MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641058098 A) filed by Benita Josephine P; and Dr. Nithyakani P on May 07, 2026, for Tri-Modal Ensemble Lung Disease Detection Using Ct, Mri And X-Ray With Adaptive Fusion And Xai.
Inventors include Benita Josephine P; and Dr. Nithyakani P.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: Tri-Modal Ensemble Lung Disease Detection Using CT, MRI, and X-ray with Adaptive Fusion and XAI" The present invention provides a tri-modal deep learning framework for the automated detection of lung diseases using computed tomography (CT), magnetic resonance imaging (MRI), and chest X-ray images. The system employs ResNetl8 architectures for CT and MRI classification, a VGG 16-based model for multi-class X-ray analysis, and a Vision Transformer (ViT) to enhance feature representation. An adaptive weighted decision-level fusion strategy is introduced, wherein the contribution of each imaging modality is dynamically determined based on its Fl-score using SoftMax normalization to improve overall classification performance. Furthermore, Gradient-weighted Class Activation Mapping (Grad-CAM) is integrated to provide visual explanations of the model's predictions, enhancing interpretability for clinical applications.
Disclaimer: Curated by HT Syndication.
