A Composable Multimodal Framework for cine CMR-Text-Driven Prediction of Heart Failure Outcomes
用于电影心脏磁共振-文本驱动的心力衰竭结局预测的可组合多模态框架
机构 * Department of Cardiology, Nanjing Drum Tower Hospital, State Key Laboratory of Pharmaceutical Biotechnology, Nanjing University(南京鼓楼医院心内科,南京大学国家药物生物技术重点实验室) ; School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University(上海交通大学电子信息与电气工程学院) ; College of Electronic and Optical Engineering, Nanjing University of Posts and Telecommunications(南京邮电大学电子与光学工程学院) ; College of Integrated Circuit Science and Engineering, Nanjing University of Posts and Telecommunications(南京邮电大学集成电路科学与工程学院) ; Department of Cardiology, Nanjing Drum Tower Hospital Clinical College of Nanjing Medical University(南京医科大学南京鼓楼医院临床学院心内科) ; Institute of Quantum Information and Technology, Nanjing University of Posts and Telecommunications(南京邮电大学量子信息与技术研究院)
专题命中 多模态评测 :multimodal(title);multi-modal(abstract);分类 cs.CV、cs.AI
AI总结 提出一种可组合多模态框架,通过整合cine CMR影像、结构化临床指标和非结构化文本记录,实现比单模态AI算法更准确的心力衰竭预后预测,并支持个性化治疗优化。