47 results about "Optic disc size" patented technology

A system for hypertensive retinopathy (HTNR) detection includes a processor and a memory, including instructions stored thereon, which when executed by the processor, cause the system to: preprocess a retinal image using contrast enhancement, noise reduction and / or resolution normalization; segment a plurality of vessels from the preprocessed retinal image to generate a vessel segmentation map; detect a retinal marker, a vascular marker and / or an optic disc marker in the preprocessed retinal image using a first machine learning model; generate a severity score based on the detections; determine that the severity score exceeds a predefined threshold; and generate an output indicating a presence of HTNR based on the vessel segmentation map and the severity score using a second machine learning model.

The invention provides an optic disk real-time continuous tracking method and device, and relates to the technical field of medical image processing. According to the method, the video sequence of the ophthalmologic operation is acquired and preprocessed, and then the preprocessed video sequence is subjected to multi-scale feature extraction and optic disc target detection, so that an optic disc detection target is obtained; the optic disk detection target is based on Kalman filtering prediction and appearance feature matching, an adaptive gating matching mechanism is introduced to carry out inter-frame target trajectory association, a target trajectory is maintained in combination with an appearance feature cache updating mechanism and ReID cosine similarity retrieval, and a trajectory tracking result is output; wherein the trajectory tracking result comprises a continuous tracking result of the optic disc position, the confidence coefficient, the trajectory identifier and the timestamp. According to the invention, the detection precision of the small-scale optic disc is improved, the shielding recovery and track continuity are enhanced, and high-precision, high-robustness and real-time optic disc continuous tracking is realized in complex operation scenes of strong reflection, low contrast, local shielding and the like.

The invention relates to a diabetic retinopathy fundus photography grading report system combined with a clinical guide, based on an artificial intelligence deep learning technology, and belongs to the field of fundus lesion analysis. The system accurately identifies and segments various lesions such as microhemangioma, bleeding, exudation and the like and symbolic structures such as optic discs, macular regions and the like by automatically analyzing fundus photographic images. The system adopts ICDR international standards to grade diabetic retinopathy, and provides diagnosis and treatment suggestions for lesion characteristics in combination with clinical guidelines of American ophthalmology institute in 2019. Through big data training, the system can generate detailed reports in real time, the early screening rate is remarkably improved, misdiagnosis and missed diagnosis are reduced, and the diagnosis speed and accuracy are improved. The system comprises a plurality of modules, such as an image pre-classification module, a deep learning focus recognition module, an ICDR grading module and a report generation module, efficient and accurate diabetic retinopathy diagnosis and grading are cooperatively achieved, and the clinical management level is improved.

This application discloses a method, apparatus, device, storage medium, and product for optic disc segmentation. The method includes: extracting multi-level features from a fundus image at both local and global levels; generating several levels of local and global features in ascending order; and then fusing the features in descending order to obtain fused features, thereby obtaining the optic disc segmentation result based on the lowest-level fused features. Each level of feature fusion includes: fusing the local and global features of the current level to obtain preliminary fused features; filtering the preliminary fused features of the current level using a spatial attention module; weighting the local and global features of the current level using the filtered data; and then combining the two weighted features with the fused features output from the next higher level to generate the final fused features of the current level. This application can improve the segmentation accuracy of the optic disc.

This disclosure provides a measurement system and method for the pathological features of hypertensive retinopathy. The measurement system includes: an acquisition module that acquires fundus images; a partitioning module that receives the fundus images and identifies and partitions the optic disc region; a segmentation module that uses an arteriovenous segmentation model to segment the fundus images into arteries and veins to obtain a three-valued image of the segmentation results. The arteriovenous vessel marking results include arterial and venous marking results formed by marking the boundaries of vessels with diameters larger than a preset vessel diameter in the training fundus images, and small vessel marking results formed by marking the course of vessels with diameters not larger than the preset vessel diameter. The measurement module measures the pathological features of hypertensive retinopathy in the fundus images based on the vessels larger than the preset vessel diameter in the partitioning and segmentation results. This disclosure enables efficient and objective measurement of the characteristics of hypertensive retinopathy.

