-time quantitative evaluation on the endoscopic surgery operation quality according to the endoscope entering speed, the intracavity pressure, the thickness of the submucous membrane, the tissue traction deformation image, the included angle between an instrument and a focus normal and the complication response time. According to the invention, full-process datamation real-time accurate evaluation of operation skills and operation safety of operators is realized.

The invention relates to the technical field of medical image processing, in particular to a digestive endoscopy image deblurring enhancement method and system.The method comprises the steps that firstly, an input digestive endoscopy original image is processed through a blurred region classification network, and a pixel-level blurred classification map capable of distinguishing an adhesion blurred region and a motion blurred region is generated; then, parallel processing is carried out according to the classification graph: for an adhesion fuzzy region, physical model restoration and color correction are carried out by estimating a transmissivity graph and an ambient light value; for a motion blur region, a self-adaptive non-blind deconvolution kernel is constructed to perform deconvolution sharpness. And finally, inputting the two processing results and the original clear area into a multi-scale feature fusion network together, carrying out adaptive feature weighted fusion and image reconstruction, and outputting a globally clear and detail-enhanced final image. According to the method, accurate identification and targeted enhancement of composite blurring are realized, and the visual quality and diagnosis availability of the digestive endoscopy image are effectively improved.

The invention discloses a capsule endoscopic image super-resolution reconstruction method based on deep learning. The method comprises the steps of designing a data enhancement and label mechanism for pollution shielding; optimizing the ESRGAN model in combination with a lightweight structure and an attention mechanism; generating a structure sensing label; and training the model. The invention provides an image super-resolution reconstruction method fused with medical structure perception in order to solve the problems that a capsule endoscopic image is low in resolution, serious in pollution and shielding, difficult in structural detail recognition and the like in an actual clinical environment. According to the method, a pollution simulation data enhancement mechanism and a structural mask label system are constructed, so that the attention capability of the model on medical key information is effectively improved; a super-division network architecture combining lightweight improvement and attention mechanism optimization is adopted, so that the reconstruction quality is ensured, and meanwhile, the computing resource demand is greatly reduced; and a structure weighting loss function and an edge perception loss strategy are designed, so that the visual performance of the focus area is obviously enhanced.

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 relates to the field of endoscope image processing, and particularly discloses an automatic lesion recognition system for endoscopy of the digestive system department, which is characterized in that after a preprocessed original endoscope image is acquired, a double-branch parallel processing architecture is used to acquire characteristics with low resolution and rich semantic information through a deep context branch, and the characteristics of the original endoscope image are acquired. The potential area of the focus is accurately deduced; meanwhile, the fine texture of the mucous membrane is captured in a lossless manner through shallow detail branches which keep high resolution in the whole process. Furthermore, through a context-guided asymmetric enhancement mechanism, a global view of a deep branch is utilized to generate an uncertainty perception attention map as a reference, and weak detail features corresponding to a potential focus area in a shallow branch are accurately irradiated and adaptively enhanced. Thus, a conservative enhancement strategy is adopted in an uncertain focus area, background noise is effectively inhibited, and therefore the detection sensitivity and robustness of low-contrast and flat focuses are fundamentally improved.

The invention discloses an ultra-wide-spectrum endoscopic imaging device capable of being used for short-wave infrared fluorescence imaging, which is used for in-vivo minimally invasive imaging and comprises an illumination module, a wide-spectrum image transmission module, an imaging module and an image processing module. The illumination module consists of a light source and a light guide optical fiber, and is used for generating illumination light from ultraviolet to short wave infrared band and transmitting the illumination light to the wide-spectrum image transmission module; the wide-spectrum image transmission module consists of a few-interface optical imaging channel and a light guide illumination channel, and is used for illuminating an imaging target, exciting target fluorescence and collecting image signals from ultraviolet to short-wave infrared bands; the imaging module is composed of an optical filter and an imaging camera, and the imaging camera can be a wide spectral response image sensor or can be formed by combining cameras working in different wavebands and is used for converting optical images in different wavebands into image data; and the image processing module is used for registering and fusing image data of different wavebands in real time and displaying the image data.

