111 results about "Diabetic retina" patented technology

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 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 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.

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.

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 discloses an alpha-cyano-4-hydroxy cinnamic acid derivative with aldose reductase inhibition activity and a preparation method and application thereof. The structure of the compound is as shown in formula I. The preparation method comprises the following steps: firstly reacting alpha-cyano-4-hydroxy cinnamic acid with a diamine compound protected by N-tert-butyloxycarbonyl (Boc) to obtain N-Boc-protected alpha-cyanocinnamic carbamide. After removal of a protective group, namely Boc from the compound, the alpha-cyano-4-hydroxy cinnamic acid derivative is obtained by reaction with N-acyl alpha-amino acid (natural or unnatural). The compound disclosed by the invention has inhibition activity against aldose reductase, and can be applied to preparation of medicaments for treating diabetic complications, such as diabetic retinopathy, diabetic senile dementia, disorders of nerve endings and other diseases.

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.

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 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.