I am a PhD student in Electrical & Computer Engineering at Duke University, working at the Center for Virtual Imaging Trials. My research focuses on developing advanced computer vision and AI methods for medical imaging applications.

My work spans vision-language models for disease localization, multi-modal segmentation algorithms, and the creation of anatomical digital twins for synthetic imaging experiments. I'm particularly interested in self-supervised and weakly-supervised learning approaches that reduce the annotation burden in medical AI.

Before joining Duke, I earned my Master's in Medical Imaging & Applications from the University of Girona (Spain) as an Erasmus+ Global Scholar, and my Bachelor's in Electrical & Electronics Engineering from VNIT Nagpur (India). I have conducted research at VICOROB Lab in Girona, BioMedia Lab at Imperial College London, NAAMII in Nepal, and CVIT at Duke University.

research interests

Computer Vision Medical Imaging Vision-Language Models Multi-Modal Learning 3D Medical Imaging Deep Learning Self-Supervised Learning Digital Twins

selected publications

Five Models for Five Modalities: Open-Vocabulary Segmentation in Medical Imaging
L. Dahal, Y. Bhandari, P. Segars, J. Lo
Computer Vision and Pattern Recognition (CVPR), 2025
XCAT 3.0: A Comprehensive Library of Personalized Digital Twins Derived from CT Scans
L. Dahal, M. Ghojoghnejad, L. Vancoillie, D. Ghosh, et al.
Medical Image Analysis, 2025
Automatic Quality Control in Computed Tomography Volumes Segmentation Using a Small Set of XCAT as Reference Images
L. Dahal, Y. Wang, F.I. Tushar, I. Montero, et al.
Medical Imaging 2023: Image Processing
Uncertainty Estimation in Deep 2D Echocardiography Segmentation
L. Dahal, A. Kafle, B. Khanal
arXiv preprint, 2020