262 results about "Retinal image" patented technology

The invention discloses a diabetes retina image classification method and system based on deep learning, and relates to the technical field of image classification, and the specific steps are as follows: collecting and preprocessing a retina image data set, and constructing a training data set; constructing an initial image classification model based on a deep neural network, and performing iterative training on the initial image classification model by using the training data set to obtain an image classification model; the initial image classification model takes a pre-trained OfficientNet network as a backbone network, and integrates a feature pyramid network structure, a lesion attention module and a classification module; and obtaining a to-be-classified image, preprocessing the to-be-classified image, inputting the preprocessed to-be-classified image into the image classification model, and outputting a classification result. According to the method, the dependence of the model on a specific data source is reduced by using a data enhancement strategy, the diagnostic performance and stability of the model on unseen retina images are improved, and the universality of clinical application is enhanced.

The invention discloses an OCT (Optical Coherence Tomography) retina image denoising method based on a high-frequency enhanced diffusion model, which is characterized in that a double-branch diffusion model network constructed based on frequency perception Fourier transform attention (FFTA) is used for separating different frequency domains, enhancing specific frequency domain features and fusing the specific frequency domain features into a spatial domain feature map to realize stronger frequency domain perception and processing capability; the invention relates to a time step T coding method for a module of frequency domain attention. The time step T of the diffusion model is used as a parameter to be coded into a frequency domain attention module to participate in self-attention matrix calculation, so that frequency domain feature processing is aligned with the iteration step number of the diffusion model, and different frequency domain information is pointedly processed at different time steps T; the frequency selective hopping mechanism uses pooling operation to obtain a high / low frequency characteristic pattern, so that the network has adaptive frequency domain retention capability for different local parts.

The invention discloses a retina thickness prediction method and system based on a multi-modal image, and the method and system achieve the effective estimation of the retina thickness under a low-cost condition through feature alignment and fusion modeling, and improve the basic screening and follow-up visit capability. According to the invention, through fusion of the multi-mode retina image data, the structure and function information of the optic nerve can be more comprehensively obtained, and the prediction accuracy of the thickness of the retina nerve fiber layer (RNFL) is improved. The OCT high-resolution hierarchical structure and the wide-view texture features of the eye fundus image are combined, so that anatomy and pathological states of optic nerves can be truly restored. The method can be used as an auxiliary method for early screening and early warning of optic neurodegenerative diseases such as glaucoma, and provides support for low-cost and high-efficiency primary screening and clinical auxiliary decision making.

The invention discloses a retina image unsupervised anomaly detection method for early screening of diabetes mellitus. The method comprises the following steps: carrying out registration and multi-scale attention-guided blood vessel segmentation on a longitudinal time sequence retina image of a patient; extracting a vascular skeleton and constructing a time sequence vascular topological graph, calculating geometric morphology and hemodynamic attributes of each vascular segment, identifying vascular morphology evolution characteristics by comparing topological graphs of adjacent time points, and calculating hemodynamic characteristics such as wall shear stress through simulation; the evolution and hemodynamic characteristics are jointly input into a time sequence encoder for unsupervised learning, and an early diabetes risk score is comprehensively generated by analyzing a reconstruction error, an abnormal score based on density estimation and a time sequence trajectory deviation degree of a potential space; the scheme of the invention does not depend on lesion labels, and can sensitively detect the tiny anomalies at the early stage of pathology from multi-dimensional dynamic changes, thereby providing an objective and quantitative new way for early screening and intervention of diabetes.

The invention provides a method and a system for predicting an Alport syndrome through a multi-modal retina image based on deep learning, and relates to the technical field of deep learning. According to the method, a retina image, an OCT image and clinical text data are fused, a dual-channel deep neural network of an image encoder and a text encoder is constructed, semantic alignment pre-training is carried out by adopting multi-modal contrast learning, and an adversarial sample enhancement mechanism is introduced to improve model robustness; unified standardized training of different device images is achieved through the style migration module, the occurrence probability and the renal function progress risk level are finally output, and high-reliability prediction under the cross-modal and cross-device condition is achieved.

A monocular and / or a binocular system may be used to generate one or more images, or videos, of a subject's retina by scanning in one or two directions in one or two dimensions to, for example, measure and / or report fixation, smooth pursuit, and / or saccadic responses of the subject's eye. The scanning and / or image generation process may be optimized to correct for distortions in the subject's eye and / or improve SNR among one or a plurality of retinal images. In some cases, the retinal images may be used to train a retinal feature detection model and / or algorithm that may be used to make predictions and / or inferences regarding a visual pattern showing features of subsequently received retinal images. These models and / or predicted patterns present within the models may be used by the retinal feature detection model and / or algorithm to monitor features of the retina and, in some instances, track voluntary and / or involuntary eye motion.

