Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

405 results about "Fundus image" patented technology

Cross-modal eye fundus image generation method and system based on generative adversarial network

The invention discloses a cross-modal eye fundus image generation method and system based on a generative adversarial network, relates to the technical field of medical image processing, and constructs an eye fundus focus perception and edge consistency generative adversarial network by taking a cyclic consistency generative adversarial network as a baseline. The core of the method is that a lesion perception mixed attention module is embedded in a bottleneck layer of a generator so as to strengthen the extraction capability of fine features of a lesion area; an edge information extraction module is designed, and key edge features are accurately extracted in combination with Roberts edge detection, wavelet transform and non-local mean denoising; and a joint loss function containing edge consistency loss is constructed, and the semantic consistency of a focus structure during cross-modal generation is ensured by minimizing the feature difference between the source image and the generated image. According to the method, the problems of disordered content, inconsistent structure and unstable training of the generated image in the prior art are effectively solved, and the simulation degree and clinical availability of the generated image are remarkably improved.
Owner:SUZHOU UNIV

Heterogeneous double-flow fusion method and system for grading diabetic retinopathy

The invention discloses a heterogeneous double-flow fusion method and system for diabetic retinopathy grading. The method comprises the following steps: obtaining an output result of diabetic retinopathy grading by utilizing a heterogeneous double-flow architecture; processing an input fundus image into images with different resolutions; extracting global context features from the low-resolution image by using a lightweight visual Transform model distilled by composite knowledge, and extracting local focus features from the high-resolution image by using a convolutional neural network model; performing interactive fusion on the global context features and the local focus features of the double-branch architecture through a symmetric bidirectional cross attention fusion module to obtain enhanced fusion feature representation; and finally, inputting the fusion features into a classifier, and outputting a severity grading result of the lesion. The method aims at improving the accuracy and robustness of hierarchical diagnosis through deep analysis of global information and local details, and can be applied to the medical fields of clinical computer-aided diagnosis, eye image analysis and the like.
Owner:HUNAN NORMAL UNIVERSITY

Cataract surgery navigation control method based on multi-modal fusion

PendingCN121129446AEye surgerySurgical navigation systemsIntraocular pressureTopographical mapping
The invention relates to the technical field of intelligent medical treatment, and discloses a cataract surgery navigation control method based on multi-modal fusion, which comprises the following steps: carrying out lightweight preprocessing on an eye fundus image, ultrasonic probe data, a corneal topographic map and intraocular pressure parameters through an edge computing architecture, and constructing an efficient feature extraction network by adopting a knowledge distillation technology; self-adaptive feature fusion is realized based on an uncertainty quantification mechanism, real-time structure recognition is provided by utilizing an augmented reality technology, an intelligent navigation strategy is generated by pre-training a reinforcement learning model, an instrument control system with multilayer safety guarantee is established, and continuous optimization of the system is realized by adopting an online learning mechanism. According to the invention, the precision and safety of the operation are effectively improved, and an effective technical scheme is provided for intelligent navigation control of the cataract operation.
Owner:浣江实验室 +1

Reading system and reading method for fundus images

The disclosure describes a reading system and a reading method for fundus images, the reading system comprising: an input module for receiving fundus images; a screening module for outputting screening results based on the fundus images, the screening results at least including quality control judgment results and lesion judgment results; a first classification module for classifying the fundus images into screening qualified images and first images to be quality controlled based on the quality control judgment results, and taking at least one image from the first images to be quality controlled and the screening qualified images as an image to be quality controlled; and a quality control module for outputting quality control results based on the image to be quality controlled. According to the disclosure, the screening accuracy of the reading system can be improved.
Owner:SHENZHEN SIBRIGHT TECH CO LTD

