About me
I recently completed my PhD in Imaging science at the Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology. I worked with Dr. Cristian A. Linte (main advisor) at Biomedical Modeling, Visualization and Image-guided Navigation Lab (BiMVisIGN). I was also co-advised by Dr. Binod Bhattarai and Dr. Bishesh Khanal. Before starting my PhD, I worked at NAAMII (a research institute in Nepal), Zeg.ai (a 3D AI solution startup), and NDS (an embedded systems and IoT startup). I completed my undergraduate in Electronics and Communication Engineering at Institute of Engineering, Pulchowk Campus, Nepal.
Research
My research focuses on data-driven medical image analysis using deep learning, particularly in scenarios with limited or noisy labeled data. I am interested in addressing the challenge of building robust deep learning models and frameworks for various downstream tasks such as classification, segmentation, image-text retrieval, report generation, and visual question answering. My work encompasses areas such as learning with noisy labels, active learning, active relabeling, self-supervised learning, and vision-language models. Recently, I have become more interested in tackling the hallucination problem in large vision-language models to develop more trustworthy systems.
Through my PhD program, I have also built a strong foundation in Imaging Science, gaining expertise in various areas, including image acquisition, camera design, calibration, image processing, imaging display, human vision, and color science.
Interests: Medical Image Analysis, Learning with Noisy Labels, Active Learning, Continual Learning, Active Relabeling, Self-supervised learning, Multimodal Learning, Vision-Languge Pretraining.
News
[June 2025] I am soon joining Nvidia as Camera Software Image Quality Engineer.
[May 2025] Our paper titled “Hallucination-Aware Multimodal Benchmark for Gastrointestinal Image Analysis with Large Vision-Language Models” got early acceptance at MICCAI 2025. (Ranked among top 9%)
[April 2025] Successfully defended my PhD “Towards Robust Deep Learning for Medical Imaging with Limited and Noisy Labeled Data” at the Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology.
[November 2024] Successfully defended my PhD proposal “Towards Robust Deep Learning for Medical Imaging with Limited and Noisy Labeled Data”
[July 2024] Presented our paper titled “Investigating the robustness of vision transformers against label noise in medical image classification” at EMBC, 2024 [Oral].
[July 2024] Our paper titled “Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise” got accepted at MICCAI, 2024.
[May 2024] Joined NVIDIA as Camera Software Quality Intern for summer 3 months.
[Oct 2023] Gave a short talk on my PhD research at PhD Research Showcase, in Industrial Associates Fall 2023 Symposium, Rochester, NY.
[Oct 2023] Attended MICCAI, 2023 at Vancouver, Canada to present our work on “Improving medical image classification in noisy labels using only self-supervised pretraining”.
[Jul 2023] Our paper titled “Improving medical image classification in noisy labels using only self-supervised pretraining” got accepted at Data Engineering in Medical Imaging workshop, MICCAI, 2023.
[Jul 2023] Presented our work on “M-VAAL: Multimodal variational adversarial active learning for downstream medical image analysis tasks” at MIUA 2023, Aberdeen, United Kingdom.
[Jun 2023] Our paper titled “M-VAAL: Multimodal variational adversarial active learning for downstream medical image analysis tasks” got accepted at Conference on Medical Image Understanding and Analysis (MIUA) 2023 for Oral presentation.
[Feb 2023] Attended SPIE Medical Imaging 2023 at San Diego, California, US to present our poster on “Investigating the impact of class-dependent label noise in medical image classification”.
[Nov 2022] Our paper titled “Investigating the impact of class-dependent label noise in medical image classification” got accepted at SPIE Medical Imaging 2023.
[Jul 2022] Joined Biomedical Modeling, Visualization and Image-guided Navigation Lab (BiMVisIGN), Rochester Institute of Technology, to work with Prof. Cristian A. Linte.
[Jan 2022] Joined AWARE-AI NRT program as Rochester Institute of Technology as Trainee.
[Oct 2021] Presented a poster of my work “How does heterogeneous label noise impact generalization in neural nets?” at IEEE Western NY Signal Processing Workshop, Rochester, NY, 2021.
[Jun 2021] Our paper titled “How does heterogeneous label noise impact generalization in neural nets?” got accepted at International Symposium on Visual Computing (ISVC) 2021.
[May 2021] Joined Machine and Neuromorphic Perception Lab (kLab), Rochester Institute of Technology, to work with Prof. Christopher Kanan.
[Aug 2020] Started PhD in Imaging Science at Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology.
[Apr 2019] Joined NepAl Applied Mathematics and Informatics Institute for research (NAAMII) to work as Research Assistant.
[Feb 2018] Started working at Nepal Digital Systems (startup company) as Firmware/Image Processing Engineer.
[Dec 2017] Completed undergraduate in Electronics and Communication Engineering, at Institute of Engineering, Pulchowk Campus, Nepal.