4 papers
Robust Cross-Domain Generalization Using Unlabeled Target Data with Source-Domain Supervision
Yuyue Zhou, Shrimanti Ghosh, Michael +7
It is often desirable to generalize medical imaging AI models trained with dense annotations to data acquired from different ultrasound scanners or clinical sites; however, retrain…
FlexICL: A Flexible Visual In-context Learning Framework for Elbow and Wrist Ultrasound Segmentation
Yuyue Zhou, Jessica Knight, Shrimanti Ghosh +3
Elbow and wrist fractures are the most common fractures in pediatric populations. Automatic segmentation of musculoskeletal structures in ultrasound (US) can improve diagnostic acc…
Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts
Assefa Seyoum Wahd, Banafshe Felfeliyan, Yuyue Zhou +5
Foundation models like the segment anything model require high-quality manual prompts for medical image segmentation, which is time-consuming and requires expertise. SAM and its va…
A Simple Framework Uniting Visual In-context Learning with Masked Image Modeling to Improve Ultrasound Segmentation
Yuyue Zhou, Banafshe Felfeliyan, Shrimanti Ghosh +6
Conventional deep learning models deal with images one-by-one, requiring costly and time-consuming expert labeling in the field of medical imaging, and domain-specific restriction…