Applied AI/ML Researcher with 9+ years at the intersection of medical imaging, deep learning, and computer vision, & nearly 6 years in industry focused on developing and prototyping solutions for real-world healthcare applications.

As an AI Research Scientist at Vope Medical, I developed real-time AI-based solutions for Surgical Image Visualization in Minimally Invasive Surgery, with nearly 2 years of experience in designing & developing ML models, optimizing image restoration pipelines, and ensuring clinical safety. My work also emphasizes model distillation & compression for low-latency deployment on edge AI platforms.

Previously, I completed my Ph.D. (2019-24, with a Gold medal & Excellence) at ETS Montreal under the supervision of Prof. Herve Lombaert and Prof. Jose Dolz. My doctoral research focused on uncertainty for image segmentation. Before that, I did a Master's (by research, 2016-19) at the MIP lab, CVIT, IIIT Hyderabad, India, where I worked on Retinal Image Enhancement under the guidance of Prof. Jayanthi Sivaswamy. I have also worked as a Senior Software Engineer for 4+ years (2012-16) at LG Soft India Pvt Ltd in Bengaluru.  I received my bachelor's degree in Electronics and Communication Engineering from the SJCE, Mysuru, India (2008-12).

Research

My research focuses on applying Machine Learning techniques to medical images. At Vopemed, I am building a Surgical image restoration pipeline for real-time deployment. In my doctoral studies, I have developed novel algorithms by leveraging uncertainty for image segmentation (MR, CT, dermoscopy) under full and limited supervision. Before this, I developed algorithms for retinal image enhancement in my Master's. In particular, I improved the quality of smartphone-based fundus and optical coherence tomography (OCT) images using unsupervised and limited supervision techniques.

More information about my work can be found on the Projects page. My resume is available here. 

Overall, my research expertise lies in Deep Learning, Computer Vision, and Medical Image Analysis, including Image Restoration/Enhancement/Reconstruction, Segmentation, Semi & Weakly supervised learning, Uncertainty, Interpretability, Calibration, Image denoising, Model Optimization & compression, Knowledge Distillation, Representation learning, Domain adaptation, Image retrieval, Vision Transformers, Generative AI (Generative Adversarial Networks, Diffusion models), Foundation, World Models and geometric deep learning.