Deep Learning
Medical Image Analysis
Chest X-rays Diagnosis
Data Distillation
Lifelong learning
Explainable AI
My current research as a PhD scholar is focused on developing innovative and interpretable AI solutions for medical image analysis, with a specific emphasis on chest x-ray diagnosis. My thesis work centers on designing a generative model that produces an explicit visualization of a disease map, which is crucial for providing clinicians with transparent and interpretable diagnostic aids. To address the practical challenges of clinical data, I am also developing methods for class-incremental learning and few-shot learning, enabling my models to efficiently adapt to new or rare diseases with minimal data. A further integral part of my thesis involves the development of coreset algorithms to optimize the data required for training large deep learning models, significantly reducing computational demands. In parallel, I am exploring knowledge distillation to create efficient, high-performing models and am working on visual question answering (VQA) to build intelligent systems that can respond to natural language queries about medical scans.
This specialized research is built upon a strong and progressive background in data science and software development. Immediately prior to my PhD, I served as a Junior Research Fellow, where I applied data-driven forecasting methods to predict solar power generation and consumption. This hands-on experience followed my M. Tech, where I conducted research on graph-based sequential change point detection, a project that culminated in a published paper. My academic journey began with a foundation in software engineering during my B. Tech, where I gained practical experience in the development and testing of web-based applications.
The culmination of these diverse experiences—from software engineering and algorithmic research to applied data forecasting and cutting-edge deep learning—has uniquely prepared me to address the multifaceted challenges in modern AI for healthcare. My work is driven by a commitment to not only advancing the technical frontiers of machine learning but also to creating tools that are efficient, adaptable, and, most importantly, clinically meaningful.
Junior Research Fellow, IIT Gandhinagar, Nov 2019 - Oct 2020.
217-A,
Department of Computer Science and Engineering,
Indian Institute of Technology Jodhpur,
NH 62, Nagaur Road,
Karwar, Jodhpur,
Rajasthan, India - 342030.