The invention relates to the technical field of medical image processing, and discloses a premature infant retinopathy diagnosis system based on an isotropic convolutional network, which comprises an image acquisition module, a segmentation module, a partition module, a staging module and a result generation module. The segmentation module is used for processing the retina image by adopting an equivariant convolutional network, and accurately segmenting an optic disc and a lesion area; the partitioning module divides a retina region according to an optic disc segmentation result; the staging module integrates the lesion segmentation result and the zoning result to output lesion staging; and the result generation module integrates all information to generate a comprehensive diagnosis report. According to the premature infant retinopathy diagnosis method and system, the image segmentation precision is improved through the equivariant convolutional network, and the automatic and high-accuracy comprehensive diagnosis of the premature infant retinopathy is realized by utilizing the cooperative work of the modules, so that the clinical diagnosis and treatment decision is effectively assisted.

The embodiment of the invention provides a fundus image segmentation method and related equipment, and belongs to the technical field of medical image processing. The method comprises the following steps: constructing and training a segmentation model which integrates a multi-scale U-Net main network, a deblurring diffusion module and a variational auto-encoder module; wherein the multi-scale U-Net enhances detail capture by introducing frequency domain reweighted jump connection; the variational auto-encoder module provides global structure prior of the image; and the deblurring diffusion module uses the prior as condition guidance to de-noise and enhance the features. According to the method, three advanced models are innovatively and synergistically fused, the problems that in the prior art, the segmentation precision of complex blood vessels and optic disc / optic cup structures in fundus images is insufficient, the robustness of blurred images is poor, and a large amount of labeled data is relied on are effectively solved, and the segmentation accuracy and stability are remarkably improved.

This invention pertains to ophthalmic image processing methods, specifically a method and system for ROI region segmentation to assist optic disc recognition. The method includes the following steps: acquiring a fundus image to be identified; identifying peripapillary atrophy arc segments in the fundus image to be identified, obtaining the identification results; determining a pre-selected region based on the intensity centroid of the fundus image to be identified; within the pre-selected region, determining the region of interest (ROI) using quadrilateral correction and the peripapillary atrophy arc segment identification results; and performing image recognition based on the ROI. This involves identifying the peripapillary atrophy arc segments and using target boundaries that intersect the peripapillary atrophy arc segments twice to perform translational correction on the fixed-size ROI, thereby utilizing peripapillary atrophy to locate the optic disc and improving the accuracy of the ROI's coverage of the actual optic disc area.

The invention discloses an ophthalmology intelligent auxiliary diagnosis method and system based on heterogeneous data collaboration, and the method comprises the steps: synchronously obtaining an ophthalmology multi-mode heterogeneous data set of a patient, including an OCT image, a fundus photograph and a visual field inspection report; the OCT image is subjected to retina layered structure segmentation, and an RNFL thickness distribution diagram is extracted; performing optic disc region positioning and blood vessel tree segmentation on the fundus photography to generate a CDR and a blood vessel curvature quantized value; mode deviation probability graph coding is carried out on the visual field inspection report, and a quadrant sensitivity missing matrix is output; an ophthalmic multimodal heterogeneous data set is associated through a patient unique identifier, and a RNFL thickness distribution map of OCT is mapped to an optic disc coordinate system of fundus photography by using feature-driven non-rigid registration. According to the invention, an ophthalmology multi-modal data cooperation barrier is broken through, an intelligent decision-making system with structure-function mutual verification is constructed, and the diagnosis reliability and clinical interpretability are significantly improved.

The invention discloses an optic disc and optic cup segmentation method based on semi-supervised learning, belongs to the field of image processing and artificial intelligence, and aims to solve the problems of instability of an optic disc and optic cup segmentation model caused by few labeled eye fundus images and poor precision caused by noise pollution. In the first stage, a double-branch improved DeepLab v3 + model is constructed to complete optic disc segmentation, after full supervision and anti-noise training are carried out by utilizing an annotated fundus image, the double-branch model is used for processing an unannotated fundus image, the anti-noise capability of the model is evaluated by counting the consistency of pseudo-label pixels before and after noise, and the model with strong anti-noise performance is used for supervising the training of the other model; in the second stage, a SegFormer model is constructed and trained to complete optic cup segmentation; and finally connecting the two models in series to realize two-stage segmentation of the optic disc and the optic cup. According to the method, unlabeled data is fully utilized for semi-supervised training, the noise immunity and segmentation precision of the model are improved, and technical support is provided for glaucoma screening work.