A method and system for the use of multi-spectral retinal images to achieve an effective, efficient, and AI enabled automated retinal disease biomarker detection using biomarker identification, segmentation, and quantification. A plurality of digital multi-spectral images of a retina of a patient at a plurality of illumination wavelengths can be done using a multi-spectral ophthalmoscope. The images can then be registered, processed, and assessed to automatically quantifying one or more biomarker based on the location and size of the biomarker in the plurality of processed multi-spectral images.

The invention discloses a medical image analysis method and system based on a visual language model, and belongs to the technical field of medical image intelligent diagnosis, and the system comprises an image preprocessing unit which carries out the down-sampling of an original retina OCT image to 256 * 256 and carries out the normalization of the original retina OCT image; the feature encoding unit comprises an image encoder based on RET Found in combination with LoRA optimization and a text encoder based on BioClinicalBERT; the class balance comparison learning unit is used for adjusting loss through class balance coefficients so as to relieve the class imbalance problem; the uncertainty estimation unit is used for calculating confidence quality and uncertainty scores based on Dirichlet distribution, and determining a threshold value in combination with an improved Youden index; and the model training unit adopts a total loss function of class balance loss and uncertainty loss, outputs a diagnosis result and an uncertainty score through transfer learning, and further comprises an image input module, a result display module and a data storage module. Rare disease classification performance and reliability are improved, training efficiency is improved through LoRA optimization, and an accurate and reliable scheme is provided for detection of the rare retina diseases.

The invention relates to the technical field of retina image quality evaluation, and particularly discloses a retina image quality evaluation method based on double-path frequency domain cross attention fusion, comprising the following steps: step S1, acquiring an RGB image; s2, preprocessing the quality of the BGR image through a contrast limit adaptive histogram equalization algorithm to obtain a CLAHE image; s3, inputting the RGB image and the CLAHE image into a dual-path frequency domain DenseNet121 network, and extracting features of the RGB image and the CLAHE image through a frequency domain attention mechanism algorithm; s4, refining the extracted features through a double cross attention algorithm, and obtaining integration of the BGR image and the CLAHE image; and S5, obtaining a quality evaluation result through a linear classifier. According to the method, important retina image structure details are reserved, and the adaptability of the model to different illumination conditions is also improved.

The invention discloses a prediabetic prediction method based on tongue image-retina image bimodal feature fusion. The method comprises the steps of constructing a tongue image and retina image pair data set and performing preprocessing; constructing a pre-diabetes prediction model, wherein the pre-diabetes prediction model comprises two multi-scale Mamba modules with the same structure, a bimodal feature fusion module and a classifier; the multi-scale Mama module extracts hierarchical multi-scale semantic features of the tongue image and the retina image of the same patient, the dual-mode feature fusion module is used for splicing and fusion, and the fused features are input into the classifier to output a prediction result of the patient in the early stage of diabetes; training the model through the training set, and monitoring convergence by using the test set to obtain a trained model; and inputting the verification set into the trained model to obtain a pre-diabetes prediction result. The problems that in the prior art, the single medical image feature prediction rate is not high, meanwhile, the convolutional neural network is difficult to capture the long-distance dependency relationship, and the calculation cost based on Transform is high are solved.

The present invention provides a method for automatic segmentation of fundus blood vessels based on low-cost noise data, including: S1: screening the data set, obtaining retinal images and pixel-level blood vessel labels through publicly available data sets; S2: constructing a convolutional neural network to generate quantifiable noise data; S3: segmenting the data set to construct a training set and a test set, and at the same time retaining one clean image data in the training set and applying corresponding noise to other images; S4: setting a loss function and training parameters; S5: alternately inputting the clean image data and the noise data into the network, and updating the network parameters by using a reweighting function; S6: obtaining a retinal image and inputting it into the trained network model to output a segmentation result. The present invention realizes that only a small amount of clean data can correct the bias brought by incorrect noise to the deep model, and improves the accuracy of automatic segmentation of fundus blood vessels when facing low-cost noise data.

