2018年6月12日学术讲座:基于机器学习和统计分析方法的磁共振人脑结构和功能连接研究

报告时间:6月12日下午1:30

报告地点:综合楼C302会议室

报告人:季冰 博士

讲座主要内容:Dynamic susceptibility contrast enhanced magnetic resonance imaging (DSC MRI) is widely used for studying blood perfusion in brain tumors. While the time-dependent changes of MRI signals in the region are used to calculate the tracer concentrations in the tissue to derive the regional blood volume, the tissue specific information associated with variations in signal profiles of the DSC MRI time course data is often overlooked.We report a new approach to characterize brain tumors by using a model free feature extraction strategy combining with a computation of blood volume from the featured time course profiles to interrogate time course data from DSC MRI of brain tumor patients. The results reveal the spatial and temporal heterogeneity of brain tumors based on features of time course profiles. The number of features/patterns in DSC data indicating the heterogeneity of the tumor is associated with the tumor grade. The new method can potentially extract more tumor physiological information from DSC MRI comparing to the traditional model-based analysis.

讲者简介:季冰,测试计量技术与仪器专业博士。20122-20163月于美国埃默里大学及佐治亚理工大学联合生物医学工程系胡小平教授实验室完成博士课题。其后担任埃默里大学和美国退休军人疗养中心的助理研究员。20178月加入埃默里大学医学院放射系毛辉教授放射和成像实验室,从事医学图像处理研究。研究方向涉及利用机器学习和统计分析方法研究磁共振影像数据中人脑的结构和功能连接以及信号序列中的特征,继而进一步探究其在疾病临床诊断中的应用。以第一作者和共同第一作者发表SCI期刊二区以上论文多篇,在国际会议发表论文13篇。并荣获了2018年埃默里大学温西普癌症中心学术研讨会-摘要专区二等奖和2018年国际医学磁共振年会教育奖学金。