112 results about "Diabetic retina" patented technology

The invention discloses an attention mechanism-based in-depth learning diabetic retinopathy classification method comprising the following steps: a series of eye ground images are chosen as original data samples which are then subjected to normalization preprocessing operation, the preprocessed original data samples are divided into a training set and a testing set after being cut, a main neutralnetwork is subjected to parameter initializing and fine tuning operation, images of the training set are input into the main neutral network and then are trained, and a characteristic graph is generated; parameters of the main neutral network are fixed, the images of the training set are adopted for training an attention network, pathology candidate zone degree graphs are output and normalized, anattention graph is obtained, an attention mechanism is obtained after the attention graph is multiplied by the characteristic graph, an obtained result of the attention mechanism is input into the main neutral network, the images of the training set are adopted for training operation, and finally a diabetic retinopathy grade classification model is obtained. Via the method disclosed in the invention, the attention mechanism is introduced, a diabetic retinopathy zone data set is used for training the same, and information characteristics of a retinopathy zone is enhanced while original networkcharacteristics are reserved.

The present invention relates to novel kinase inhibitors and modulator compounds useful for the treatment of various diseases. More particularly, the invention is concerned with such compounds, kinase / compound adducts, methods of treating diseases, and methods of synthesis of the compounds. Preferrably, the compounds are useful for the modulation of kinase activity of Raf kinases and disease polymorphs thereof. Compounds of the present invention find utility in the treatment of mammalian cancers and especially human cancers including but not limited to malignant melanoma, colorectal cancer, ovarian cancer, papillary thyroid carcinoma, non small cell lung cancer, and mesothelioma. Compounds of the present invention also find utility in the treatment of rheumatoid arthritis and retinopathies including diabetic retinal neuropathy and macular degeneration.

The invention discloses a deep learning-based diabetic retina image classification method and system in the technical field of artificial intelligence. The method comprises steps: a fundus image is acquired; the same fundus image is imported to a microvascular tumor-like lesion recognition model, a hemorrhagic lesion recognition model and an exudative lesion recognition model for recognition; andaccording to recognition results, lesion feature information is extracted, a trained SVM classifier is then adopted to classify the extracted lesion feature information, and a classification result isacquired, wherein the microvascular tumor-like lesion recognition model is obtained when a microvascular tumor-like lesion candidate area in the fundus image is extracted and is then inputted to a CNN model for training, and the hemorrhagic lesion recognition model and the exudative lesion recognition model are obtained when a hemorrhagic lesion area and an exudative lesion area in the fundus image are marked and are then inputted to an FCN model for training. The requirements on the description ability of the network model are reduced, the model is easy to train, a lesion focus area is positioned and delineated for different lesions, and clinical screening by a doctor is facilitated.

The present invention relates to novel kinase inhibitors and modulator compounds useful for the treatment of various diseases. More particularly, the invention is concerned with such compounds, kinase / compound adducts, methods of treating diseases, and methods of synthesis of the compounds. Preferrably, the compounds are useful for the modulation of kinase activity of Raf kinases and disease polymorphs thereof. Compounds of the present invention find utility in the treatment of mammalian cancers and especially human cancers including but not limited to malignant melanoma, colorectal cancer, ovarian cancer, papillary thyroid carcinoma, non small cell lung cancer, and mesothelioma. Compounds of the present invention also find utility in the treatment of rheumatoid arthritis and retinopathies including diabetic retinal neuropathy and macular degeneration.

The invention discloses a diabetic retina eye ground image pathology detection method comprising the following steps: preprocessing a medical eye ground image so as to form a standard eye ground image; dividing areas for the eye ground image so as to form m sub-images of different eye ground areas; using a multilayer area convolution nerve network model to extract an area depth feature vector of the eye ground sub-image; using the area depth feature vector as the LSTM nerve network input, predicting correlations of different areas, and forming an eye ground image global feature vector; finally, using a whole articulamentum and softmax to realize multi-classification detection of the eye ground image. The method is based on retina eye ground images and labels that can be crawled on the internet, uses the correlation between the eye ground image area depth features and the adjacent area, and realizes the diabetic retina eye ground image pathology automatic detection via the convolution nerve network and recursion nerve network algorithms, thus effectively improving the detection accuracy and timeliness.