The invention discloses a registration method based on a three-dimensional retina OCT (Optical Coherence Tomography) image, which relates to the technical field of OCT image registration, and comprises the following steps of: in the registration process of the OCT image, firstly, carrying out preliminary registration by taking anatomical feature points of the retina as key references of basic alignment, and eliminating global mismatching errors; after the preliminary registration is completed, the OCT image is divided into a plurality of sub-regions in an equal area, and each sub-region is used as an independent analysis unit, thereby facilitating the subsequent precise analysis of the local optical characteristics of each analysis unit. According to the method, global errors are eliminated through initial registration of retina anatomical feature points, image division and abnormal signal extraction are combined, healthy and scar tissue areas are intelligently recognized through a machine learning model, weights are dynamically adjusted to preferentially depend on the healthy areas, interference of scars on registration is reduced, registration reliability is improved, clinical misjudgment is reduced, and the accuracy of registration is improved. And technical support is provided for accurate diagnosis and treatment of retinopathy.

The invention discloses an unsupervised OCT retina image denoising method based on a diffusion model. The unsupervised OCT retina image denoising method comprises the following steps: 1) preprocessing an original OCT retina image; 2) performing wavelet transform on each preprocessed OCT retina image to decompose a low-frequency domain and a high-frequency domain; 3) for the high-frequency domain component obtained through decomposition, extracting high-frequency multi-scale features through processing of a backbone network and a multi-layer convolutional network; 4) constructing a diffusion model architecture, and gradually adding noise to the original OCT image in a forward process by using U-Net as a skeleton network of a diffusion model so as to degrade the original OCT image into a pure noise image; and 5) in the U-Net noise prediction process, fusing the high-frequency multi-scale features into the diffusion model to guide the removal of the noise, and finally generating a denoised OCT image. The method gets rid of dependence on a large number of true value labels which are difficult to obtain, and the OCT image quality is improved.

The utility model belongs to the technical field of medical instruments, and particularly relates to an artificial lens for people with color vision disorder. The surface of the intraocular lens is a spherical surface or at least one surface is an aspheric surface or at least one surface is a discontinuous surface, the intraocular lens is colored and at least uses one coloring dye, and the coloring range of the intraocular lens at least comprises part of an optical area. According to the intraocular lens, at least one inhibition band exists in the wavelength range of 380 nm to 780 nm of the spectrum transmittance of the intraocular lens, and the minimum value of the spectrum transmittance in the inhibition band is lower than the nearest peak value of the spectrum transmittance in the wavelength range of 380 nm to 780 nm, so that the situation that the surface roughness is too high due to film coating is avoided, cell deposition on the surface of a film layer is avoided, the color vision correction safety is improved, and the color vision correction efficiency is improved. The correction effect of color vision correction is guaranteed, the problem that the surface reflectivity is high due to the fact that the surface of the artificial lens is coated with a film is effectively solved, optical interference is prevented, the retina is prevented from receiving stray light, and the signal-to-noise ratio of a retina image is prevented from being reduced.

The invention discloses a diabetic nephropathy patient retinopathy image classification method based on artificial intelligence, and relates to the technical field of medical images, and the method comprises the steps: collecting a retina image, carrying out the denoising and contrast adjustment, and generating a standardized image; carrying out feature constraint by utilizing a generative adversarial network guided by medical priori knowledge in combination with microaneurysm morphology and bleeding area texture features, generating a retina image with enhanced pathological features, and constructing an amplification training data set; training a deep convolutional neural network based on the data set, identifying microaneurysm and bleeding lesion by using a multi-scale feature extraction layer, and outputting a preliminary classification result; and a reinforcement learning environment is constructed in combination with clinician feedback, and a classification decision threshold is dynamically adjusted to optimize lesion grading parameters. According to the method, cross-modal correlation analysis is adopted, retinopathy features and biochemical time sequence data are fused, and the accurate classification capacity of diabetic retinopathy images is improved.

A computer-implemented method, system, and computer-readable medium, for determining a level of hypertension of a person. Image data defining a retinal image of a retina of the person that has been captured by a retinal imaging system is acquired. Processing the image data is performed to identify a plurality of vessel segments present in the retinal image. Determining is performed of respective widths of vessel segments of at least a subset of the plurality of vessel segments present in the retinal image. Calculating, as a vascular summary metric, at least one average value or median value of the determined widths of the vessel segments present in the retinal image, is performed to determine a level of hypertension by which the person has been affected.

A patient screening system for providing recommendations for screening of potential diseases or disease risk(s) of a patient based on their health records and retinal images, is described herein. The patient screening system may include an optical imaging device operable at a doctor's office, and associated methods configured to generate the recommendation. The patient screening system may implement various AI / ML models trained on a training dataset of anonymized patient data. The patient screening system may be based on discovering correlations between features of the retinal images and the health records in the training dataset, and corresponding disease diagnoses included in the health records. The patient screening system may also implement classifiers for various diseases based on data in the training dataset. Any patient screening based on the recommendation may be followed up, and results of such screening used to improve performance of the patient screening system.