Cataract eye fundus image adaptive enhancement method based on fuzzy evaluation

The invention provides a fundus image enhancement method based on adaptive fuzzy evaluation and frequency domain enhancement, and the method comprises the following steps: S1, obtaining cataract fundus image samples of different fuzzy levels, and constructing a training data set; s2, constructing an image adaptive enhancement model based on fuzzy evaluation, wherein the image adaptive enhancement model comprises a fuzzy evaluation module, a consistency keeping module and a frequency adaptive enhancement module; and S3, performing model training on the constructed image adaptive enhancement model by using the training data set to obtain a trained image adaptive enhancement model which is used for adaptive enhancement of the cataract eye fundus image. According to the method, the structural definition and color fidelity of the cataract blurred fundus image can be effectively improved, and the diagnosis availability and clinical value of the image are improved.
Owner:FUZHOU UNIV

Myopia image deep learning recognition model training method

The invention discloses a myopia image deep learning recognition model training method, particularly relates to the technical field of medical image processing and deep learning, and is used for solving the problem that an existing deep learning model lacks anatomical structure priori knowledge guidance in myopia eye bottom image analysis. The method comprises the following steps: acquiring a myopia eye bottom image and anatomical structure priori knowledge data, extracting a multi-scale feature map by using a deep learning model, analyzing the geometric morphology of a key anatomical component based on standard spatial relationship information, and generating a spatial constraint loss item; according to the method, key anatomical path topology coherence is evaluated based on topology connection information, topology constraint loss items are generated, a loss item fusion strategy is dynamically adjusted according to a training stage, finally, a model is iteratively trained to convergence through a gradient back propagation algorithm, and organic combination of medical priori knowledge and a deep learning model is realized. And the clinical rationality and reliability of model output are improved.
Owner:SHANGHAI YUANHE VISION TECH CO LTD

Glaucoma multi-mode auxiliary diagnosis device and electronic equipment

According to the glaucoma multi-mode auxiliary diagnosis device and the electronic equipment, firstly, first feature extraction and second feature extraction are carried out on an eye fundus image and an OCT image respectively, then semantic spaces of an eye fundus image mode and an OCT image mode are aligned by utilizing comparison loss, and the first feature and the second feature are fused by utilizing a cross attention mechanism, so that an eye fundus image is obtained. According to the method, the two modal data are subjected to fusion to obtain fusion features, then the fusion features are subjected to feature extraction to obtain third features, and glaucoma classification judgment is performed based on the third features, so that global modeling of the two modal data can be realized, effective features are extracted to perform glaucoma classification judgment, and the accuracy and timeliness of diagnosis are ensured.
Owner:CENT SOUTH UNIV

Portable system for identifying potential cases of diabetic macular oedema using image processing and artificial intelligence

Diabetes is a disease characterized by high levels of blood glucose. It is important to keep diabetes under control to avoid short- and long-term complications. Diabetes can affect vision due to the alterations it produces in the blood vessels of the retina. This is known as Diabetic Retinopathy (DR), which is one of the leading causes of impaired vision in developed countries. One of the complications of diabetic retinopathy is Diabetic Macular Edema (DME), which is the leading cause of vision loss in diabetic patients and can appear at any stage of diabetic retinopathy. This consists of the gradual accumulation of fluid in the macula, the most important area of the retina. The determination of diabetic macular oedema is very important for the retina. The determination of diabetic macular oedema is very important for adequate treatment of this condition. A variety of technological options are used for detecting diabetic retinopathy, although only the most sophisticated detect macular oedema, a complication that appears as a consequence of diabetic retinopathy and is one of the leading causes of blindness. The invention describes a portable system for detecting diabetic macular oedema by capturing a fundus image using a portable ophthalmoscope; said image is sent via wired or wireless means to an embedded system that has an algorithm based on artificial intelligence, which extracts information from the image and processes same to identify the presence of the condition being studied.
Owner:CENT DE RETINA MEDICA Y QUIRURGICA SC

Eye fundus image quality control method and device, storage medium and electronic equipment