The invention provides a retinopathy auxiliary diagnosis system, and the system comprises an image enhancement module which carries out the defogging enhancement processing of an inputted fundus image set, and outputs an enhanced image set; the target detection module positions the optic disc and the macular of each fundus image in the enhanced image set, and outputs a positioning result; the orientation screening module judges and screens qualified images according to a positioning result and a predefined orientation rule; the extraction backbone of the double-branch classification network extracts high-level features and middle-level features; the first classification branch outputs a global classification result based on the high-level features; the second classification branch outputs a local classification result based on the middle-level features; and the diagnosis unit receives the global classification result and the local classification result to generate an auxiliary diagnosis result. According to the system, a discrete series model is replaced by an integrated architecture, redundant calculation is eliminated through connection of image enhancement and target detection, and the problem of high risk of missed diagnosis is solved through orientation evaluation, global and local branch parallel processing and collaborative optimization.

The invention provides an image processing method, electronic equipment and a storage medium, and the method comprises the steps: carrying out the gray processing of an eye fundus image, and obtaining a gray image, the retina in the eye fundus image comprises an optic disc; determining a relationship between a corresponding brightness value and a pixel point based on the grayscale image, and determining a target position of the optic disk; and determining a first classification result of the fundus image according to the target position, wherein the first classification result comprises a left eye image and a right eye image. The method can reduce the classification cost of the eye fundus image and improve the classification precision.

The invention discloses a calculation method for standardized statistics of the area of a retinal fibrous vascular membrane, and the method comprises the following steps: employing a same non-contact wide-angle imaging system and a same amplification factor, and taking an optic disc as a center to shoot a standard eye model reference image containing a preset model vitreous head and an eye fundus image in a patient eye operation; by taking a vitreous body cutting head as a reference, aligning the two images through Canny edge detection, minimum circumcircle positioning and Hough transform, and zooming until the contour of the vitreous body cutting head coincides; the method comprises the following steps: carrying out graying, de-noising, Otsu segmentation, connectivity screening and edge fitting on the basis of a white highlight feature of an FVM (Fiber Virtual Machine), so as to obtain an FVM contour; and overlapping the grids to count the number of the covered grids, and finally calculating the actual area of the FVM according to a formula. The invention provides an FVM area quantification calculation scheme which is uniform in reference standard, accurate in quantification and wide in application range, and provides a uniform quantification standard for comparing the FVM resection efficiency of different surgical instruments.

A method of determining pathologic myopia by using the geometric structure of a posterior sclera of a fundus includes obtaining geometric location data about a fovea, an optic disc, and a deepest point of the eye (DPE) in the posterior sclera of the fundus; obtaining an elevation difference TEPSfovea−DPE between the fovea and the DPE, an elevation difference TEPSdisc−DPE between the optic disc and the DPE, and an elevation difference TEPSfovea−disc between the fovea and the optic disc by using location information about the fovea, the optic disc, and the DPE in the posterior sclera; and determining pathologic myopia by using at least two elevation differences selected from among the elevation difference TEPSfovea−DPE between the fovea and the DPE, the elevation difference TEPSdisc−DPE between the optic disc and the DPE, and the elevation difference TEPSfovea−disc between the fovea and the optic disc.

The disclosure describes a neural network-based glaucoma recognition device and method, which includes an input unit, a preprocessing unit, a segmentation unit, a feature extraction unit, and a classification unit. The input unit is used to receive a first image. The preprocessing unit is used to preprocess the first image to obtain a first preprocessed image. The segmentation unit is used to input the first preprocessed image into an artificial neural network based on deep learning to generate an optic disc region image and an optic cup region image. The feature extraction unit obtains multiple glaucoma features based on the optic disc region image and the optic cup region image corresponding to the first preprocessed image. The classification unit is used to input feature information including glaucoma features corresponding to the first preprocessed image into a classifier based on machine learning for classification to obtain a glaucoma classification result. According to the present scheme, the accuracy of glaucoma recognition can be improved.