The invention discloses a diagnostic assistant system for diabetic retinal complications based on convolution neural network, which includes: a training set and a test set preparation module, which are used to prepare the training set and the test set for type 2 diabetes mellitus complicated with retinopathy and non-type 2 diabetes mellitus complicated with retinopathy; a convolution neural network construction module is used to construct convolution neural network; a convolution neural network optimization module is used to optimize the constructed convolution neural network, a convolution neural network training module is to train the convolution neural network by using the training set, a classified output module, wherein the test set is input as a well-trained neural network, an outputvalue is type 2 diabetes mellitus complicated with retinopathy and non-type 2 diabetes mellitus complicated with retinopathy. The system provides the basis for the early diagnosis of diabetes mellitus complicated with retinopathy and optimizing the diagnosis process, in-depth study is combined with the electronic medical record information and a good result is achieved.

The invention discloses a diabetic retina feature grading device in an eye fundus image based on attention mechanism and feature fusion. The diabetic retina feature grading device comprises a featuredetection classification network module used for extracting first-grade diabetic retina features and second-grade diabetic retina features in the eye fundus image of an input sample, and outputting fine classification feature images extracted from the first-grade diabetic retina features and the second-grade diabetic retina features; an original image classification network module used for extracting third-grade diabetic retina features and fourth-grade diabetic retina features in the eye fundus image of the input sample, and outputting rough classification feature images extracted from the third-grade diabetic retina features and the fourth-grade diabetic retina features; an attention mechanism and feature fusion module for conducting feature fusion on the fine classification feature images output by the feature detection classification network module and the rough classification feature images output by the original image classification network module by adopting an attention mechanism, and outputting the prediction probability of the diabetic retina feature grade of the image of the input sample. The device ensures faster speed, and the classification evaluation index Kappa reaches 81.33%.

A non-surgical method for preventing or reducing the rate of the progression of non-proliferative diabetic retinopathy to the proliferative form of diabetic retinopathy comprising intravitreally administering to a patient suffering from non-proliferative diabetic retinopathy an effective amount of serine proteinase enzyme sufficient to create, without surgery, a posterior vitreal detachment to prevent or reduce the progression of proliferative diabetic retinopathy in said patient. Also disclosed is a non-surgical method of treating ocular conditions such as retinal ischemia, retinal inflammation, retinal edema tractional retinal detachment, tractional retinopathy, vitreous hemorrhage and tractional maculopathy by intravitreally administering to a patient suffering from one or more of these conditions with an effective amount of a serine proteinase enzyme to reduce or treat that particular ocular condition. Plasmin, microplasmin and miniplasmin are preferred serine proteinase enzymes and plasmin is the most preferred.

The invention discloses a method for performing eye ground focus recognition through eye ground color pictures. All parts in the eye ground color pictures are automatically positioned and measured, the disease pre-screening effect is achieved, pictures with lesion suspicion are automatically screened out, and bleeding, effusion and microaneurysm can be positioned and recognized rapidly and efficiently, so that diabetic retinopathy and other diseases can be subjected to auxiliary diagnosis, and workloads of doctors are relieved; the result does not depend on doctor's experience, the result is more objective, the doctor can be effectively assisted in disease diagnosis, and the purpose of remote consultation is achieved.

A fundus microaneurysm target detection model based on an R-CNN architecture realizes detection and identification of a fundus microaneurysm focus, and the method comprises the following steps: preprocessing a fundus image; carrying out blood vessel segmentation on the preprocessed image; performing three steps of local adaptive threshold segmentation, blood vessel removal and area screening on the preprocessed image to obtain a real microaneurysm candidate region; expanding the number of training samples by adopting data enhancement; using a transfer learning method, using a pre-trained VGG16 network for carrying out feature extraction on a sample, and adding a microaneurysm classifier behind the feature extraction network for joint training. According to the scheme, a new method is provided for diabetic retina image fundus microaneurysm target detection.

