Lei's Research
Lei Li
Biomedical Image Analysis
Department of Engineering Science, University of Oxford
Overview
Lei Li
2023-04-15 17:41:15

Biography

Lei Li is a Postdoctoral Research Assistant at the Institute of Biomedical Engineering, University of Oxford. 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 artificial intelligence based medical image analysis for healthcare. Specifically, she is focusing on developing novel computational algorithms for cardiac image computing, multi-modality image computing, and cardiac digital twins. 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 MedIA and TMI. She is a Board member of Women in MICCAI (WiM) and Editorial Board Member of the Journal of Medical Artificial Intelligence. She has been co-organizer of four MICCAI challenge events, including LAScarQS 2022, MyoPS 2020, MS-CMRSeg 2019, and MM-WHS 2017. She is a reviewer for many journals and conferences, including MedIA, IEEE TPAMI, IEEE TMI, IEEE TBME, Neural Networks, Neurocomputing, ISBI, IPMI, MIDL, and MICCAI, and obtained IEEE TMI Distinguished Reviewer (2020-2022).

I am on the academic job market for faculty positions in AI/ML/MIC for healthcare! Please feel free to reach out if you have potential job opportunities. CV

Research/Education Experience

  • 08/2021-now   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)
  • 12/2019-03/2021   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)

Talks/Posters

  • 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
  • 17/06/2022   Invited posters at SmartHeart Conference 2022.
  • 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

Academic Services

Selected Work

Deep Computational Model for the Inference of Ventricular Activation Properties
STACOM, 369-380, 2023
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 inference of ventricular activation properties, i.e., conduction velocities and root nodes.
Keywords: Digital twin; Deep computational models; Ventricular activation properties; ECG simulation
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
Lei Li © 2023
Theme | Hexo Academic