5 papers
Perturb-and-Restore: Simulation-driven Structural Augmentation Framework for Imbalance Chromosomal Anomaly Detection
Yilan Zhang, Hanbiao Chen, Changchun Yang +10
Detecting structural chromosomal abnormalities is crucial for accurate diagnosis and management of genetic disorders. However, collecting sufficient structural abnormality data is…
Revisiting Data Scaling in Medical Image Segmentation via Topology-Aware Augmentation
Yuetan Chu, Zhongyi Han, Gongning Luo +1
Understanding how segmentation performance scales with training data is fundamental for developing data-efficient medical AI systems. In this study, we systematically revisit data…
Facial Foundational Model Advances Early Warning of Coronary Artery Disease from Live Videos with DigitalShadow
Juexiao Zhou, Zhongyi Han, Mankun Xin +19
Global population aging presents increasing challenges to healthcare systems, with coronary artery disease (CAD) responsible for approximately 17.8 million deaths annually, making…
Improving Representation of High-frequency Components for Medical Visual Foundation Models
Yuetan Chu, Yilan Zhang, Zhongyi Han +5
Foundation models have recently attracted significant attention for their impressive generalizability across diverse downstream tasks. However, these models are demonstrated to exh…
Deep learning-driven pulmonary artery and vein segmentation reveals demography-associated vasculature anatomical differences
Yuetan Chu, Gongning Luo, Longxi Zhou +13
Pulmonary artery-vein segmentation is crucial for disease diagnosis and surgical planning and is traditionally achieved by Computed Tomography Pulmonary Angiography (CTPA). However…