A non-surgical method for preventing or reducing the rate of the progression of non-proliferative diabetic retinopathy to the proliferative form of diabetic retinopathy comprising intravitreally administering to a patient suffering from non-proliferative diabetic retinopathy an effective amount of serine proteinase enzyme sufficient to create, without surgery, a posterior vitreal detachment to prevent or reduce the progression of proliferative diabetic retinopathy in said patient. Also disclosed is a non-surgical method of treating ocular conditions such as retinal ischemia, retinal inflammation, retinal edema tractional retinal detachment, tractional retinopathy, vitreous hemorrhage and tractional maculopathy by intravitreally administering to a patient suffering from one or more of these conditions with an effective amount of a serine proteinase enzyme to reduce or treat that particular ocular condition. Plasmin, microplasmin and miniplasmin are preferred serine proteinase enzymes and plasmin is the most preferred.

The invention provides a retinal fundus image segmentation method and device, which can realize automatic, efficient and accurate segmentation of retinal fundus image blood vessels and optic disks under the condition of only a small number of labeled samples. The method comprises the steps of acquiring a training set image and a corresponding annotation image, wherein the image is a retinal fundusimage; carrying out consistent random cutting and blocking on the obtained training set image and the corresponding annotation image; constructing a U-shaped full convolutional neural network; inputting the randomly clipped and blocked training set images and the corresponding annotation images into a constructed U-shaped full convolutional neural network, and training the U-shaped full convolutional neural network; and segmenting the retinal fundus image by using the trained U-shaped full convolutional neural network. The invention relates to the field of artificial intelligence and diabeticretina diagnosis.

The invention belongs to the technical field of medical image processing, and discloses a diabetic retinopathy classification method and device based on a graph network. The diabetic retinopathy classification method based on the graph network comprises the steps of acquiring a preset number of fundus color images and subjecting the fundus color images to normalization preprocessing to serve as normalization images; constructing a graph structure by using the normalized image, and carrying out feature extraction on the graph structure to obtain to-be-processed data; and constructing a convolutional neural network model, and carrying out convolutional neural network training on the to-be-processed data to obtain a diabetic retinopathy grade classification model. Graphic data are structured,and classification of fundus color images is realized through a graph structure analysis algorithm in combination with a convolutional neural network model and through automatic film reading of a computer.

Methods for the treatment or prevention of a number of ocular diseases or disorders are disclosed. In particular, methods are disclosed for the amelioration of macular degeneration, diabetic retinophaty and other retinopathies, as well as uveitis, presbyopia, dry eye, glaucoma, blepharitis and rosacea of the eye. The methods comprise administration of a compositions comprising an ophthalmologically acceptable carrier or diluent and a hydoxylamine compound in a therapeutically sufficient amount to prevent, retard the development or reduce the symptoms of one or more of the ophthalmic conditions.

The invention provides a diabetic retinopathy recognition method and device and electronic equipment, and relates to the technical field of image recognition. The method comprises the following steps:collecting a fundus image to be recognized; inputting the fundus image into a diabetic retinopathy recognition model, wherein the diabetic retinopathy recognition model is obtained by training basedon an instance segmentation model; determining a focus in the fundus image through the diabetic retinopathy recognition model; and labeling at least one of the type, the position and the shape of thefocus through the diabetic retinopathy recognition model. According to the method, the type, the position and the shape of the focus in the fundus image are directly recognized through the diabetic retinopathy recognition model, and accurate recognition of lesion staging can be achieved.

The present invention provides a serum / plasma miRNA marker related to type 2 diabetic retinopathy and use thereof. The serum / plasma miRNA marker related to the type 2 diabetic retinopathy is one or a combination of two of hsa-let-7a-5p, hsa-miR-novel-chr5_15976, hsa-miR-28-3p, has-miR-20a-5p, has-miR-151a-5p, has-miR-148a-3p and has-miR-223s-3p. The serum / plasma miRNA marker related to the type 2 diabetic retinopathy is stable and can be used to early assist to diagnose whether a diabetic patient is combined with DR, and the disease progression of the diabetic retinopathy patient can be dynamically monitored, and the serum / plasma miRNA marker can be used to prepare an early diagnosis product of type 2 diabetes and the diabetic retinopathy.

