12 results about "Macular edema" patented technology

According to the maculopathy diagnosis device and method based on GCN and Mama cooperation and the medium, feature interaction processing is carried out by designing a GMMN module (a graph mapping Mama network), each pixel is regarded as a feature node, and through combination of graph convolution and Mama coding, the advantages of the two methods are brought into full play, and the respective limitations of the two methods are overcome at the same time. Furthermore, a mapping module is developed, and effective cross-branch feature fusion is realized by using a geometrical relationship between feature nodes. A large number of experimental results prove that the network has excellent performance when the CFP modal image is used for automatic diagnosis of macular edema, and the effectiveness and clinical application potential of the method are verified. According to experimental verification on two public data sets of IDRID and Messidor and one private data set, 91.26%, 94.58% and 98.43% of diagnosis accuracy are achieved respectively, it is indicated that the method can achieve a good diagnosis effect on different data sets, and the huge potential of the method in clinical application is highlighted.

The invention relates to a diabetic macular edema treatment effect prediction system, method and equipment, and belongs to the technical field of biomedicine. Comprising the steps of obtaining and preprocessing clinical data of a patient before treatment to obtain effective data; performing feature screening on the data to obtain feature data; constructing a prediction model, and training the prediction model by using the feature data to obtain an optimal vision recovery prediction model and an optimal edema regression prediction model; according to the two types of prediction models, a combined prediction model is constructed by adopting logic weighted fusion; inputting clinical data of a patient to be treated into the two types of prediction models to obtain a prediction result; and according to a prediction result, carrying out interpretability analysis on the optimal prediction model and the combined prediction model to obtain key characteristic variables, and further obtaining the probability of vision recovery and edema regression of the to-be-treated patient after treatment. According to the method, comprehensive and multi-dimensional sources of prediction variables are ensured, and the limitation of only depending on image data or subjective evaluation is effectively overcome, so that the prediction precision is improved.

The present invention relates to methods, devices, and compositions for treating macular edema associated with non-infectious uveitis. For example, the methods include treatment of certain populations of subjects having macular edema associated with non-infectious uveitis by administering to the subjects a triamcinolone composition via non-surgical administration to the suprachoroidal space (SCS) of the eye.

The invention provides a traditional Chinese medicine composition used in the perioperative period of fundus surgery and a preparation method and application thereof, and belongs to the technical field of traditional Chinese medicine. The traditional Chinese medicine composition for the perioperative period of the fundus surgery is prepared from the following components in parts by weight: 9 to 15 parts of radix astragali seu hedysari, 6 to 12 parts of radix angelicae sinensis, 6 to 12 parts of radix rehmanniae, 6 to 12 parts of herba ecliptae, 3 to 9 parts of radix paeoniae rubra, 3 to 9 parts of rhizoma atractylodis macrocephalae, 6 to 12 parts of semen plantaginis, 1 to 6 parts of radix saposhnikoviae and 1 to 6 parts of ramulus cinnamomi. By adopting the traditional Chinese medicine composition, the postoperative vision of a patient subjected to fundus surgery can be effectively improved, the retina sensitivity is improved, and the visual function of a macular region is improved; absorption of fundus hemorrhage is effectively promoted, the central fovea thickness of a macular region is reduced, and absorption of postoperative macular edema is promoted; the traditional Chinese medicine composition can improve eye local and whole body traditional Chinese medicine syndromes, and is safe in clinical medication.

The application discloses a kind of based on MEA-Net network's modeling method of multi-expert system, the application includes data pre-processing, cutting and proportionally distributing production image data and label data set;In order to improve fundus retinal lesion classification accuracy, the application designs Multi-Expert attention Net network model.Input module is preliminary extracted to data, replaceable expert network module is responsible for the depth analysis of feature, and voting module is strengthened by separating channel adjacent module on channel space to feature, and output weight realizes expert voting, finally, classification result is obtained by output module.The application can use the picture information of optical coherence tomography, can analyze and extract the characteristics of the four types of macular edema degeneration performances of OCT image PED, SRF, IRF, HRF, and lay the foundation for subsequent retinal disease classification and analysis to improve efficiency.

