We are actively engaged in a number of exciting projects that span across various domains of research. Below are some of the key projects our group is currently working on:
Generalized Histopathology Disease Diagnosis
Description: Histopathological analysis is a cornerstone of disease diagnosis and treatment planning. With the explosion of big data, rapid development in machine learning, and increasing global connectivity, collaborative training of machine learning models across different organizations and countries is at an unprecedented level. The biggest concern with collaborative training in healthcare is data privacy concerns, which limit data sharing and the clinical implementation of what is technically possible. The proposed solution aims to fill this gap by providing a standardized, privacy-preserving framework for histopathology analysis across diverse datasets.
Multimodal Architectures and their applications
Description: In this project, we are exploring how involvement of multiple modalities can improve predictions and overall interpretability. Our team is exploring various fusion algorithms to explore the possibilities of these architectures. We are also actively working on literary analysis of the current scenario of application of such technologies in healthcare applications.
High Dimensional Subsampling
Description: This project focuses on developing stronger algorithms for efficient Subsampling from high dimensional data. The current algorithms in this domain are either time-inefficient or not able to extract to representative data. This project has far reaching applications in the domain of genomics.