The invention discloses an eye fundus image quality control method and device, a storage medium and electronic equipment, and relates to the technical field of image processing. The eye fundus image quality control method comprises the steps of determining a to-be-processed eye fundus image; based on an effective area of the to-be-processed eye fundus image, determining at least one type of quality quantification data corresponding to the to-be-processed eye fundus image, the effective area being used for representing an unshielded eye fundus structure area; and determining a quality control result of the to-be-processed eye fundus image based on the at least one type of quality quantification data corresponding to the to-be-processed eye fundus image, the quality control result comprising an image quality score and / or a quality problem corresponding to the image quality score. According to the eye fundus image quality control method provided by the embodiment of the invention, the score of the eye fundus image to be processed and the quality problem corresponding to the score can be intuitively known, so that related personnel can know the score and the quality problem, the normalization of the eye fundus image is improved, and standardization of eye fundus image data is facilitated.
Owner:EVISION TECH (BEIJING) CO LTD

Automatic cataract eye fundus image grading method and system based on semi-supervised learning

The invention discloses a cataract fundus image automatic grading method based on semi-supervised learning, and belongs to the field of medical artificial intelligence. Characteristic parameters are extracted through multi-modal feature fusion of the eye fundus image of a patient, a semi-supervised learning neural network model is constructed, a pseudo-label training model is formed in combination with a small amount of labeled data and a large amount of unlabeled data, automatic classification of the eye fundus image of cataract is realized, and the problems of low manual classification efficiency and high labeled data acquisition cost are solved. In the preprocessing stage, texture and color multi-dimensional feature parameters of an image are extracted, and image data are obtained through dimension reduction. In the model construction stage, network training data of double convolution activation layers and double maximum pooling layers are adopted, and the model outputs all levels of probabilities to realize grading. The semi-supervised iterative training adopts a pseudo tag generation and model optimization alternating strategy, and a high-confidence sample expansion training set is screened. In the evaluation stage, the performance of the model is comprehensively measured by using multiple indexes and a visualization technology, and finally the model is deployed and applied to provide reliable support for clinical diagnosis.
Owner:XIAN UNIV OF TECH

Passive domain adaptive eye fundus image segmentation method based on adaptive mask and curvature regularization

The invention belongs to the technical field of image processing, and particularly relates to a passive domain adaptive eye fundus image segmentation method based on adaptive mask and curvature regularization, which comprises the following steps: constructing a teacher-student self-training framework, and generating a pseudo tag by using a weak enhancement teacher model to guide student model training, an adaptive mask consistency strategy is introduced in the training process, adaptive mask processing is carried out on a target domain image, the mask proportion and size are adaptively adjusted according to the sample difficulty and the size of a pseudo-label area, a model is guided to keep prediction consistency under the shielding condition, and thus the pseudo-label reliability and the context modeling capability are improved; meanwhile, by introducing an average negative curvature regularization constraint, an irregular boundary in a prediction result is suppressed, the smoothness and structural continuity of a segmentation result are enhanced, and finally the precision and generalization ability of the model in a cross-device and cross-dataset fundus image segmentation task are improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Myopia eye bottom lesion progress prediction method and system based on multi-modal sequence data

The invention belongs to the field of myopia bottom-of-eye lesion prediction, and discloses a myopia bottom-of-eye lesion progress prediction method and system based on multi-modal sequence data, and the method comprises the steps: extracting fundus image features through employing a local structure guided multi-scale vision Transform; the method comprises the following steps: acquiring table data, extracting features through respective network modules, and carrying out cross-attention mechanism fusion; processing data of irregular time points by using Transform time coding and an LSTM pseudo sequence method, and converting the data into continuous time sequence input; estimating the contribution of each time point data in prediction by using time interval coding and time difference weighting; a weighted attention mechanism is adopted to endow modal information of different time points with different weights, and data features which have the most influence on the progress in different periods are identified; the image features and the table data features are fused through a cross-attention mechanism, and a unified feature vector is formed; and outputting the progress trend of future lesions of the patient. According to the method, the lesion occurrence or progress trend at a specific age or a future time point can be predicted, and a scientific basis is provided for individualized management.
Owner:EYE & ENT HOSPITAL SHANGHAI MEDICAL SCHOOL FUDAN UNIV