The invention discloses a multi-photon optical fiber array endoscopic imaging device and method based on hollow spiral scanning, and belongs to the technical field of biological imaging. The device comprises a laser collimation and beam expansion module, a pulse chirp module, a light beam switching module, an endoscopic detection module and a fluorescence acquisition module. The light beam switching module comprises an optical switch and an optical fiber array composed of at least two low-group-velocity dispersion single-mode optical fibers. The endoscopic detection module drives the optical fiber array to execute hollow spiral scanning through the resonance driver, the track starting point is not located at the view field original point, and central dense sampling is avoided. According to the method, the optical fibers are switched through the optical switch, so that the optical fibers execute spatial non-coincident hollow spiral scanning, multi-photon signals such as fluorescence, second harmonic and fluorescence lifetime are acquired, a central hole is complemented through image reconstruction and fusion, and a complete field imaging result is obtained. Light damage of the central area is remarkably reduced, the imaging resolution uniformity is improved, the fused image is true and reliable based on physical sampling, and the system stability is high.

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 discloses an ear-nose-throat endoscope wireless image transmission system based on NFC near field triggering, relates to the field of medical apparatuses and instruments, and solves the problem that an existing wireless image transmission system is poor in image acquisition and transmission efficiency. The data acquisition module is used for performing cavity cross-sectional area analysis according to an image intercepted by an endoscope to obtain target endoscopic video analysis data, screening disease matching patients according to patient symptoms and obtaining corresponding endoscopic video analysis data to obtain endoscopic patient initial matching data; the data analysis module is used for analyzing the cross sectional area of the endoscopic video stream and the endoscopic depth of a lens to obtain endoscopic cavity similarity and performing type division on the endoscopic video stream of the matched patient according to the endoscopic cavity similarity to obtain video stream matching data; and the image transmission module is used for carrying out endoscope near-field triggering setting and endoscopic image wireless transmission on the target endoscopic patient according to the video stream matching data. According to the system and the method, the collection efficiency and the transmission efficiency of the endoscopic image can be 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.

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 relates to the technical field of endoscopic image analysis, in particular to a cystoscope tumor focus real-time positioning and boundary intelligent recognition system and method, and the system comprises a feature extraction module, a breakpoint detection module, a contour closing module, a boundary evaluation module and a smooth display module. According to the method, edge features are accurately captured by calculating pixel gradient vector data, homology matching is performed on end points of a fracture contour according to a gradient direction trend, connection pixels are automatically interpolated and filled between the breakpoints along a tangential direction, and non-closed edge gaps caused by illumination or shielding are repaired to form a complete closed contour. A boundary uncertainty evaluation model is constructed by combining gray uniformity and gradient intensity in a local neighborhood, a smoothing processing intensity radius is adaptively adjusted according to the boundary uncertainty evaluation model, depth smoothing is applied to a high-risk area, high-confidence area details are reserved, zigzag artifact interference is eliminated, and a high-risk area is obtained. And a continuous and high-precision self-adaptive focus boundary conforming to the real anatomical form of the tissue is generated.

The invention relates to the technical field of medical image processing, in particular to a gynecological endoscope image intelligent analysis and cervical lesion precise diagnosis system. Comprising an image enhancement module, a differential geometric feature extraction module, a topology preserving manifold learning module, a curvature-blood vessel correlation analysis module, a biopsy point accurate positioning module, a real-time intelligent auxiliary diagnosis module, a clinical feedback module and a self-adaptive optimization module. Micro morphological change features are extracted through multi-scale curvature analysis; a topology sensitive encoder and a manifold alignment decoder are adopted, and a key topology structure is kept; establishing a correlation model of the tissue surface curvature change and the blood vessel morphology, and analyzing differential morphological characteristics; determining an optimal biopsy position based on the comprehensive characteristics; according to the method, the diagnosis result and basis are generated, visual display is provided, the detection rate of cervical lesions, especially early minimal lesions, is remarkably increased, the missed diagnosis rate is reduced, and multi-point biopsy is reduced.

