5 papers
Imaging-Derived Coronary Fractional Flow Reserve: Advances in Physics-Based, Machine Learning, and Physics-Informed Methods
Tanxin Zhu, Emran Hossen, Chen Zhao +4
Purpose of Review Imaging derived fractional flow reserve (FFR) is rapidly evolving beyond conventional computational fluid dynamics (CFD) based pipelines toward machine learning (…
Improving Generalizability of Hip Fracture Risk Prediction via Domain Adaptation Across Multiple Cohorts
Shuo Sun, Meiling Zhou, Chen Zhao +8
Clinical risk prediction models often fail to be generalized across cohorts because underlying data distributions differ by clinical site, region, demographics, and measurement pro…
Anatomy Guided Coronary Artery Segmentation from CCTA Using Spatial Frequency Joint Modeling
Huan Huang, Michele Esposito, Chen Zhao
Accurate coronary artery segmentation from coronary computed tomography angiography is essential for quantitative coronary analysis and clinical decision support. Nevertheless, rel…
Blood Pressure Prediction for Coronary Artery Disease Diagnosis using Coronary Computed Tomography Angiography
Rene Lisasi, Michele Esposito, Chen Zhao
Computational fluid dynamics (CFD) based simulation of coronary blood flow provides valuable hemodynamic markers, such as pressure gradients, for diagnosing coronary artery disease…
ShadowServe: Interference-Free KV Cache Fetching for Distributed Prefix Caching
Xingyu Xiang, Raj Joshi, Yuhan Liu +6
Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when netw…