Lei's Research
Lei Li
Lecturer
Digital Heart Modeling Lab, University of Southampton
Overview
Lei Li
2024-03-10 16:42:21

Biography

Lei Li is a Lecturer (equals to Assistant Professor) at the School of Electronics & Computer Science, University of Southampton. She received her PhD degree from the School of Biomedical Engineering, Shanghai Jiao Tong University in 2021 and obtained the SJTU 2021 Outstanding Doctoral Graduate Development Scholarship. During her PhD, she was a visiting PhD student at Fudan University and King’s College London, respectively. She received her bachelor’s degree in Department of Medical Information Engineering, Sichuan University, in 2016.

Her research interest is AI for healthcare, specifically focusing on medical image analysis, multi-modal AI, and cardiac digital twins. She has already published more than 40 papers in peer-reviewed journals and international conferences, including MedIA, IEEE TMI, MICCAI and FIMH. Some of these works have been selected as the most popular cited paper in MedIA and TMI. She is a Board Member of Women in MICCAI (WiM) and Area Chair of MICCAI 2024. She has been selected as the Rising Star of Women in Engineering by Asian Deans’ Forum 2023. She has co-organized four MICCAI challenge events, including LAScarQS 2022, MyoPS 2020, MS-CMRSeg 2019, and MM-WHS 2017. She serves as a reviewer for many journals and conferences, including MedIA, IEEE TPAMI, IEEE TMI, IEEE TBME, Neurocomputing, Information Fusion, Neural Networks, ISBI, IPMI, MIDL, and MICCAI, etc.

I am on looking for self-motivated PhD students who are interested in AI for heathcare, especially AI powered personalized virtual heart modelling (application link).

Research/Education Experience

  • 01/2024-now   Lecturer, School of Electronics & Computer Science, University of Southampton, Southampton, UK
  • 01/2024-now   Visiting Researcher, Institute of Biomedical Engineering, University of Oxford, Oxford, UK
  • 08/2021-12/2023   Postdoctoral Research Assistant, Institute of Biomedical Engineering, University of Oxford, Oxford, UK (Supervisor: Professor Vicente Grau)
  • 09/2016-06/2021   PhD, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China (Supervisor:Professor Xiahai Zhuang)
  • 01/2020-03/2021   Visiting PhD, School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK (Supervisor: Professor Julia A Schnabel)
  • 12/2017-12/2019   Visiting PhD, School of Data Science, Fudan University, Shanghai, China (Supervisor: Professor Xiahai Zhuang)
  • 09/2012-06/2016   Bachelor, Dept. Medical Information Engineering, Sichuan University, Chengdu, China (Related Academics: Gang Yang)

Academic Services

Honors & Awards

  • 2024: Featured Woman in Science at RSIP Vision
  • 2023: The Rising Star of Women in Engineering - Asian Deans’ Forum 2023
  • 2023: IEEE TMI Distinguished Reviewer - Gold Level (2022-2023)
  • 2022: IEEE TMI Distinguished Reviewer - Bronze Level (2020-2022)
  • 2022: SJTU 2021 Outstanding Doctoral Graduate Development Scholarship
  • 2019: Best Poster Award in the 2019 International Conference on Data Science

Invited Talks

  • 23/02/2024   Invited talk “AI Powered Personalized Virtual Heart Modelling” at Biomedical Research Centre (BRC) Science Forum in University of Southampton.
  • 29/01/2024   Invited talk “Artificial Intelligence in Cardiac Image Computing and Modeling” at Department of Biomedical Engineering, National University of Singapore (NUS).
  • 18/07/2023   Invited talk “Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference”, in Multi-scale & Multi-modality Digital Health Collaboration Workshop, supported by the Alan Turing Institute.
  • 10/06/2023   Invited talk “Artificial Intelligence in Cardiac Image Computing and Modeling”, which is hosted by Prof. Yi Dai at Nankai University. Talk info
  • 15/02/2023   Invited talk “Artificial Intelligence in Cardiac Image Computing and Modeling”, which is hosted by Prof. Evangelos B. Mazomenos at University College London.
  • 08/12/2022   Invited talk “Domain Generalization and Distributed Learning for Left Atrial Segmentation from Multi-Center LGE-MRI”, in Turing workshop on Human-AI Interaction in Bio-Medicine.
  • 18/09/2022   Oral presenter in STACOM 2022 for the paper “Deep Computational Model for the Inference of Ventricular Activation Properties”. Video
  • 12/04/2022   Invited talk “Left Atrial LGE MRI Computing for Atrial Fibrillation” at MICS (in Chinese). PPT; Video
  • 27/09/2021   Oral presenter in M&Ms-2 for the paper “Right Ventricular Segmentation from Short- and Long-Axis MRIs via Information Transition”. Video

