Google Scholar – ResearchGate – Github – LinkedIn – Twitter – Semantic Scholar – dblp – ORCiD – publons
Debesh Jha, Ph.D.,
Visiting Assistant Professor, Department of Computer Science, University of South Dakota
Research Overview:
My primary research focuses on developing advanced artificial intelligence algorithms to improve medical imaging across various clinical domains, including upper and lower gastrointestinal (GI) tract imaging, lung and liver tumor analysis, and predictive modeling for radiation therapy outcomes. Accurate medical diagnosis significantly depends on high-quality imaging data and sophisticated computational techniques. However, current diagnostic accuracy in radiology and gastrointestinal (GI) endoscopy is frequently limited by challenges such as data scarcity, interobserver variability, biases, and limited generalizability. To overcome these issues, my work emphasizes the meticulous curation of comprehensive, multinational datasets, including CirrMRI600+ for liver cirrhosis imaging, PolypDB, PolypGen, and Kvasir-SEG for colonoscopy, as well as HyperKvasir and KvasirCapsule for GI endoscopy and video capsule endoscopy. Additionally, I develop novel segmentation architectures such as ResUNet++, DoubleUNet, ColonSegNet, and transformer-based models that significantly enhance diagnostic accuracy.
In the past, I have developed algorithms for colonoscopy/endoscopy. One of our recent algorithms, ColonSegNet and data, Kvasir-SEG has been by NVIDIA Clara. I am highly optimistic about the potential of AI tools to function as an additional diagnostic support for radiologists, enabling enhanced healthcare quality and informed decision-making. Furthermore, I investigate predictive modeling and organ-at-risk assessment to optimize radiation therapy planning and outcomes. By integrating curated datasets with state-of-the-art deep learning methodologies, my research aims to substantially elevate the precision, generalizability, and clinical effectiveness of AI-driven diagnostics and therapies in healthcare.
Research Interests
- Medical Image Segmentation – Liver, lung, pancreas, polyp, and multi-organ segmentation in CT/MRI.
- Multimodal AI & Vision-Language Models – AI-driven medical VQA, vision-language integration for diagnostics.
- AI for Endoscopy & Surgery – Real-time polyp detection, instrument tracking, and AI-assisted navigation.
- Cancer Imaging & Precision Medicine – Advanced AI for prostate and lung cancer segmentation, diagnosis, and treatment planning.
- Foundation & Large Vision Models – Transformers, diffusion models, and SAM-based architectures for medical AI.
- Camouflaged & Anomaly Detection – AI-driven solutions for defect detection, abnormality analysis, and medical scene understanding.
- Ethical AI & Generative Models – Addressing bias, fairness, and responsible deployment of AI in healthcare.
- Non-Invasive Diagnostics – AI-powered biopsy-free liver disease detection and enhanced oncology imaging.
- AI in Sports Analytics – Performance optimization and strategic decision-making through AI-driven insights.
Recent News:
- Recognized among the world’s top 2% scientists by Stanford University and Elsevier ranking for contributions to AI in biomedical engineering.
- Received A & S Professional Development Grant Program from the University of South Dakota for Spring 2025.
- Elevated to IEEE Senior Member.
- 3 papers are accepted at ICASSP 2025.
- 3 papers are accepted at IEEE CVF WACV 2025.
- Our work DiffBoost is accepted at IEEE TMI.
- Received Poster of Distinction during Digestive Disease Week (DDW) 2024.
- Our paper on “Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation” won the Best Industry-Related Paper Award at ICPR2024
- Selected as Junior Distinguished Research and Development (R&D) Award for the year 2024 by the IEEE Chicago Section Award committee.
- 5 papers presented at MICCAI 2024.
- 2 papers are accepted at the 2024 CVPR Workshop.
- IEEE TMI Distinguished Reviewer Silver Level Award for 2023-2024
- Acting as an associate editor for Frontiers in Radiation Oncology.
- Acting as an associate editor for Medical Physics Journal.
- Our Kvasir-SEG dataset was mentioned in the “Artificial Intelligence Index Report 2022″ from Stanford University.
- I am serving as the Guest Editor of “Applications of Artificial Intelligence for the Diagnosis of Gastrointestinal Diseases.” Please feel free to submit your work.
- I am serving as the Guest Editor of “Machine-Learning-Based Process and Analysis of Medical Images“. Kindly consider your high-quality work.
- One paper was accepted at MICCAI 2022.
Achievements & Recognition
- Recognized among the world’s top 2% scientists by Stanford University and Elsevier ranking for contributions to AI in biomedical engineering.
- Received Poster of Distinction during Digestive Disease Week (DDW) 2024.
- NSF ICORPS award 2025
- Best Industry-related Paper Award, International Association for Pattern Recognition (IAPR) at ICPR 2024.
- Received A & S Professional Development Grant Program from the University of South Dakota for Spring 2025.
- Elevated to IEEE Senior Member.
- Received Junior Distinguished Research and Development (R&D) Award for the year 2024 by the IEEE Chicago Section Award committee.
- Received Junior Distinguished Research and Development (R&D) Award for the year 2022 by the IEEE Chicago Section Award committee.
- Received the first-ever Paper with Code Contributor Award
- MICCAI 2022 Student Travel Award (Co-author)
- Best student paper award finalist (CBMS 2020), Mayo Clinic, Rochester, USA.
- Best paper award at International Conference on Electronics, Information, and Communication (ICEIC 2018), Hawaii, USA.
- Best Poster Presentation Award at International Conference on Electronics, Information, and Communication (ICEIC 2018), Hawaii, USA.
Guest & Associate Editor
Ongoing Projects & Collaborations:
Actively seeking collaborations in medical image analysis, deep learning, gastrointestinal diagnostics, surgical data science, and trustworthy AI applications.
Please feel free to contact me for collaboration opportunities.