The invention relates to a composition containing 50 to 99 parts by weight of arctiin with the purity of more than 90 percent or 1 to 50 parts by weight of arctigenin and a preparation method thereof, and the functions of the composition are the treatment and the prevention of diabetic retinopathy. In the invention, by extracting the arctiin and the arctigenin, the pharmacological, toxicological and clinical trial results show that the composition of arctiin or arctigenin of the invention has the advantages of strong treatment effect and small toxicity and side effects in the treatment of the diabetic retinopathy.

An enzyme-linked detection kit for detecting VEGF. A kit body contains an enzyme-linked reaction plate coated by a VEGF acceptor and a monoclonal antibody, an enzyme conjugate labelled by HRP and configured by antibody and a protective agent, a freeze-drying powder of the VEGF protein as a positive contrast, a protein freeze-drying powder as a negative contrast, a sample diluent, a PBST concentrated lotion, a chromogenic substrate configured by 3,3',5,5'-tetramethyl benzidine, 2MH2SO4 as a stopping solution and a seal plate gummed paper. The kit can be used in diagnosis and prognosis of cancer, angiopathy, diabetes, retinopathy and rheumatoid arthritis, and has advantages of accuracy, specificity, sensitivity, stability and convenience, etc.

The invention discloses a retinal image segmentation algorithm based on a residual error U-NET network, which comprises the following steps: A, downloading a color fundus retina image, and carrying out sample expansion on the downloaded image; B, preprocessing the original image; C, obtaining an Improved residual U-NET network by adding a residual structure to the U-NET network; D, taking the processed retina image as input, and carrying out pre-training on the training sample to obtain Initial parameters of the residual U-NET network model; E, Segmenting test samples using a trained residualU-NET neural network model to obtain a final retinal vessel image segmentation map; the residual U-NET neural network model iss adopted to segment the diabetic retina image, the processing effect isgood, the method can be widely applied to the field of diabetic retina diagnosis, and powerful theoretical and technical support is provided for pathological diagnosis of the diabetic retina image.

The invention relates to the technical field of image processing, in particular to a diabetic retina image quality detection method based on an image analysis technology. The method comprises the following steps of: preprocessing the fundus image, performing morphological treatment, equalization treatment and filtering treatment on the fundus image during the pretreatment process, performing brightness detection, optic disc detection and definition detection after the pretreatment, and finally obtaining the fundus image to be diagnosed, and diagnosing diabetic retinopathy. The preprocessing operation in the method greatly improves the visibility of the retinal fundus image, It is more advantageous for doctors to diagnose and analyze the patients' condition, and the quality inspection operation can greatly reduce the occurrence of the unqualified fundus images taken at the census spots. The fundus images which pass the quality inspection can be used for the preliminary diagnosis of diabetic retinopathy.

The invention provides application of echinacoside or acteoside in preparation of angiogenesis inhibitor medicines. Tests prove that angiogenesis echinacoside and acteoside can be used for effectively inhibiting reproduction of vascular endothelial cells, can be used as angiogenesis inhibitors for treating tumors, diabetic retinopathy, rheumatoid arthritis, prostatic hyperplasia or psoriasis and other angiogenesis dependent diseases and have a wide market prospect.

The invention discloses a diabetic retina image automatic classification method. According to the method, first, denoising, normalization and other preprocessing are performed on images; second, underthe condition that sample data is insufficient, a migration learning strategy and a data enhancement strategy are adopted to extract depth features for classification; and finally the extracted features are input into a classifier to classify retina pathological images into five types. Through the method, the classification accurate rate can reach 93%, and the method has good robustness and generalization performance.

