Lei Li

Postdoctoral Research Assistant

University of Oxford

Lei Li is a Postdoctoral Research Assistant at the Institute of Biomedical Engineering, University of Oxford. She obtained her PhD degree from the School of Biomedical Engineering, Shanghai Jiao Tong University in 2021. During her PhD, she was a visiting PhD student at Fudan University and King’s College London, respectively. She obtained the SJTU 2021 Outstanding Doctoral Graduate Development Scholarship. Her research interest is at the interface between machine learning and medical imaging, including developing novel computational methods for medical image analysis as well as translating the methods to clinical research and healthcare. She has already published more than 30 papers in peer-reviewed journals and interregnal conferences, including MedIA, IEEE TMI, and MICCAI. Some of these works have been selected as the most popular/ cited paper in IEEE TMI and MedIA. She is now one of the Board Members of Women in MICCAI (WiM) and an Editorial Board Member of the Journal of Medical Artificial Intelligence. She has co-organized four MICCAI challenge events, including LAScarQS 2022, MyoPS 2020, MS-CMRSeg 2019, and MMWHS 2017. She is a reviewer for many journals and conferences, including MedIA, IEEE TPAMI, IEEE TMI, IEEE TBME, Neurocomputing, IPMI, ISBI, MIDL, and MICCAI.

The potential applications of Artificial Intelligence (AI) in preventative health care are wide-ranging and profound, especially with the support of big data. Therefore, the applicant has set her sight to develop research along the line that she has always pursued: BIG DATA and AI, and specifically, with a particular emphasis on cardiac image analysis and modeling, such as left atrial (LA) LGE MRI computing, multi-modality cardiac image computing, and patient-specific cardiac modeling and simulation. Her major academic achievements include: (a) in terms of LA LGE MRI computation, she proposed a LA scar projection strategy and a novel graph-cuts framework, a joint LA cavity and scar segmentation framework, and a federation learning framework for multi-center data computing; (b) in terms of multi-modality image computation, she proposed a novel cross-modal multi-atlas segmentation framework, a myocardial pathology segmentation framework with a flexible combination of multi-sequence MRIs, and a joint multi-modality registration and segmentation framework; (c) in terms of patient-specific cardiac modeling and simulation, she proposed a novel deep computational model based on Bayesian neural networks for the inverse inference of ventricle activation properties; developed an efficient orthotropic Eikonal model for the myocardial infarction simulation. In the future, the applicant will extend her previous research to personalized multi-scale cardiac simulation to advance the application of cardiac “digital twins” in the field of personalized and precision medicine.

Keywords:
Cardiac "Digital Twin" ｜ Personalized and Precision Medicine｜Cardiac Image Computing and Simulation｜Artificial Intelligence｜Big Data