MUMBAI, India, Oct. 12 -- Intellectual Property India has published a patent application (202641118753 A) filed by Easwari Engineering College; and Srm Institute Of Science And Technology, Ramapuram Campus on October 05, 2026, for Reliability-Aware Explainable Multimodal Disease Diagnosis Using Vision Transformer And Clinicalbert For Chest X-Ray Analysis.
Inventors include Kapilan K; Prashanth R; and Saranya D.
The application for the patent was published on October 09, 2026, under issue no. 41/2026.
Abstract: The present invention relates to a reliability-aware explainable multimodal system for disease diagnosis using chest X-ray images and clinical reports. The system receives a chest X-ray image and associated clinical text, preprocesses the inputs, and extracts visual features using a Vision Transformer (ViT) and contextual textual features using ClinicalBERT. A reliability estimation module evaluates the reliability of the visual and textual representations based on available image and clinical information. A reliability-aware adaptive fusion module dynamically adjusts the contribution of the two modalities and generates a fused representation for disease classification. The system further provides explainable predictions using Grad-CAM and/or attention-based visualization for identifying influential image regions and SHAP-based attribution for identifying important clinical terms. The final output provides predicted disease or findings together with confidence, reliability level, and supporting visual and textual evidence, thereby enabling transparent and trustworthy clinical decision support Total Number of Words: 141 words
Disclaimer: Curated by HT Syndication.