An apparatus for obtaining an image of a retina is described herein. The apparatus includes an optical relay that defines an optical path and is configured to relay an image of the iris along the optical path to a pupil, a shutter is disposed at the pupil and configured to define at least a first shutter aperture for control of light transmission through the pupil position, a tube lens disposed to direct light from the shutter aperture to an image sensor, and a prismatic input port disposed between the shutter and the tube lens and configured to combine, onto the optical path, light from the relay with light conveyed along a second light path that is orthogonal to the optical path.

The invention relates to the technical field of premature infant disease prediction, in particular to a premature infant retinopathy onset risk prediction method and system, and the method comprises the following steps: S1, clinical data collection: collecting the clinical data of a premature infant; s2, retina image data acquisition: acquiring retina image data of a premature infant, and acquiring microstructure and blood flow state information of retina blood vessels; s3, data preprocessing: preprocessing the acquired retina image data and clinical data; s4, correlation analysis of the retina image and clinical data: revealing potential correlation between the retina image and the health condition of the premature infant, and predicting the occurrence probability of retinopathy; s5, risk assessment and intervention suggestion: dynamically assessing the retinopathy risk of the premature infant, and providing personalized intervention suggestions; according to the method, high-value features in multi-source data are effectively captured, and the prediction accuracy of retinopathy is improved.

The invention discloses a retina OCT (Optical Coherence Tomography) image denoising method based on zero sample learning. The method comprises the following steps: generating a noise independent image pair for a single noisy image by adopting a CDIS (Coherent Discrete Identifier) The method comprises the following steps of: carrying out de-noising by using an MLFSnet network (AF-MSDSConv, Aap-LSM, SA, a reconstruction module); using RMSE symmetry and consistency joint loss zero sample training; in the reasoning stage, an original image is directly input, and a same-resolution de-noising result is output. The speckle noise can be significantly suppressed and the layered structure of the retina can be retained without noise-free true values or pairwise data, so that the retina can be used while being shot.

A method and system for the use of multi-spectral retinal images to achieve an effective, efficient, and AI enabled automated retinal disease biomarker detection using biomarker identification, segmentation, and quantification. A plurality of digital multi-spectral images of a retina of a patient at a plurality of illumination wavelengths can be done using a multi-spectral ophthalmoscope. The images can then be registered, processed, and assessed to automatically quantifying one or more biomarker based on the location and size of the biomarker in the plurality of processed multi-spectral images.

The invention relates to the technical field of medical health, and discloses a health assessment system and method based on multi-dimensional retinal aortic aneurysm monitoring data, and the method comprises the steps: collecting a retinal image of a patient with retinal aortic aneurysm, and extracting the aortic aneurysm features of the patient with retinal aortic aneurysm, setting an eye dynamic monitoring network of the patient with the greater aneurysm of the retina; performing time synchronization processing on the iconography image, the clinical examination data, the biomarker data and the real-time eye data to obtain multi-modal synchronization data; based on the multi-modal synchronous data, determining a risk evaluation index of the patient with the greater retina aneurysm, and constructing a personalized risk analysis model of the patient with the greater retina aneurysm; creating a risk scoring mechanism for the patient with the greater retinal aneurysm, and setting a health feedback tool for the patient with the greater retinal aneurysm. According to the invention, accurate prediction of the retina great aneurysm can be realized.

The invention discloses a retinal vessel segmentation and lesion detection method based on incremental learning. The method comprises the specific steps that firstly, an original image of a data set STARE is acquired, and preprocessing such as segmentation and data enhancement is carried out on an original retina image; then, a VGAT-Net-IL network model is constructed, the network takes a coding-decoding symmetric structure as a trunk, a visual cortex mechanism is simulated through an adaptive receptive field module to dynamically adjust a receptive field, and local details and global features of the retinal vessels are cooperatively extracted; meanwhile, a dynamic bimodal attention module is innovatively integrated, variable convolution is introduced into the dynamic bimodal attention module to adaptively adjust a sampling position, a blood vessel region is precisely focused in combination with a space and channel attention mechanism, and after the dynamic bimodal attention module, a Bayesian semantic association module is introduced to generate features containing semantic association; in order to solve the problem that old knowledge is easy to forget when a model learns new lesion features, an incremental learning technology training model is introduced. According to the method, the retinal vessel segmentation precision and the lesion detection capability are improved, and a reliable image analysis basis is provided for retinal disease diagnosis.