Children myopia prediction method based on multi-modal data fusion

A children myopia prediction method based on multi-modal data fusion comprises the following steps: acquiring and preprocessing children myopia original data including clinical data and color fundus image data; constructing a children myopia prediction model; the children myopia prediction model comprises a feature extraction module, a feature fusion module and a result prediction module; the feature extraction module extracts clinical features of the clinical data and image features of the color fundus image data; the feature fusion module fuses the clinical features and the image features to generate final fusion features; inputting the final fusion feature into a result prediction module to generate a prediction probability; training a children myopia prediction model according to the prediction probability; and inputting the verification set in the child myopia original data into the trained child myopia prediction model to generate a prediction result. According to the method, through a multi-head self-attention mechanism, the problem of dynamically weighting different modal features is solved, and the robustness of the model is remarkably improved.
Owner:HANGZHOU DIANZI UNIV

Retina fundus image generation method based on diffusion model

The invention discloses a retina fundus image generation method based on a diffusion model. Firstly, a training data set and a regularization data set are constructed; then, constructing a diffusion model which comprises a variational auto-encoder, a U-Net denoising network and a text encoder; the variational auto-encoder comprises a variational encoder and a variational decoder, and the U-Net denoising network is embedded between the variational encoder and the variational decoder; the structured text prompt passes through a text encoder to obtain a text embedding vector, and the vector is injected into the U-Net denoising network as condition information; the variational encoder compresses the retina fundus image into potential features, the U-Net denoising network carries out denoising on the potential features under the guidance of condition information, and the denoised potential features are reconstructed into a high-resolution retina fundus image through the variational encoder; and finally, generating a retina fundus image based on the pre-trained diffusion model. The controllability of image generation is improved, and the generated image is highly consistent between the focus form and the medical description.
Owner:HEBEI UNIV OF TECH

Fundus imaging apparatus

A fundus imaging apparatus includes two or more curved mirrors, an illumination optical system, and an image sensor. The illumination optical system includes a slit with an opening configured to be disposed at a fundus conjugate position. Here, the fundus conjugate position is substantially conjugate optically to a fundus of an eye to be examined. The illumination optical system is configured to irradiate slit-shaped illumination light, that is generated by irradiating light from a light source onto the slit, onto the fundus through the two or more curved mirrors. The image sensor is configured to be disposed at the fundus conjugate position and to receive returning light from the eye to be examined. At least one of both ends of the opening in a longitudinal direction is displaced in a shorter direction of the opening with reference to the longitudinal direction passing through a center of the opening.
Owner:TOPCON CORPORATION

Diabetic retinopathy image classification method based on multi-feature fusion network model

The invention discloses a diabetic retinopathy image classification method based on a multi-feature fusion network model, and the method comprises the steps: S1, obtaining an initial fundus image data set, and constructing a sample training set based on the initial fundus image data set, a first enhanced image data set, and a second enhanced image data set; s2, constructing a retinopathy image classification model, and training the retinopathy image classification model based on the sample training set to obtain a trained retinopathy image classification model; the retinopathy image classification model comprises a first multi-feature fusion enhancement module, a second multi-feature fusion enhancement module, a third multi-feature fusion enhancement module, a fourth multi-feature fusion enhancement module and a classification module; the classification module performs classification based on the input data to obtain a retinopathy image classification result. By designing a plurality of multi-feature fusion enhancement modules and double attention modules, hierarchical fusion of lesion features is realized, the recognition precision of tiny lesions is improved, dynamic calibration of a lesion area feature map is realized, and finally, high-precision and robust DR automatic classification is realized.
Owner:DALIAN NEUSOFT UNIV OF INFORMATION

Passive field adaptive eye fundus image segmentation method and device based on difficulty perception