Teaching Experience

  • Undergraduate Courses
    • Biomedical Image Analysis
      • Demonstrator: ~3 hours per week; Weeks 6-8 of Trinity Term 2023; University of Oxford
      • Demonstrator: ~3 hours per week; Weeks 6-8 of Trinity Term 2022; University of Oxford
    • Information Engineering Systems
      • Demonstrator: ~12 hours per week including providing undergraduate with guidance, feedback, and marking; Weeks 7-8 of Hilary Term 2023; University of Oxford
  • Postgraduate Courses
    • Medical Imaging, Microscopy and Analysis
      • Demonstrator: ~5 hours per week; Weeks 5-6 of Hilary Term 2023; University of Oxford
      • Demonstrator: ~5 hours per week; Weeks 5-6 of Hilary Term 2022; University of Oxford

Selected Works

Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference
IEEE Transactions on Medical Imaging, 2024
Patient-specific cardiac computational models are essential for the efficient realization of precision medicine and in-silico clinical trials using digital twins. Cardiac digital twins can provide non-invasive characterizations of cardiac functions for individual patients, and therefore are promising for the patient-specific diagnosis and therapy stratification. However, current workflows for both the anatomical and functional twinning phases, referring to the inference of model anatomy and parameter from clinical data, are not sufficiently efficient, robust, and accurate. In this work, we propose a deep learning-based patient-specific computational model, which can fuse both anatomical and electrophysiological information for the inverse inference of infarcted area.
Keywords: Cardiac gigital twins; Myocardial Infarction; Deep computational models; Inverse inference
Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review
Medical Image Analysis, vol. 77, 102360, 2022
LGE MRI is commonly used to visualize and quantify left atrial (LA) scars. The position and extent of LA scars provide important information on the pathophysiology and progression of atrial fibrillation (AF). Hence, LA LGE MRI computing and analysis are essential for computer-assisted diagnosis and treatment stratification of AF patients. Since manual delineations can be time-consuming and subject to intra- and inter-expert variability, automating this computing is highly desired, which nevertheless is still challenging and under-researched. This paper aims to provide a systematic review on computing methods for LA cavity, wall, scar, and ablation gap segmentation and quantification from LGE MRI, and the related literature for AF studies."
Keywords: Atrial fibrillation; LGE MRI; Left atrium; Review
AtrialJSQnet: A New Framework for Joint Segmentation and Quantification of Left Atrium and Scars Incorporating Spatial and Shape Information
Medical Image Analysis, vol. 76, 102303, 2022
LA and atrial scar segmentation from LGE MRI is an important task in clinical practice. Previous methods normally solved the two tasks independently and ignored the intrinsic spatial relationship between LA and scars. In this work, we develop a new framework, namely AtrialJSQnet, where LA segmentation, scar projection onto the LA surface, and scar quantification are performed simultaneously in an end-to-end style. We propose a mechanism of shape attention (SA) via an implicit surface projection to utilize the inherent correlation between LA cavity and scars. Besides, a spatial encoding (SE) loss is introduced to incorporate continuous spatial information of the target in order to reduce noisy patches in the predicted segmentation.
Keywords: Joint optimization; Atrial segmentation; Scar quantification; Spatial encoding; Shape attention
AtrialGeneral: Domain Generalization for Left Atrial Segmentation of Multi-Center LGE MRIs
MICCAI, 557-566, 2021
Though deep learning-based methods can provide promising LA segmentation results, they often generalize poorly to unseen domains, such as data from different scanners and/or sites. In this work, we collect 140 LGE MRIs from different centers with different levels of image quality. To evaluate the domain generalization ability of models on the LA segmentation task, we employ four commonly used semantic segmentation networks for the LA segmentation from multi-center LGE MRIs. Besides, we investigate three domain generalization strategies, i.e., histogram matching, mutual information based disentangled representation, and random style transfer, where a simple histogram matching is proved to be most effective.
Keywords: Atrial fibrillation; Left atrium; Multi-center LGE MRIs; Domain generalization
Right Ventricular Segmentation from Short- and Long-Axis MRIs via Information Transition
STACOM, 259-267, 2021
Right ventricular (RV) segmentation from MRI is a crucial step for cardiac morphology and function analysis. However, current methods for the RV segmentation tend to suffer from performance degradation at the basal and apical slices of MRI. In this work, we propose an automatic RV segmentation framework, where the information from long-axis (LA) views is utilized to assist the segmentation of short-axis (SA) views via information transition. Specifically, we employed the transformed segmentation from LA views as a prior information, to extract the ROI from SA views for better segmentation. The information transition aims to remove the surrounding ambiguous regions in the SA views."
Keywords: RV segmentation; Multi-view MRI; Information transition
Atrial Scar Quantification via Multi-Scale CNN in the Graph-Cuts Framework
Medical Image Analysis, vol. 60, 101595, 2020
LGE MRI appears to be a promising alternative for scar assessment in patients with atrial fibrillation (AF). Automating the quantification and analysis of atrial scars can be challenging due to the low image quality. In this work, we propose a fully automated method based on the graph-cuts framework, where the potentials of the graph are learned on a surface mesh of the LA using a multi-scale CNN.
Keywords: Atrial fibrillation; Left atrium; LGE MRI; Graph learning; Multi-scale CNN
Links
Professor Xiahai Zhuang Professor Julia A Schnabel Professor Vicente Grau Fudan ZMIC Lab Oxford BioMedIA Southampton DHBE group
Lei Li © 2023
Theme | Hexo Academic