The invention relates to the technical field of image processing, in particular to a full-eye image automatic splicing method and system based on sweep-frequency OCT, and the method comprises the steps: collecting anterior segment images and retina images at different visual angles in combination with manual guidance; pre-processing the anterior segment images of different visual angles to obtain anterior chamber angle information, performing rigid registration on the anterior segment images based on the anterior chamber angle information, and fusing the registered anterior segment images to obtain an anterior segment OCT spliced image; performing transverse and longitudinal registration on the retina images of different visual angles by using the synchronously acquired laser eye fundus images, and performing fusion and curvature correction on the registered retina images to obtain a retina OCT spliced image; and splicing the anterior segment OCT spliced image and the retina OCT spliced image to obtain a full-eye image. According to the method and the device, the anterior segment image and the retina image can be seamlessly spliced while high-resolution detail presentation is ensured, and a more complete full-eye image with a clearer structure is obtained.

The invention relates to a retina image processing method and device and a computer readable storage medium, and relates to the technical field of image processing. The retina image comprises a fundus photo and an optical coherence tomography angiography (OCTA) image, and the processing method of the retina image comprises the following steps: determining candidate feature points in the fundus photo and the OCTA image; selecting marker feature points in the fundus photo and the OCTA image from the candidate feature points based on eye anatomy information; and on the basis of the marker feature points in the fundus photo and the OCTA image, aligning the vascular structures in the fundus photo and the OCTA image.

The present application discloses a method, apparatus, device, and storage medium for lesion grading, relating to the field of computer vision technology. The method includes: obtaining a retinal image to be processed; inputting the retinal image to be processed into a pre-trained diabetic retinopathy grading model to obtain a diabetic retinopathy grading result, where the diabetic retinopathy grading model is trained based on a multi-branch network architecture. The present application can improve the credibility of the diabetic retinopathy grading model.

Embodiments disclose systems and methods that aid in screening, diagnosis and / or monitoring of medical conditions. The systems and methods may allow, for example, for automated identification and localization of lesions and other anatomical structures from medical data obtained from medical imaging devices, computation of image-based biomarkers including quantification of dynamics of lesions, and / or integration with telemedicine services, programs, or software.

The embodiment of the invention provides a method for acquiring maculopathy edema features in a retina image and electronic equipment, and relates to the technical field of image recognition. The method for acquiring the maculopathy edema features in the retina images comprises the following steps: acquiring a current retina image to be recognized in a plurality of retina images; determining an edema brightness threshold value of the current retina image based on the brightness value of the pixel in the vitreous body region of the current retina image; based on the brightness value of each pixel in the current retina image and an edema brightness threshold value of the current retina image, an edema area in the current retina image is determined, and the brightness value of the pixel in the edema area is smaller than the edema brightness threshold value. According to the invention, feature extraction can be carried out on the macular oedema region in the image based on the brightness value of the pixel in the retina image.

The invention relates to the technical field of visual function detection, in particular to a visual function detection method and system based on image analysis, and the method comprises the following steps: collecting a multi-wavelength reflection image of fundus, adjusting a light source to set wavelength parameters, activating camera equipment to receive an image, and carrying out the denoising and contrast adjustment of the collected image. A multi-wavelength retinal image dataset is generated. According to the method, the definition and the contrast ratio of the image are greatly improved by collecting the multi-wavelength image and carrying out detailed denoising processing, higher precision is brought to damage identification, misdiagnosis opportunities are reduced, the retinal damage is mapped by calculating the light intensity gradient, the damage range is accurately captured, positioning of the damage area is refined, and the accuracy of damage identification is improved. Through high-speed capture and data analysis of pupil dynamic response, deep insight of an eye movement mode is provided, visual function evaluation is more visual and comprehensive, and comprehensiveness and accuracy of evaluation are enhanced through cross validation of visual field defect and pupil dynamic data.

Disclosed is an electronic device for screening autism spectrum disorder (ASD) and ASD symptom severity based on a retina image including an input unit that receives the retina image, a classification model that classifies whether there is the ASD, and the ASD symptom severity based on the retina image by using a deep learning algorithm, and at least one processor that controls the input unit and the classification model. The at least one processor is configured to preprocess the received retina image, to train the classification model such that the classification model classifies the ASD and typical development (TD) by using the preprocessed retina image, and classifies the ASD symptom severity, and to allow the trained classification model to screen whether there is the ASD and the ASD symptom severity depending on the input retina image.