The invention discloses a diabetic retinopathy image labeling method based on deep learning. The method comprises the following steps: selecting a training sample and a test sample; wherein the samplepreprocessing comprises the steps of cutting, overturning and normalization processing of a sample image; constructing a deep full convolutional neural network as an image encoder, using a transfer learning method to initialize network parameters, and then sending the preprocessed sample image data into the network to obtain a feature vector; and constructing a decoder taking a deep recurrent neural network LSTM as a vector, sending the obtained feature vector into the LSTM structure for decoding, and obtaining the annotation information of the sample image. The annotation information is explanation of the focus point information in the sample image, so that a doctor and a patient can be helped to understand the image content more deeply, and the diagnosis efficiency and precision are improved. According to the method, the diabetic retinopathy image is automatically labeled by using the deep convolutional neural network and the deep recurrent neural network, so that the comprehensiveness of focus point information in the image is improved.

Provided are methods, pharmaceutical formulations and kits thereof for the treatment and / or prevention of conditions mediated by neovascularization, abnormal angiogenesis, vascular permeability, or combinations thereof, of posterior and / or anterior tissues and fluids of the eye, including conditions associated with proliferative retinopathies, for example, diabetic retinopathy, age-related maculopathy, retinopathy of prematurity, retinopathy associated with macular edema, or retinopathy associated with sickle cell disease, using the topical administration of mecamylamine or a pharmaceutically acceptable salt thereof to the eye. Methods of preparing the pharmaceutical formulations are also provided.

The invention discloses a deep learning based diabetic cornea image disease classification method. The method comprises following steps: step A, downloading a data set of diabetic cornea images from akaggle website; step B, subjecting obtained diabetic cornea image data set to following pretreatments: color balance adjustment, brightness adjustment, contrast adjustment, zooming, and cutting; stepC, on the basis of a VGG network model, establishing a new VGG-L network classification model; step D, training the established model by the preprocessed image data set; and step E, judging the classification accuracy of the trained model by using a test set of diabetic cornea images. The adopted classification method can divide the diabetic cornea images into five groups according to the diseaselevels and has the advantages of high classification accuracy, good robustness, and good extensiveness.

The invention provides composition and a method for preventing or treating CNV (choroidal neovascularization)-associated ocular diseases. The composition is a recombinant vector expression unit and arecombinant viral vector of a suitable AAV (adeno-associated virus) coat, wherein the recombinant vector expression unit contains a VEGF (vascular endothelial growth factor) antibody or a functional fragment gene of the VEGF antibody. The composition can prevent or treat the CNV-associated ocular diseases such as age-associated macular degeneration and diabetic retinopathy by intravitreal or subretinal injection.

The invention provides an ELISA detection kit used for detecting human vascular endothelial growth factors (VEGF). In the detection kit, there is a VEGF acceptor coated enzyme-linked reaction plate, a enzyme conjugate prepared from horseradish peroxidase (HRP) labeled antibodies and a protective agent, lyophilized powder of VEGF protein used as positive contrast, lyophilized powder of protein used as negative contrast, sample diluents, PBST concentrated lotion, a chromogenic substrate prepared from 3,3',5,5'-tetramethyl benzidine, 2MH2SO4 used as a stopping solution and shrouding glue paper. The kit can be used for diagnosis and prognosis of cancers, angiopathy, diabetic retinopathy and rheumatoid arthritis and has the advantages of accuracy, specificity, sensitivity, stability, convenience and the like.

The invention discloses a vascular endothelial growth factor (VEGF) receptor enzyme linked diagnosis kit. A VEGF receptor coated enzyme linked reaction plate, an enzyme conjugate prepared through a horse radish peroxidase (HRP)-marked monoclonal antibody and a protecting agent, VEGF protein freeze-dried powder serving as positive comparison, protein freeze-dried powder serving as negative comparison, sample diluting liquid, PBST concentrated washing liquid, a chromogenic substrate prepared through 3,3',5,5'-tetramethyl benzidine, 2MH2S04 serving as stop buffer and shrouding adhesive paper are arranged in a kit body. The kit can be used for diagnosing and prognosis of diseases related to VEGF receptors such as cancer, angiopathy, diabetes retina disease and rheumatoid arthritis, has the advantages of being accurate, special, flexible, stable, convenient and the like, and has wide application prospects.