18 results about "Narrow-band imaging" patented technology

The invention relates to the technical field of medical image processing, in particular to a cross-modal image fusion detection system for endoscopic early cancer lesions, which comprises a data acquisition module for acquiring a white light endoscope and a narrow-band imaging image; the data annotation module carries out pixel-level annotation, and the data enhancement module amplifies a data set by using CycleGAN; the white light data module and the narrowband data module train feature extraction models respectively; the feature alignment and attention module solves the problem that feature scales and semantics between two modes are inconsistent, and efficient fusion is achieved. The edge enhancement module enhances feature extraction of small focuses through the generative adversarial network; the fusion model construction module fuses the features and the transition area data to generate a fusion model; and the output module processes the white light and the narrow-band imaging image and outputs a fused image. Through feature alignment, an attention mechanism and a CyclGAN data enhancement technology, the problem of insufficient medical image data is effectively solved, the model generalization ability is enhanced, and efficient and accurate early cancer focus detection is realized.

The utility model relates to a lens structure of a double-lens capsule endoscope, which comprises two capsule endoscope lenses with different imaging functions, namely a lens with a narrow-band imaging characteristic and a high-definition ultra-wide-angle lens, the optical system of the first lens comprises a first lens group, a first diaphragm, a second lens group and first protective glass; the first lens group comprises a meniscus negative lens with negative focal power, a convex-concave negative lens with negative focal power and a meniscus lens with positive focal power; the second lens group comprises a biconvex lens with positive focal power and a biconcave lens with negative focal power; the optical system of the second lens comprises a third lens group, a second diaphragm, a fourth lens group and second protective glass; the third lens group comprises a convex-concave positive lens with positive focal power; and the fourth lens group comprises a bonding lens and a convex-concave lens with positive focal power, and the bonding lens is formed by bonding a biconvex lens with positive focal power and a concave-convex lens with negative focal power and has the positive focal power. The lens can enlarge the view field coverage range and improve the detection accuracy.

The invention relates to the technical field of medical image processing, in particular to a combined narrowband and fluorescence imaging method and system for bronchoscope focus detection. According to the method provided by the invention, based on deep learning, features with discrimination capability in a narrow-band imaging image and an auto-fluorescence imaging image are selected and extracted, fusion of different imaging technology advantages of focus detection is realized through decision fusion, and the speed and accuracy of focus identification are improved; meanwhile, the method provided by the invention can better adapt to different scenes and lesion features, has better generalization ability, improves the specificity and sensitivity of focus detection, and is beneficial to improving the diagnosis accuracy and efficiency.

An apparatus for detecting and treating gastrointestinal pathology. The apparatus includes a wireless capsule, where the wireless capsule includes at least one of: an optical imaging system, a thermal imaging system, or a camera. The camera is a narrow band imaging system, a white light imaging system, or both.

The invention relates to the technical field of medical imaging, in particular to a narrowband-based multi-harmonic magnetic particle imaging method, which comprises the following steps of: determining a magnetic particle imaging area, and acquiring a first area and a second area according to the magnetic particle imaging area; placing a magnetic nanoparticle sample in the first area, externally applying a magnetic field, and extracting harmonic signals to construct a system matrix; placing a measured object in the second area and externally applying a magnetic field, and extracting harmonic signals to construct a harmonic signal matrix of the measured object; and according to the system matrix and the harmonic signal matrix of the measured object, constructing an equation to be solved and carrying out inversion solution to obtain an image of magnetic nanoparticle concentration distribution. Compared with a broadband imaging technology, the narrow-band imaging technology is adopted, the requirement for the bandwidth of a magnetic particle imaging system is lowered, and the problem of insufficient bandwidth under high-frequency excitation is solved.

