Intellectual Property India Publishes Patent Application for Liver Diseases Progression Diagnosis Using Cross Attention Fusion Of Multimodality Data

MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641068322 A) filed by Aarupadai Veedu Institute Of Technology, Vinayaka Missions Research Foundationdu on June 01, 2026, for Liver Diseases Progression Diagnosis Using Cross Attention Fusion Of Multimodality Data.

Inventors include Dhasaradhan K; and Jaichandran R.

The application for the patent was published on July 17, 2026, under issue no. 29/2026.

Abstract: Present invention generally relates to a system and method for liver disease progression diagnosis using cross attention fusion of features from multimodality data of liver disease patients. Liver disease is the most common life threatening disease increasing worldwide and accurate diagnosis and predicting of these diseases will help in providing better treatments. Traditional diagnosis methods take long time and requires skilled man power whose access in Umited in rural areas. Alternatively, ML and DL methods can be used to assist physicians in diagnosis of liver diseases. Most of the existing ML and DL methods use single modality data and multimodal methods use simple concatenation of multimodality data in the diagnosis of diseases which may not be accurate. Hence these invention presents a Multimodal Deep Learning Frameworks using Cross Attention Fusion of Multimodality Data for Diagnosis and Prediction of Progression of liver disease. Present invention includes attention-based TransUNet encoder that extracts features from liver MRI images, the ResNetSD encoder that extracts features from liver CT images, and the MLP encoder that extracts features from patients’ clinical data. Cr-oatsstention fusion module generates a feature map by associating features extracted from liver MRI images, liver CT images, and clinical data of liver disease patients and assigns more weightage to the most significant features. Joint Diagnostic Network classifies liver diseases as HCC, cirrhosis, and NAFLD and predicts the progression rate of liver disease as no progression, mild, moderate, or severe progression. Present invention is evaluated using metrics such as Accuracy, Precision, Sensitivity, Specificity, Fl-score and AUC-ROC. Results show the present invention has significant improvement in diagnosis and prediction of progression of liver disease compared to existing methods.

Disclaimer: Curated by HT Syndication.