Sandesh Pokhrel
Research Assistant, NAAMII || Computer Vision Engineer, Fogsphere
Hi! I’m Sandesh Pokhrel, a passionate computer vision researcher at NAAMII under Assistant Professor Dr. Binod Bhattarai. I am working at the forefront of medical imaging and its applications through computer vision and AI. I current lead a project on automatic coronary artery segmentation and stenosis detection in angiographic images in two hospitals in Nepal. My research focuses trustworthy AI through Out-of-Distribution detection in gastrointestinal vision by utilizing various modalities. My research at NAAMII is funded by Fogsphere where I research and optimize state of the art computer vision methods on edge devices for safety critical applications.
As a computer engineering graduate from Institute of Engineering(IOE), Pulchowk Campus, I have developed a diverse skill set in advanced AI and computer vision technologies. My expertise spans out-of-distribution detection, multi-modal learning, self-supervised learning, object detection and segmentation, pose estimation, speech recognition and voice cloning. I specialize in applying these cutting-edge techniques to develop innovative software solutions that address critical real world challenges. My work focuses on bridging the gap between complex AI concepts and practical applications, driving meaningful impace across multiple domains.
As personal interests, I enthusiastically watch and play football, and am an avid star gazer on cloudless nights.
Looking forward to connecting with you!
Research Interests: Medical AI, Multi modal learning, Out-of-distribution detection, Cardiovascular imaging, Gastrointestinal Vision
latest posts
Dec 27, 2023 | The Mouse Math |
---|---|
Feb 27, 2023 | Aftermath of CIT |
Dec 27, 2022 | Children in Technology |
selected publications
- DEMI, MICCAICross-Task Data Augmentation by Pseudo-label Generation for Region Based Coronary Artery Instance Segmentation2024Accepted at DEMI, MICCAI 2024
- Convnextv2 fusion with mask R-CNN for automatic region based coronary artery stenosis detection for disease diagnosisarXiv preprint arXiv:2310.04749, 2023Runner up at ARCADE, MICCAI 2023
- DEMI, MICCAITTA-OOD: Test-time Augmentation for Improving Out-of-Distribution Detection in Gastrointestinal VisionarXiv preprint arXiv:2407.14024, 2024Accepted at DEMI, MICCAI 2024