The invention discloses a macular oedema lesion screening method and system based on prototype dynamic pseudo tags, belongs to the technical field of macular oedema lesion screening, and aims to solve the technical problem of low macular oedema lesion screening accuracy in the prior art. The method comprises the following steps: acquiring OCT image sample data, macular oedema negative and positive labels, full labeling labels and point labeling labels; a macular oedema lesion segmentation model is constructed and trained, the macular oedema lesion segmentation model comprises a UNet encoder, a strong branch UNet decoder, a weak branch UNet decoder and an attention mechanism module, feature vectors output by the UNet encoder serve as input of the strong branch UNet decoder and the weak branch UNet decoder, and feature vectors output by the strong branch UNet decoder and the weak branch UNet decoder serve as input of the attention mechanism module. The outputs of the UNet encoder and the weak branch UNet decoder are used as the input of the attention mechanism module; and obtaining an OCT image to be detected, inputting the OCT image to the model, and obtaining a macular edema lesion screening result after a feature map E output by the UNet encoder and a segmentation prediction map S output by the weak branch UNet decoder pass through an attention mechanism module.

The invention provides a fundus macular oedema image processing method based on improved YOLOv11 and DeepSeek, and relates to the technical field of ophthalmic disease screening, and the method specifically comprises the steps: employing an improved YOLOv11 network structure, adding a lightweight dynamic convolution module LDConv module and a convolution block attention module CBAM, dynamically adjusting the shape and size of a convolution kernel, and carrying out the detection of the fundus macular oedema image. Multi-scale lesion characteristics such as macular edema and exudates are accurately captured; an attention map is generated through a channel and a space attention mechanism, key lesion areas of macular edema are preferentially concerned, interference of background noise is inhibited, and therefore accuracy and robustness of lesion recognition are further improved; a DeepSeek large language model is introduced, and on the basis of a detection result, personalized diagnosis and treatment suggestions conforming to clinical guidelines are generated in combination with clinical information (such as age, pathogenesis and treatment history) of patients; the system provides a structured treatment scheme and a follow-up visit plan and assists doctors in making more scientific and personalized decisions.

This invention relates to the application of an AAV carrying anti-VEGF recombinant protein in the prevention or treatment of proliferative diabetic retinopathy. After loading Fc-engineered VEGF antibody into an AAV vector, it can be used in drugs for the treatment of proliferative diabetic retinopathy. After injection, it can significantly improve the visual function of patients and reduce macular edema after a single dose. The anti-VEGF recombinant protein can be expressed for a long time, and can maintain the drug effect over a long period of time.

An ophthalmic formulation for treating macular edema, optic neuritis, and non-infectious endophthalmitis, comprising an active ingredient for treating an eye disease and a carrier or auxiliary material for the ophthalmic formulation, wherein the active ingredient for treating the eye disease is a glucocorticoid and / or nonsteroidal drug, and the carrier or auxiliary material for the ophthalmic formulation contains a surfactant, an ionic polymer, and a solvent, or the carrier or auxiliary material for the ophthalmic formulation contains low-degree-of-polymerization povidone, medium-degree-of-polymerization povidone, and a solvent. [Solution] This ophthalmic formulation, administered by eye drops, carries (encapsulates) glucocorticoid and / or nonsteroidal drugs, passes through the anterior segment of the eye, and is transported to the posterior segment to treat macular edema, optic neuritis, and non-infectious endophthalmitis. It has excellent clinical value and very positive social significance.

The present invention provides a method for treating an eye disease such as age-related macular degeneration (AMD), diabetic retinopathy (DR), or macular edema (ME), comprising administering a composition comprising a therapeutically effective amount of beauvericin to an individual in need thereof.

The embodiment of the present application provides a maculopathy edema feature acquisition method in a retinal image and an electronic device, and relates to the technical field of image recognition. The maculopathy edema feature acquisition method in a retinal image comprises the following steps: acquiring a current retinal image to be recognized in a plurality of retinal images; determining an edema brightness threshold of the current retinal image based on the brightness value of the pixels in the vitreous body region of the current retinal image; and determining an edema region in the current retinal image based on the brightness value of each pixel in the current retinal image and the edema brightness threshold of the current retinal image, wherein the brightness value of the pixels in the edema region is less than the edema brightness threshold. The present application can extract the macular edema region in the image based on the brightness value of the pixels in the retinal image.