This invention relates to the fields of medical image processing and auxiliary diagnosis of ophthalmic diseases, specifically to a method and system for retinal vessel and optic disc segmentation based on multi-dimensional attention and edge enhancement mechanisms. It first acquires and preprocesses fundus images, then constructs an EIAIU_Net segmentation model integrating a multi-dimensional attention module and an edge enhancement Transformer module. The model is trained based on a paired shuffling consistency strategy, which reduces the dependence on absolute positional information. After inputting the preprocessed image into the model, multi-path features are generated through residual fusion using the SSA-IAI module, and then bidirectional interaction between edge and global features is achieved using the EETF module's dual-branch structure to generate interactive enhancement features. Finally, pixel-level segmentation results are obtained through the output layer. This invention solves the problems of low efficiency and severe loss of detail in traditional methods, and insufficient segmentation accuracy and limited generalization ability of existing deep learning models, enabling automatic segmentation of retinal vessels and optic discs.

The present application relates to the technical field of medical image segmentation, and particularly relates to a retinal fundus picture optic disc and cup adaptive segmentation method and system.The present application carries out multiple random forward propagation in the first U-Net to obtain a rough segmentation mean graph and a variance graph.Before calculating the second U-Net, the following adaptive judgment is made on the area of the rough segmentation optic disc: if the area is greater than or equal to a preset threshold, the fundus picture and the rough segmentation mean graph are input into the second U-Net to obtain the optic disc and cup segmentation result;if the area is less than the preset threshold, the weighted uncertainty graph needs to be further calculated, which is the weighted superposition of the rough segmentation optic disc and the high variance graph, and the weight considers both the distance of the rough segmentation optic disc and the high variance area and the shape of the optic disc and the high variance area.The weighted uncertainty graph, the fundus picture and the rough segmentation mean graph are input into the second U-Net to obtain the optic disc and cup segmentation result.Through adaptive judgment, the present application effectively improves the optic disc and cup segmentation precision.

The present application provides an eye state evaluation method and an electronic device. The method comprises: obtaining an optic disc image region from a first fundus image, and generating a plurality of optic cup disc ratio evaluation results based on the optic disc image region by a plurality of first models; obtaining a first evaluation result of the eye based on the optic cup disc ratio evaluation results; performing a plurality of data augmentation operations on the first fundus image to generate a plurality of second fundus images; generating a plurality of optic nerve fiber layer defect evaluation results based on the second fundus images by a plurality of second models; obtaining a second evaluation result of the eye based on the optic nerve fiber layer defect evaluation results; and obtaining an optic nerve evaluation result of the eye based on the first evaluation result and the second evaluation result. Thus, the present application can provide a reference for doctors when evaluating the eye state of patients, thereby helping doctors to give appropriate evaluation results for the eyes of patients.

The invention provides an eye fundus image-based atrophy arc classification method and device, equipment and a storage medium, and the method comprises the steps: obtaining an eye fundus image of a target object, and extracting a corresponding optic disc region and an atrophy arc region in the eye fundus image; determining target feature information based on the optic disk area and the atrophy arcing area, wherein the target feature information comprises pixel information data corresponding to the candidate images in the optic disk area and the atrophy arcing area; and when the target feature information satisfies a preset classification condition, determining a classification result of the arc-shrinking region. After the eye fundus image is preprocessed, the atrophic arc area is subjected to data statistics, the pixel information data after statistics is analyzed according to a set rule, and then atrophic arc classification and recognition are achieved. Therefore, the method can achieve the technical effects of achieving the multi-class division of the atrophic arc and improving the recognition precision.

