MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202641093351 A) filed by Forus Health Pvt Ltd. on July 31, 2026, for System And Method For Ophthalmic Analysis Using A Vision-Language-Based Model.
Inventors include Bharadwaj, Shivam; and Purnapatra, Subhajit Banerjee.
The application for the patent was published on August 07, 2026, under issue no. 32/2026.
Abstract: Disclosed herein is a method for ophthalmic analysis using a vision-language-based model. The method includes serializing (902) a set of multimodal ophthalmic inputs and generating (904) fused embeddings comprising one or more global classification tokens and lesion-level visual patch tokens, using a multimodal encoder. Furthermore, the method includes decoding (906), in a single forward pass from the fused embeddings, a output, a user-readable biomarker caption output, and a saliency-uncertainty output and generating (908) token-grounded region masks for each token in a set of biomarker tokens appearing in the user-readable biomarker caption output with corresponding image regions. Further, the method includes enforcing (910) Tri-Output Consistency by penalizing, resolving, or flagging disagreement among the output, the user-readable biomarker caption output, and the saliency-uncertainty output. Furthermore, the method includes deriving (912) instance-level biomarker masks and quantitative biomarker metrics based on performing uncertainty-gated biomarker analytics and generating (914) a standards-aware clinical report.
Disclaimer: Curated by HT Syndication.
