MUMBAI, India, Nov. 2 -- Intellectual Property India has published a patent application (202641121856 A) filed by Dr. R. Praveena; Dr. S. Elango; Dr. K. Sakthimurugan; A. Gowtham; M Hariharan; and Dr. T. R. Ganesh Babu on October 12, 2026, for Artificial Intelligence-Based Correlation And Quantification Of Macular Edema Using Fundus Photograp.
Inventors include Dr. R. Praveena; Dr. S. Elango; Dr. K. Sakthimurugan; A. Gowtham; M Hariharan; and Dr. T. R. Ganesh Babu.
The application for the patent was published on October 30, 2026, under issue no. 44/2026.
Abstract: The present invention relates to an Artificial Intelligence (AI)-based multimodal retinal image analysis system and method for automated detection of macular edema using fundus and Optical Coherence Tomography (OCT) images. The invention utilizes fundus and OCT images acquired from the same eye to obtain complementary information regarding retinal surface abnormalities and retinal structural changes. The acquired images are subjected to modality-specific preprocessing and segmentation to enhance image quality and isolate the clinically relevant retinal and macular regions. Subsequently, Convolutional Neural Network (CNN)-based feature extraction is performed independently on the processed fundus and OCT images to obtain discriminative morphological, vascular, and structural features. An optimization-based feature selection technique is then employed to eliminate redundant features and identify the most significant features from both modalities. The selected features are correlated and fused to establish the relationship between fundusbased pathological manifestations and OCT-based retinal structural abnormalities. The resulting multimodal correlated feature representation is provided to an AI-based classification module for categorizing the retinal condition as normal or abnormal and identifying the presence of macular edema. The proposed invention provides an integrated, automated, and non-invasive computer-aided approach for multimodal retinal assessment, thereby improving the utilization of complementary information from fundus and OCT imaging for accurate macular edema screening and classification.
Disclaimer: Curated by HT Syndication.