The invention relates to the technical field of coherence tomography, in particular to a household optical coherence tomography system, which comprises a data acquisition module for acquiring an optical coherence tomography image and three-dimensional tomography data of an eyeball; the data division module is used for dividing an optical coherence tomography image into grids and determining an image quality index; the center positioning module is used for positioning the center point of the optic disc based on the low-brightness connected region; the coordinate establishing module is used for screening qualified grids based on image quality indexes and extracting a retina network feature point set to establish a coordinate system; the coordinate verification module is used for projecting the three-dimensional chromatography data to a two-dimensional plane to carry out coincidence comparison so as to verify the qualification of a coordinate system; the quality evaluation module is used for determining whether the scanning quality is qualified or not based on the coordinate system verification result and the image quality index; and the optimization adaptation module is used for dynamically adjusting a preset threshold value based on a quality evaluation result so as to optimize feature point extraction. The technical problem that cross-time data cannot be accurately compared due to inconsistent scanning poses is solved.

A method for application of light to one or more eyes of a user is disclosed. The method comprises identification of location of an optic disk on a retina in the one or more eyes and selectively applying the light onto the optic disc to stimulate the optic disk.

FIELD: ophthalmology.SUBSTANCE: used for objective differential diagnostics of the anatomical form of the optic nerve disc (OND) deepening. Optical coherence tomography is performed on the Optovue RTVue XR Avanti System using the 3D Disc program. Images of the optic disc are obtained in the horizontal plane, a straight line is drawn between the visible boundaries of the retinal pigment epithelium (RPE) and the position and shape of the bottom of the OND deepening are assessed. When the depression is at the level of the RPE and the angle of its bottom is less than or equal to 90° a triangular shape is defined. If the depression is located above the RPE level and the angle of its bottom is more than 90° a flat shape is defined. If the depression is below the RPE level and the bottom angle is less than or equal to 90° a wedge shape is defined. If the depression is below the RPE level, and its bottom forms a base and two angles, a trapezoidal shape is defined.EFFECT: improving the accuracy, objectivity and reproducibility of determining the individual anatomical shape of the OND excavation by using a stable anatomical landmark – the RPE and standardized geometric parameters, which eliminates subjective error in diagnosis.1 cl, 7 dwg, 1 tbl, 3 ex

The invention discloses a fundus image optic cup and optic disc segmentation method and device based on edge enhancement and visual features, and belongs to the technical field of image segmentation, and the method comprises the steps: employing an optic disc ROI coarse positioning model to carry out the positioning of an obtained to-be-segmented fundus image, and generating an optic disc ROI image; a Laplace feature map and a semantic vector are extracted from an optic disk ROI image by using an optic cup and optic disk segmentation model, multilayer feature coding is performed on the semantic vector to obtain a coding feature map, edge feature enhancement is performed on the coding feature map of each level according to the Laplace feature map and the decoding feature map of the previous level, and an edge enhancement feature map of each level is generated. And decoding each edge enhanced feature map, a fusion feature map of the coding feature map of the same level and the decoding feature map of the previous level to obtain a decoded feature map, and finally performing pixel classification on the decoded feature map to obtain an optic cup and optic disk segmentation result. According to the method, the segmentation precision of the optic cup and the optic disc is improved while the relatively high calculation efficiency is maintained.

The application relates to a retinal blood vessel parameter acquisition method and device and a retinal analysis equipment. The method comprises the following steps: acquiring a retinal blood vessel image to be analyzed; inputting the retinal blood vessel image into a pre-trained retinal blood vessel parameter acquisition model to obtain retinal blood vessel parameters in the retinal blood vessel image; the retinal blood vessel image is a retinal optic disc center image or a retinal non-optic disc center image; the retinal blood vessel parameter acquisition model comprises an encoder and multiple predictors; the retinal blood vessel parameter acquisition model is constructed by training a multi-task joint pre-training model; the multi-task joint pre-training model comprises an original encoder, a decoding module and multiple original predictors; and the original encoder learns deep retinal blood vessel knowledge based on the decoding module in the training process. The method can reduce the complexity of retinal blood vessel parameter acquisition, reduce processing errors, and improve the accuracy of the acquired retinal blood vessel parameters.

The present application relates to the technical field of medical image processing, in particular to a method and system for automatic detection of optic disc neovascularization based on bimodal optical scanning, comprising the following steps: step S1, scanning around the optic disc of a single eye and outputting N continuous bimodal optical scanning images containing the boundary of the optic disc, and establishing a data set containing the boundary label of the optic disc according to the N frequency domain optical coherence tomography images; step S2, training, verifying and testing the data set using a convolution network to obtain the detection result of the boundary of the optic disc; step S3, screening out the candidate area of optic disc neovascularization on each frequency domain optical coherence tomography image and optical coherence tomography angiography image; step S4, screening out the optic disc neovascularization area in each candidate area of optic disc neovascularization; and step S5, calculating the volume of the optic disc neovascularization of a single eye.