The invention discloses an optical fiber coupling real-time correction method in a single-mode and multi-mode optical fiber endoscopic imaging system, which comprises the following steps of: firstly, manually adjusting reflectors M1 and M2 to an optimal multi-mode optical fiber coupling state, acquiring images of light spots at the near end and the far end of a laser beam in the state by using a CCD (charge coupled device) 1 and a CCD 2, and calculating the position of a central coordinate of the images; and collecting a speckle image formed by the light spot through the scattering medium by using a CCD3 (charge coupled device 3). The system monitors the center coordinates of near-end and far-end light spots at the current moment and the correlation coefficient of the current speckle image and the collimation state image in real time. The piezoelectric mirror bracket is fed back and adjusted in real time through the center coordinates of the two spot light spots and the correlation coefficient of the speckles, so that the correlation coefficient of the speckles is kept above a set threshold value, and automatic calibration of light beams is achieved. On the basis of the traditional thinking that two points determine one straight line, the correlation coefficient of using speckles is increased, the alignment precision is improved, and the method has certain practicability and application prospects.

The invention belongs to the technical field of medical robots and minimally invasive surgery, and provides a robot control system and method for blue laser vaporization surgery of prostatic hyperplasia. Mapping the nuclear magnetic image volume data to a deformation field under an ultrasonic acquisition coordinate system, and deforming the preoperative nuclear magnetic image to an intra-operative ultrasonic space by using the deformation field to complete image registration; fusing the registered image with a stereoscopic vision system; the spatial depth of the surface of the target tissue is obtained from the endoscopic image so as to supplement navigation information; according to the utility model, the prostate deformation and probe posture change adaptive capacity in an operation is improved, the real-time visual closed-loop regulation and control capacity is improved, and the characteristics of small light spots, shallow heat diffusion, excellent hemostasis and the like of blue laser are combined, so that the vaporization and hemostasis precision in a tiny blood vessel dense area is ensured, and the problems of large tissue trauma and the like are avoided.

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 discloses an intelligent auxiliary diagnosis and grading system for gastrointestinal tumor endoscopic images, which belongs to the technical field of medical image processing and computer-aided diagnosis and comprises a multi-modal image preprocessing and segmentation module, a lesion feature extraction and diagnosis module, a grading and depth evaluation module and a closed-loop feedback optimization module. The system receives white light, a narrow band and an amplified endoscopic image, adaptive segmentation is performed to obtain a lesion area, mucous membrane morphology, capillary and gland features are extracted, Paris classification, Vienna classification and infiltration depth evaluation are realized, and segmentation parameters are subjected to closed-loop optimization according to classification confidence. And intelligent auxiliary support is provided for early diagnosis and treatment decision of gastrointestinal tumors.

The image processing device 1X includes an acquisition means 30X, a score calculation means 31X, and a classification means 32X. The acquisition means 30X is configured to acquire an endoscopic image in which an examination target is photographed by a photographing unit provided in an endoscope. The score calculation means 31X is configured to calculate scores on likelihoods of respective candidate classes corresponding to types of lesion, wherein the candidate classes are candidates for classification of an image group of the acquired endoscopic image. The classification means 32X is configured to perform the classification of the image group upon determining that at least one of the scores has reached a threshold value.

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.

The invention provides an endoscope image real-time dynamic three-dimensional reconstruction method and system, and the method comprises the steps: obtaining initial monocular endoscope image data, constructing an endoscope image training data set through a Gaussian splash algorithm and a chaos algorithm, constructing a 3D reconstruction constraint network, and carrying out the real-time dynamic three-dimensional reconstruction of an endoscope image. The 3D reconstruction constraint network is pre-trained in combination with the endoscope image training data set and a preset physical loss function, real-time monocular endoscope image data is obtained, a dynamic 3D Gaussian scene is generated, scene rendering is conducted on the dynamic 3D Gaussian scene of the endoscope based on endoscope visual parameters corresponding to the real-time monocular endoscope image data, and the dynamic 3D Gaussian scene of the endoscope is obtained. The method comprises the steps of generating ideal monocular endoscope image data, obtaining a discrimination update parameter group by adopting a rendering discrimination update mechanism, and performing feedback optimization on a 3D reconstruction constraint network based on the discrimination update parameter group. The accuracy, the speed and the robustness of three-dimensional reconstruction of the endoscope are improved.

