Publications: 'Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models' (MICCAI 2025), 'Investigating the robustness of vision transformers against label noise in medical image classification' (EMBC 2024), 'Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise' (MICCAI 2024), 'Improving medical image classification in noisy labels using only self-supervised pretraining' (MICCAI 2023), 'M-VAAL: Multimodal variational adversarial active learning for downstream medical image analysis tasks' (MIUA 2023). Other achievements: Successfully defended his PhD thesis and presented at multiple international conferences.
Research Experience
Worked at BiMVisIGN lab during his PhD, focusing on medical image analysis. Previously worked at NAAMII (a research institute in Nepal), Zeg.ai (a 3D AI solution startup), and NDS (an embedded systems and IoT startup).
Education
PhD in Imaging Science, Rochester Institute of Technology, Advisors: Dr. Cristian A. Linte (primary advisor), Dr. Binod Bhattarai, and Dr. Bishesh Khanal; Bachelor's in Electronics and Communication Engineering, Institute of Engineering, Pulchowk Campus, Nepal.
Background
Research Interests: Medical Image Analysis, Learning with Noisy Labels, Active Learning, Continual Learning, Active Relabeling, Self-supervised learning, Multimodal Learning, Vision-Language Pretraining. Background: Recently completed a PhD in Imaging Science at the Chester F. Carlson Center for Imaging Science, RIT, focusing on data-driven medical image analysis using deep learning.
Miscellany
Soon joining NVIDIA as a Camera Software Image Quality Engineer; personal interests not mentioned.