An information processing apparatus according to the present disclosure includes a transformation unit configured to transform a first region and a second region in a fundus image so that an angle formed between a first straight line and a second straight line approaches 180 degrees, the first and second regions being defined by the first straight line and the second straight line, the second region being larger than the first region, the first straight line passing through a first feature portion related to a macula in the fundus image and being located on a temporal side, the second straight line passing through the first feature portion and a second feature portion related to an optic disc in the fundus image and being located on a nasal side.

The invention relates to the technical field of image processing, and discloses a fundus image microvessel analysis method, system and device and a medium, and the method comprises the steps: obtaining an OCTA image, and carrying out the layering processing of the OCTA image; for any layered image, identifying an optic disc surrounding atrophy area in the layered image; determining an initial analysis area in the layered image, and extracting a corrected analysis area except the atrophy area around the optic disc in the initial analysis area; identifying an upper blood vessel bow sub-region and a lower blood vessel bow sub-region in the corrected analysis region; determining a first blood vessel density of the upper blood vessel bow sub-region based on the first blood flow signal of the upper blood vessel bow sub-region; determining a second blood vessel density of the lower blood vessel bow sub-region based on the second blood flow signal of the lower blood vessel bow sub-region; an asymmetry indicator is determined based on the first blood vessel density and the second blood vessel density. The method has the beneficial effect that more accurate and more specific quantitative evaluation of the fundus capillary state is realized.

The application discloses a kind of dense lesion semi-automatic labeling method for fundus image, method includes constructing and training dense lesion segmentation network, macula fovea positioning network and optic cup optic disc segmentation positioning network;Utilize network to process to obtain dense lesion prediction contour area, macular area and optic cup optic disc area respectively;Three labelers are assigned to fundus image, each labeler selects key area and other area from macular area and optic cup optic disc area and carries out labeling operation, to obtain first round labeling result;According to first round labeling result, the lesion labeling consistency index between every two labelers is calculated to determine two labelers to execute second round lesion labeling, and second round labeling result is obtained;Second round labeling result is audited to obtain final labeling result.Therefore, the problem of large difficulty in dense lesion labeling and large difference in labeling by different personnel is solved, and the labeling efficiency is improved, the labeling time is reduced, and the labeling cost is reduced.

This invention provides a retinal data processing method and apparatus. The method includes: acquiring OCT data including the macula and optic disc region of the fundus; processing the OCT data using a pre-constructed target model to obtain a classification result of the OCT data, the classification result including the probability distribution of the subject belonging to two categories: normal or abnormal cognitive function; processing the classification result based on gradient class activation mapping to generate a visual heatmap of the retinal region corresponding to the classification result, the visual heatmap highlighting the retinal anatomical region that contributes the most to the current classification result. This method can provide doctors with retinal feature data and classification results indicating abnormalities for auxiliary diagnosis, enabling doctors to accurately diagnose the patient's mental and cognitive function status based on this data and classification results.

The invention provides a multi-modal health data feature extraction method and system, and relates to the technical field of medical data processing, and the method comprises the steps: obtaining a multi-modal health data set which comprises time sequence physiological data, image data and text data; performing random noise processing on the time sequence physiological data to extract blood pressure fluctuation characteristics; based on the blood pressure fluctuation characteristics, performing structural noise processing on the image data to extract morphological characteristics of the fundus blood vessels; in the process of extracting the morphological features of the fundus blood vessels, dynamically positioning three feature anchor points on a fundus image corresponding to the image data; the anatomical positions of the three characteristic anchor points are respectively an optic disc edge upper quadrant reference point, a macular region bitamporal trunk blood vessel bifurcation core point and an arteriovenous cross indentation center point; and constructing a dynamic response area based on the three feature anchor points. The cardiovascular event risk assessment precision can be improved.