报告题目：Multi-omics Analysis for Clinical Outcome Assessment

主讲人：焦志成

单位：布朗大学

时间：9月5日9:00

腾讯ID：218-278-766

摘要：In recent years, advanced artificial intelligence (AI) methods, especially deep learning models have achieved great success in many applications of biomedical data analysis, including tumor segmentation, prognosis prediction, etc. However, most of the existing studies formulate problems as classification tasks, making them hard to meet the real clinical needs of quantified assessment and longitudinal analysis. Therefore, we discussed the applications of deep learning models for time-to-event prognosis based on multi-modal medical data. In this talk, I will mainly present two of my research thrusts on i) prognostication of COVID-19 patients and ii) recurrence prediction of lung cancer patients. Our proposed frameworks achieve promising prognosis prediction of COVID-19 patients that succeeds in providing clinically meaningful allocation of medical resources and obtaining individualized recurrence risk assessment of lung cancer patients.

简介：焦志成，布朗大学Warren Alpert医学院助理教授，影像AI实验室主任，罗得岛医院研究员。2018年于西安电子科技大学获工学博士学位（高新波教授），曾在北卡罗莱纳大学（教堂山，沈定刚教授）和宾夕法尼亚老员工物医学图像计算中心（CBICA）担任博士后研究员。研究兴趣主要包括基于人工智能方法的多模态医学数据分析、深度学习以及其在计算机视觉上的应用。目前主要从事基于影像和临床数据的病人预后分析（COVID-19等），肿瘤病人复发预测和人机协同的计算机辅助检测与诊断。研究成果发表在The Lancet Digital Health, Nature Digital Medicine, JAMA Network, eBiomedicine, IEEE Transactions on Medical Imaging, IEEE Transactions on Neural Networks and Learning System等期刊和会议。