MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202541134203 A) filed by Dhaanish Ahmed College Of Engineering, Chennai, Tamil Nadu, on Dec. 31, 2025, for 'retinal fundus multi disease detection using deep neural networks.'
Inventor(s) include Dr. P. Paramasivan; Mrs. M. Shagar Banu; Dr. R. Sivakani; Dr. C. Satheesh; Mrs. G. Agalya; Mr. S. Tamilselvam; Ms. S. Nimmi Devi; Dr. K. Pradeep; Dr. P. V. Bhuvaneshwari; and Mr. J. Jayaprakash.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a system and method for the automated detection of multiple diseases from retinal fundus images using a deep neural network architecture. Current automated diagnostic tools are predominantly limited to the detection of a single pathology, such as diabetic retinopathy, which does not reflect the clinical reality where patients often present with co-existing conditions. This invention utilizes a convolutional neural network (CNN) backbone, such as ResNet or EfficientNet, for feature extraction, followed by a.multilabel classification head. "The system is trained on a large, annotated dataset of retinal fundus images labeled for a plurality of diseases, including but not limited to diabetic retinopathy, glaucoma, age-related macular degeneration, and pathological myopia. By employ.ing a sigmoid activation function and binary cross-entropy loss for each disease class, the model learns to identify the presence of one or more diseases simultaneously in a single inference pass. The invention provides a comprehensive screening tool that enhances diagnostic efficiency, assists ophthalmologists in triage, and facilitates early intervention for a spectrum of sight-threatening conditions, thereby addressing a critical unmet need in scalable teleophthalmology and public health screening programs."
Disclaimer: Curated by HT Syndication.