The invention discloses a difficulty perception-based passive domain adaptive fundus image segmentation method and device, and belongs to the technical field of computer vision processing, and the method comprises the steps: obtaining a target domain fundus image, and carrying out the preprocessing of the target domain fundus image; initializing a teacher model and two student models; performing weak enhancement processing on the preprocessed image, inputting the processed image into a teacher model, obtaining a prediction probability, calculating an entropy value of each sample, and dividing the samples into an easy sample set and a difficult sample set according to the entropy values; strong enhancement processing is carried out on the easy sample set and the difficult sample set, and then the easy sample set and the difficult sample set are respectively input into student models for training; external information is injected into the two student models respectively, and the training process is optimized; after each iteration period is finished, the parameters of the teacher model are updated based on the parameters of the two student models until the teacher model converges; and inputting a to-be-segmented eye fundus image into the converged teacher model to obtain a segmentation result of the eye fundus image. According to the invention, high-precision segmentation of the optic cup and optic disc of the eye fundus image is realized.
Owner:UNIV OF JINAN

Image processing method, image processing device, program

An image processing method performed by a processor includes: a step of acquiring a fundus image in which choroid blood vessels are visualized; a step of extracting choroid arteries in the fundus image acquired in the acquiring step by performing image processing on the fundus image; and a step of generating a fundus image in which the choroid arteries extracted in the extracting step are highlighted.
Owner:NIKON CORP

System and method for detecting opthalmic conditions using machine learning

A system for detecting retinal detachment is provided herein. The system includes an imaging device configured to capture a retinal fundus image of an individual, a processor, and a memory storing instructions. When executed by the processor, the instructions cause the system to preprocess the retinal fundus image to remove extraneous background information and enhance retinal features, input the preprocessed retinal fundus image into a trained machine learning model, generate a determination of whether the retinal fundus image indicates presence of retinal detachment using the trained machine learning model, and output the determination to a user interface. The machine learning model is trained on a set of labeled retinal fundus images to classify images as indicating presence or absence of retinal detachment.
Owner:DXAI INC

Eye fundus image synthesis method and device, electronic equipment and storage medium

The embodiment of the invention provides a fundus image synthesis method and device, electronic equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the steps of obtaining a fundus center through target detection based on an original fundus image, and obtaining an initial light spot through light spot generation; configuring the light spot grade of the initial light spot based on the distance between the initial light spot and the fundus center; modifying light spot parameters of the initial light spot according to the light spot grade to obtain a target light spot; performing image synthesis on the target light spot and the original fundus image to obtain an intermediate fundus image; and performing image reconstruction based on the middle fundus image to obtain a target fundus image. According to the embodiment of the invention, the image quality of the eye fundus image after formation can be improved.
Owner:SOUTHERN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Fundus disease multi-label detection method based on OfficientNet and spatial attention mechanism

The invention discloses a fundus disease multi-label detection method based on an OfficientNet and a space attention mechanism, and belongs to the crossing field of medical image processing and artificial intelligence. According to the method, a convolutional neural network with an OfficientNet-B4 as a backbone is constructed, and a space attention module is embedded, so that concurrent detection of various common fundus diseases in a fundus image is realized. For the problems of high resolution, uneven image quality, unbalanced categories, label scarcity and the like of fundus images, a data preprocessing strategy including CLAHE brightness enhancement and monocular label reconstruction is provided; according to the method, a Focal Loss loss function and a Cosine Annealing with Warm Restarts learning rate scheduler are introduced into model training, so that the learning ability of the model for a few categories and the overall convergence efficiency are improved. And the constructed model supports multi-label independent prediction. Experimental results show that the method is superior to an existing method in evaluation indexes such as accuracy, precision and recall rate, has good robustness and popularization value, and is suitable for various application scenes such as primary ophthalmology screening, remote diagnosis and auxiliary clinical decision making.
Owner:JIANGSU OCEAN UNIV +1