Provided in the present application are an image enhancement method and apparatus, an electronic device, and a storage medium, relating to the technical field of image processing. The method comprises: acquiring a medical data set, and collecting speckle images by means of an optical fiber endoscope; generating a synthetic data set on the basis of the speckle images and medical images in the medical data set; and performing adversarial training on a deep learning model on the basis of the synthetic data set and the medical data set to generate an image reconstruction model, so as to perform image reconstruction on endoscopic images on the basis of the image reconstruction model to obtain image reconstruction results. The present application solves the problem of poor image enhancement effect of image enhancement in the related art.

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 invention discloses a self-adaptive intervention type single-array-element photoacoustic endoscopic imaging near-field noise removal method based on a spatial domain and morphological characteristics. The method comprises the following steps that 1, original data of photoacoustic endoscopic imaging are obtained; step 2, adaptively generating a patch mask area; 3, preprocessing the image in a frequency domain; step 4, executing strip interference detection based on adaptive spatial domain filtering on the non-plaque region to obtain a spatial domain noise mask; step 5, screening strip-shaped noise areas; step 6, performing interpolation restoration on the noise area; 7, calculating the convergence degree and the noise level in the iteration process; and step 8, outputting a final result after polar coordinate transformation. The intrusive single-array-element photoacoustic endoscopic imaging method can effectively inhibit strip-shaped interference signals occurring in intrusive single-array-element photoacoustic endoscopic imaging and reduce the covering influence of background noise on target signals, so that the imaging quality of a near-end area is improved, and the structural definition and contrast ratio of overall imaging are remarkably optimized.

The image processing device 1X includes an infiltration distance acquisition means 32X and an output control means 33X. The infiltration distance acquisition means 32X is configured to acquire, based on an endoscopic image obtained by photographing an examination target by a photographing unit provided in an endoscope, an infiltration distance of a tumor part of the examination target in the endoscopic image. The output control means 33X is configured to output an image or sound based on the infiltration distance to an output device. It can be used to support examiner's decision making and the like.

The invention discloses an esophageal anomaly detection method and system based on an endoscope image, and relates to the technical field of medical image processing, and the method comprises the steps: extracting a brightness component from an enhanced image, generating a smooth layer and a detail layer through weighted least square filtering, calculating a spectrum guide weight based on a dimension-reduced hyperspectral image, and carrying out the detection of the esophageal anomaly. Fusing the detail layer and the smooth layer to generate a de-noised brightness map, generating a de-noised image through color conversion, calculating spectral intensity characteristics based on the dimension-reduced hyperspectral image, generating an initial foreground mask, and generating an optimized mask through morphological closed operation optimization; through hyperspectral imaging, multi-modal feature fusion and local gamma value enhancement, the spectral feature capture capability of the lesion and the visualization effect of the lesion area are improved, and the accuracy and robustness of lesion segmentation and classification are significantly improved.

The invention provides an endoscope image sensing method and system based on self-supervised learning, and the method comprises the steps: constructing and training an endoscope image sensing model, obtaining a real-time endoscope image sequence pair, inputting the real-time endoscope image sequence pair into the endoscope image sensing model for sensing, outputting a predicted retracement endoscope image sequence, and outputting a predicted retracement endoscope image sequence. An image sequence matching mechanism based on deep learning is adopted, the predicted retracement endoscope image sequence and the real-time retracement endoscope image sequence are matched, difference evaluation and screening are carried out on the predicted retracement endoscope image sequence and the real-time retracement endoscope image sequence after matching, and a corresponding uncertainty evaluation result is generated; and performing interpretability prompting based on the uncertainty evaluation result, and optimizing a corresponding module of the endoscope image sensing system according to a feedback result of the interpretability prompting, thereby realizing efficient and accurate identification of the abnormal region in the endoscope image.