MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202611099062 A) filed by Prof. Dr. Annapurna. R; Prof. Dr. Siddalingesh M. Kudari; Dr. Monika Sharma; Prof. Dr. Alka Tyagi; Dr. Jagjeet Singh; Dr. Shweta Mumbaraddi; and Prof. Dr. Jyoti Kumbar on August 17, 2026, for Machine Learning-Based Clinical Anatomy Analysis And Personalized Disease Diagnosis Support System.
Inventors include Prof. Dr. Annapurna. R; Prof. Dr. Siddalingesh M. Kudari; Dr. Monika Sharma; Prof. Dr. Alka Tyagi; Dr. Jagjeet Singh; Dr. Shweta Mumbaraddi; and Prof. Dr. Jyoti Kumbar.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present invention relates to the development of the system will accept multi-modal patient data in the form of medical images and electronic health records (EHR). In order to identify the spatial anatomical features in the pre-processed images, a 3D Convolutional Neural Network (CNN) will be used. In addition to that, an NLP model will be used to extract the clinical features from the EHR. The anatomy analysis engine will map the spatial features with respect to the dynamic probabilistic anatomical atlas for quantifying the structural and morphological variations in the data. The main novelty of the system can be seen in the attention-based multi-modal fusion network which would combine these anatomical variations with the clinical history of the patient for generating a patient-specific feature vector. This vector will then be analyzed by a predictive classification model that would produce a very personalized report including the disease scores, clinical pathways and visualization of the anatomical markers responsible for the diagnosis. FIG.1
Disclaimer: Curated by HT Syndication.