The present application relates to the technical field of medical image processing, and particularly relates to a combined narrowband and fluorescence imaging method and system for bronchoscopy lesion detection. The method provided by the present application realizes selection and extraction of features with discriminative ability in narrowband imaging images and autofluorescence imaging images based on deep learning, and realizes fusion of advantages of different imaging technologies for lesion detection through decision fusion, thereby improving the speed and accuracy of lesion recognition. Meanwhile, the method provided by the present application can better adapt to different scenes and lesion characteristics, has better generalization ability, improves the specificity and sensitivity of lesion detection, and is beneficial to improving the diagnostic accuracy and efficiency.

The application belongs to the technical field of endoscope imaging, and provides an endoscope color crosstalk suppression method and an endoscope. The method comprises the following steps: acquiring an original endoscope image collected by an image sensor; identifying target object parameters in the original endoscope image, wherein the target object parameters comprise a target color channel corresponding to a target object and a target size parameter; determining a target blur convolution kernel corresponding to the target object parameters according to a mapping relationship between calibration target object parameters and a calibration blur convolution kernel, wherein the target blur convolution kernel represents a combination of an optical diffusion parameter corresponding to the target size parameter of the target object in the target color channel and a sensor crosstalk parameter in a target channel; and performing deconvolution processing on the original endoscope image based on the target blur convolution kernel to obtain an endoscope imaging image. The method can solve the problems of tissue boundary blurring and tissue color distortion caused by optical diffusion and image sensor crosstalk during narrowband imaging, thereby more accurately displaying the color change of the tissue.

This invention relates to a dual-lens capsule endoscope lens, comprising two capsule endoscope lenses with different imaging functions: a lens with narrowband imaging characteristics and a high-definition ultra-wide-angle lens. The optical system of the first lens includes a first lens group, a first aperture, a second lens group, and a first protective glass. The first lens group includes a meniscus negative lens with negative optical power, a convex-concave negative lens with negative optical power, and a meniscus lens with positive optical power. The second lens group includes a biconvex lens with positive optical power and a biconcave lens with negative optical power. The optical system of the second lens includes a third lens group, a second aperture, a fourth lens group, and a second protective glass. The third lens group includes a convex-concave positive lens with positive optical power. The fourth lens group includes a cemented lens and a convex-concave lens with positive optical power. The cemented lens is formed by cementing a biconvex lens with positive optical power and a concave-convex lens with negative optical power, and also has positive optical power. This lens can expand the field of view coverage and improve detection accuracy.

The invention discloses a cervical cancer screening system and equipment. The cervical cancer screening system comprises a light emitting unit and a processing unit, the light emitting unit is used for emitting target light irradiated on to-be-detected tissue in a target working mode, and the target working mode comprises at least one of a white light imaging mode, a fluorescence imaging mode and a narrow-band imaging mode; the processing unit comprises a light emitting control unit and an image processing unit; the light emitting control unit is respectively connected with the light emitting unit and the image processing unit; and the light emitting control unit is used for generating a detection image according to the target light and carrying out lesion position identification and lesion grading on the to-be-detected tissue based on the detection image. By arranging the light emitting unit and the processing unit, accurate positioning and grading of cervical lesions are achieved.

The invention relates to the technical field of image processing, in particular to an intelligent image recognition system based on a digestive system department image. According to the technical scheme, the system comprises an acquisition terminal and a processing terminal, wherein the acquisition terminal is used for acquiring a first image of the intestinal tract of a user in a white light mode and a second image corresponding to a narrow-band imaging mode under different light source incidence angles; the processing terminal identifies a three-dimensional convex-concave structure of the inner wall of the intestinal tract according to the gray difference of the first image at different light source incidence angles so as to position a three-dimensional change area; screening out pixel points with blood vessel features in the second image, and marking blood vessel pixel points at corresponding positions of the first image; performing texture analysis on the blood vessel pixel points of the three-dimensional change areas to obtain a texture distribution coefficient of each three-dimensional change area; and according to the texture distribution coefficient and the optical flow characteristics generated by each three-dimensional change area in the adjacent image frames, carrying out area division on the first image so as to improve the accuracy of image area intelligent identification.