AI analysis method for fundus image blood vessels

The invention relates to the field of medical image processing, and discloses an AI analysis method for fundus image blood vessels, which comprises the following steps: acquiring images at different time points of the same fundus, respectively reconstructing a blood vessel topology network and measuring geometric parameters; constructing an equivalent blood flow resistance network based on the network and a preset fluid dynamic model, and calculating a static function field containing parameters such as virtual blood flow at each time point; spatial registration is carried out on the two time point function fields, differential calculation is carried out on corresponding blood vessel segment parameters after registration, a differential data set is generated, a visual differential stress evolution graph is constructed, and then an analysis result of fundus image blood vessels is generated. According to the method, dynamic and multi-dimensional quantitative evaluation of the function evolution process of the fundus vascular network under the stress reaction is realized through space-time comparison and function modeling, and an accurate and comprehensive decision basis is provided for early diagnosis, illness monitoring and curative effect evaluation of related fundus diseases.
Owner:SHANGHAI SUPORE INSTR

Retina image registration method and system based on grid supervision and key point learning

The invention provides a retina image registration method and system based on grid supervision and key point learning, and belongs to the technical field of medical image processing. The method comprises the following steps: acquiring an RGB fundus image pair; encoding the RGB eye fundus image pair through a shared feature extraction branch to obtain a down-sampling feature map; processing the down-sampling feature graph through a key point extraction branch and a descriptor decoder branch respectively, and extracting a key point probability graph and a feature descriptor; predicting the offset of the key points in the local window based on the paired feature descriptors through a key point offset prediction module; and carrying out position calibration on the key points in the key point probability graph based on the offset, and outputting a registered image. According to the method, self-supervised training is realized by using dense gridding marking points, and manual marking is not needed; through lightweight network design and a key point offset calibration mechanism, high registration precision is maintained while the parameter quantity is significantly reduced, and the method is suitable for clinical real-time deployment and retinal disease analysis.
Owner:SHANDONG UNIV

Fundus imaging device

A fundus imaging device has a fixation optical system, an OCT optical system, an imaging optical system, and a controller. The controller is configured to acquire a focus evaluation value based on a slit image formed by slit-shaped illumination light on a two-dimensional imaging element of the imaging optical system in a case where an optical scanner of the imaging optical system deflects in a predetermined direction. The controller is configured to perform diopter correction control of the OCT optical system by driving a first focus adjustment unit of the OCT optical system based on the focus evaluation value.
Owner:NIDEK CO LTD

Fundus imaging system

PendingUS20260013722A1OthalmoscopesReflection illuminationDisplay device
The invention discloses a fundus imaging system, which includes an optical path folding lens set, a virtual reality display, visible light fixation lamps, an illumination module, an image sensor, and a processor. The virtual reality display and the human eye are located on different sides of the optical path folding lens set. The virtual reality display forms images on the retina of the fundus of the human eye through the optical path folding lens set. The visible light fixation lamps are sequentially turned on to guide the eyeball of the human eye to rotate. When the visible light fixation lamp is turned on, the illumination module emits illumination light through the optical path folding lens set to illuminate the retina. The retina reflects the illumination light to form fundus light. The image sensor receives fundus light through the optical path folding lens set to form a sub-fundus image. The processor stitches all sub-fundus images into a full-fundus image and drives the virtual reality display to display the full fundus image.
Owner:MEDIMAGING INTEGRATED SOLUTION INC

Real-time ir fundus image tracking in the presence of artifacts using reference landmarks

To provide a more efficient system / method for eye motion tracking.SOLUTION: A system and method for eye motion tracking. An anchor point and a plurality of auxiliary points are selected from the reference image. Individual live images in the sequence of images are then searched for a match between the anchor point and the ancillary point. First, an anchor point is found, and then the search for individual auxiliary points is limited to a search window defined by the known distance and / or orientation of the auxiliary point to be searched relative to the anchor point.SELECTED DRAWING: Figure 4
Owner:CARL ZEISS MEDITEC INC +1

Blood vessel analysis method and system based on ultra-wide-angle fundus fluorescent angiography image

