Dr. Debesh Jha is an Assistant Professor of Computer Science at the University of South Dakota and a leading researcher in artificial intelligence for medical imaging. His work focuses on developing robust and generalizable AI systems for disease detection, medical image segmentation, and precision oncology across domains such as gastrointestinal endoscopy, liver cirrhosis MRI, lung and pancreatic tumors, surgical imaging, and radiation therapy.

He develops advanced deep learning, transformer, diffusion, and vision–language model–based methods, and has created several widely used medical imaging datasets, including CirrMRI600+, Kvasir-SEG, HyperKvasir, Kvasir-Capsule, PolypDB, and GastroVision. His algorithms—including ResUNet++, DoubleUNet, NanoNet, and other transformer-based architectures—are used globally, with Kvasir-SEG and ColonSegNet integrated into NVIDIA Clara AI applications.

Dr. Jha is recognized among the world’s top 2% of scientists by Stanford University and Elsevier and has published extensively in leading venues such as Medical Image Analysis, IEEE Transactions on Medical Imaging, Nature Scientific Data, and MICCAI. He has organized international workshops and challenges, served as a Guest Editor, reviewed more than 200 papers, and is an IEEE Senior Member. His honors include the IEEE Junior Distinguished R&D Award and the Papers With Code Contributor Award.

Before joining USD, he held research positions at Northwestern University, Simula Research Laboratory, and UiT The Arctic University of Norway. He holds a PhD in Computer Science (UiT/Simula) and master’s and bachelor’s degrees in engineering from South Korea and Nepal. At USD, he leads a multidisciplinary research group focused on advancing trustworthy, explainable, and clinically deployable AI systems for healthcare.

Artificial Intelligence, Machine Learning Fundamentals, Deep Learning, Computer Vision, Data Science & Data Mining, Pattern Recognition, Signal & Image Processing.

Multimodal AI & Vision–Language Models (VLMs), Artificial Intelligence, Medical dataset curation, Explainable AI & Responsible AI, Computer Vision & Medical Image Analysis, Medical Image Segmentation & Detection, AI in Medicine & Healthcare Diagnostics, AI in Gastroenterology & Endoscopy, AI in Dentistry, AI for Precision Oncology, AI in Sports Analytics, Generative AI & Diffusion/Transformer Architectures, Foundation Models for Medical Imaging, Robust, Generalizable & Efficient Deep Learning, Trustworthy, Safe & Ethical AI, Data-centric and Model-centric AI for Healthcare.