This invention provides a novel magnifying endoscopic grading method and system for superficial esophageal squamous cell carcinoma based on IPCL recognition, relating to the fields of medical image processing and endoscopic-assisted diagnosis. This invention acquires narrowband or blue light imaging frames, uses a transparent cap for scale calibration, performs vascular enhancement, threshold segmentation, and morphological opening and closing operations on the images, extracts the vascular skeleton and calculates roughness indices, and simultaneously performs connected component analysis and maximum diameter measurement on avascular and stretched regions. Grading is determined by combining preset thresholds across multiple image frames, outputting the grading results and recording key parameters, thus achieving objective, accurate, stable, and repeatable automatic grading of invasion depth.

The present invention discloses a high luminous flux Halpha band ultra-wide angle lens, which includes a front lens group and a rear lens group. The aperture stop is located between the front lens group and the rear lens group. In the front lens group, lens L1 is a negative meniscus lens, lens L2 is a negative biconcave lens, lens L3 is a biconcave negative lens, lens L4 is a biconvex positive lens, and lens L5 is a biconvex positive lens. The combined focal length f 前 of the front lens group is 60.878 ± 2 mm. In the rear lens group, lens L6 is a biconcave negative lens, lens L7 is a biconvex positive lens, lens L8 is a biconvex positive lens, lens L9 is a biconvex positive lens, and lens L10 is a biconvex positive lens. The combined focal length f 后 of the rear lens group is 88.576 ± 2 mm. The narrowband filter is placed at the aperture stop position. The high luminous flux Halpha band ultra-wide angle lens of the present invention has 4 times the light passing ability compared with the traditional wide-angle lens, and the image quality is uniform in the field of view. The angles of the light rays incident on the filter in each field of view are similar, which is more suitable for narrowband imaging with a filter.

The invention provides a SiC-based heat-proof material gas-solid interface unbalanced reaction analysis method under high enthalpy, which mainly comprises the following steps: (1) on the basis of a SiC-based composite ceramic material, constructing a multi-physical field coupling thermal environment by utilizing a high-enthalpy plasma wind tunnel and regulating and controlling flow field parameters, structures and material surface reaction conditions; and (2) then, cooperatively applying four spectroscopy diagnostic technologies of radiation spectrum, narrow-band imaging spectrum, laser absorption spectrum and infrared radiation, and synchronously measuring multiple physical quantities of spatial and temporal distribution of a near-wall flow field of the SiC-based composite ceramic material to extract associated characteristics of the surface macroscopic thermal response and near-wall flow of the SiC-based composite ceramic material. And furthermore, the catalysis-oxidation-nitridation competitive coupling rule in the gas-solid interface unbalanced reaction of the SiC-based material under the long-time high enthalpy is systematically disclosed. According to the invention, multi-dimensional analysis can be provided for gas-solid interface non-equilibrium reaction mechanism research, and fine simulation and quantitative characterization of multi-field coupling phenomena such as passive oxidation, active oxidation, passive / active oxidation transition and the like can be realized.

The present invention relates to the field of medical imaging technology, and in particular to a narrowband multi-harmonic magnetic particle imaging method, comprising: determining a magnetic particle imaging region, obtaining a first region and a second region based on the magnetic particle imaging region; placing a magnetic nanoparticle sample in the first region and applying an external magnetic field, extracting harmonic signals to construct a system matrix; placing a test object in the second region and applying an external magnetic field, extracting harmonic signals to construct a test object harmonic signal matrix; constructing an equation to be solved based on the system matrix and the test object harmonic signal matrix and performing an inverse solution to obtain an image of the magnetic nanoparticle concentration distribution. The present invention adopts narrowband imaging technology, which reduces the bandwidth requirements of the magnetic particle imaging system compared to broadband imaging technology, solving the problem of insufficient bandwidth faced under high-frequency excitation.