ActiveCN121010589AImage enhancementImage analysisFundus fluorescein angiographyData set
The invention relates to the technical field of medical image classification, and discloses a blood vessel analysis method and system based on an ultra-wide-angle fundus fluorescent angiography image, and the method comprises the steps: obtaining the ultra-wide-angle fundus fluorescent angiography image, and carrying out the preprocessing of the fundus image, and obtaining a sample library; based on the images in the sample library, marking the fundus blood vessels, and constructing a fundus blood vessel analysis training data set; constructing a model, training the model by using the fundus blood vessel analysis training data set, and automatically extracting a blood vessel skeleton of the to-be-detected image through the trained model; according to the extracted vascular skeleton, a cross point detection algorithm is adopted to identify vascular nodes; and carrying out region division on the fundus image, calculating a blood vessel curvature value in each region according to a blood vessel skeleton and a blood vessel node, and obtaining an analysis result of fundus blood vessel distribution and a blood vessel form. The method can be used for accurately observing the curvature change of the blood vessel in each quadrant and each distance, and assisting a clinician in quickly and accurately analyzing the fundus angiography image.
Owner:TONGJI UNIV

An illumination device for fundus observation

The application provides an illumination device for fundus observation, comprising a contact lens, a light guide plate and an illumination light source; the contact lens is provided with an arc-shaped side and a light-in side, the arc-shaped side is used for adhering to the cornea; the light-in side is provided with the light guide plate; the light guide plate is provided with a light inlet and a light outlet; the incident light of the illumination light source is incident into the light guide plate through the light inlet, the light guide plate reflects the incident light and the reflected light is incident into the contact lens through the light outlet; the incident light passes through the arc-shaped side of the contact lens and the cornea and is incident into the eyeball to illuminate the fundus. The illumination device for fundus observation of the application sets the illumination light source on the side of the contact lens and limits and adjusts the angle of the light incident into the eyeball through the light guide plate, so that the number of the light incident into the fundus is increased, and the contact fundus imaging device can form clear and accurate fundus imaging while reducing the traditional light spot interference.
Owner:SUZHOU JUNXIN SHIDA MEDICAL TECH CO LTD

Eye fundus image quality evaluation method and system, intelligent terminal and storage medium

The invention relates to a fundus image quality evaluation method and system, an intelligent terminal and a storage medium, and relates to the technical field of fundus image quality evaluation, and the method comprises the steps: obtaining a to-be-evaluated fundus image; inputting the eye fundus image into a backbone network based on a ResNet18 network structure to obtain a multi-scale feature map; performing spatial size scaling and alignment processing on the multi-scale feature map to obtain a scaled and aligned feature map; carrying out series fusion on the scaled and aligned feature maps to obtain a fused feature map; adding the position coding matrix and the fusion feature map element by element to obtain a coding feature map; inputting the coding feature map into a multi-size feature fusion module to obtain a multi-size fusion feature map; inputting the multi-size fusion feature map into a plurality of feature optimization modules to obtain an optimized feature map; and splicing and fusing the plurality of optimized feature maps, and inputting the fused optimized feature maps into a full connection layer for binary classification so as to output a quality evaluation result of the eye fundus image. The method has the effect of improving the accuracy of eye fundus image quality evaluation.
Owner:NINGBO MING SING OPTICAL R & D

Medical image processing method, fundus image processing method, model generation method, equipment, storage medium and program product

The embodiment of the invention provides a medical image processing method, a fundus image processing method, a model generation method, equipment, a storage medium and a program product, which are applied to the field of image processing, and comprise the following steps: obtaining a first medical image and clinical information obtained by shooting a first organ object of a target user; inputting the first medical image and the clinical information into an image processing model, extracting image features in the first medical image by using a first image encoder in the image processing model, and extracting text features of the clinical information by using a text encoder; using a feature reconstruction module to obtain reconstruction features associated with the second organ object based on the image features, and using the text features to correct the reconstruction features; generating, using a third image decoder, a second medical image based on the corrected reconstruction feature; the second medical image comprises a second organ object and is used for analyzing the second organ object. According to the scheme of the embodiment of the invention, the obtaining cost of the second medical image is reduced.
Owner:BEIJING FRIENDSHIP HOSPITAL CAPITAL MEDICAL UNIV +1