The present invention belongs to the field of medical image processing technology, specifically a cross-modal endoscopic image conversion and lesion area segmentation method. The present invention converts the digestive tract endoscope white light image into a high-quality narrowband image by constructing a neural network based on intrinsic representation learning; uses an unsupervised training essential feature extractor to obtain the essential features of the white light image, and predicts the lesion area through a void space convolution pooling pyramid network to obtain the segmentation result of the lesion area; during testing, the white light image to be tested only needs to be forward propagated once with an auxiliary narrowband image to obtain the narrowband image corresponding to the white light image. This method adopts an unsupervised learning method, has good generalization, and has excellent effects on different endoscopic devices. The present invention can provide additional narrowband imaging for white light endoscope equipment and provide a better reference for doctors' diagnosis. The lesion area segmentation based on the assistance of narrowband images can automatically locate the lesion area, thereby greatly improving the efficiency of disease diagnosis and reducing the morbidity and mortality.

The invention belongs to the technical field of endoscope imaging, and provides an endoscope color crosstalk suppression method and an endoscope, and the method comprises the steps: obtaining an original endoscope image collected by an image sensor; identifying target object parameters in the original endoscope image, wherein the target object parameters comprise a target color channel and a target size parameter corresponding to a target object; determining a target fuzzy convolution kernel corresponding to the target object parameter according to a mapping relation between a pre-calibrated calibration target object parameter and a calibration fuzzy convolution kernel, the target fuzzy convolution kernel represents a combination of an optical diffusion parameter corresponding to a target size parameter of the target object under the target color channel and a sensor crosstalk parameter under the target channel; and performing deconvolution processing on the original endoscope image based on the target fuzzy convolution kernel to obtain an endoscope imaging image. The problems of tissue boundary blurring, tissue color distortion and the like caused by optical diffusion and image sensor crosstalk during narrow-band imaging are solved, so that the tissue color change is displayed more accurately.

This invention relates to a multimodal imaging capsule endoscopy system, comprising: a capsule endoscope, an external wireless power supply module, and an image receiving and processing module. The capsule endoscope includes a white light and narrow band imaging module for acquiring white light and narrow band images, an autofluorescence imaging module for acquiring autofluorescence images, a wireless transmission module for transmitting the white light, narrow band, and autofluorescence images to the external image receiving and processing module, a light source control module for controlling the on / off state of different light sources within the capsule endoscope, a wireless power supply receiving module for providing power to the capsule endoscope, a position control module for controlling the position and orientation of the capsule endoscope in the gastrointestinal tract, and a capsule shell encapsulation. The external wireless module provides power to the capsule endoscope via the wireless power supply receiving module. The image receiving and processing module receives and analyzes images acquired by the capsule endoscope via the wireless transmission module. Compared with existing technologies, this invention achieves sensitive, accurate, and non-destructive detection of early-stage atypical hyperplasia or superficial gastrointestinal cancer, significantly reducing missed detections and false positives.

This invention discloses a comprehensive decision support method and system for potential oral malignant diseases, comprising: constructing a pre-diagnosis risk prediction agent that integrates patient behavioral risk factors, genetic susceptibility markers, and multispectral initial screening images; generating a malignancy probability trajectory and triggering tiered screening through a time-series prediction model; establishing an in-diagnosis precision assessment agent that performs differential homeomorphic registration of autofluorescence and narrowband imaging images to generate fused data, and constructing an interpretable reasoning network to locate critical areas of malignancy in conjunction with pathological grading; constructing a post-diagnosis dynamic monitoring agent that establishes a digital twin model based on lesion baseline data, extracts mucosal texture and vascular morphological evolution features from each follow-up visit to generate malignancy trend curves and individualized intervention strategies; and constructing a multi-agent co-evolutionary framework that uses desensitized full-cycle data to perform federated closed-loop iterative optimization of the parameters of each agent. This aims to improve the early identification accuracy of precancerous lesion malignancy risk and optimize clinical intervention pathways.