Dr. Zeju Li  

Post-Doctoral Researcher

Nuffield Department of Clinical Neurosciences,
University of Oxford,
John Radcliffe Hospital, Oxford, UK.

 
Email zeju.li(at)ndcn.ox.ac.uk

Zeju Li is currently a Post-Doctoral Researcher in FMRIB Analysis Group, University of Oxford, working with Prof. Saad Jbabdi. Previously, he obtained his PhD in Computing from BioMedIA Group with Prof. Ben Glocker, Imperial College London. During his PhD, he spent time in MIRACLE Group (Institute of Computing Technology) and Huawei Noah's Ark Lab (London). He got both his MSc and BSc from the Department of Electronic Engineering, Fudan University.

                             

Zeju Li is boardly interested in medical image computing, neuroimaging and machine learning. Currently, Zeju Li is working on building AI models that can 1) operate reliably and stably (e.g. interpretability, uncertainty), 2) advance medical imaging pipelines (e.g. reconstruction, segmentation) 3) and eventually enhance our understanding of brain functions (e.g. fMRI, dMRI).

Actively looking for collabrations on medical image analysis! Please get in touch for brainstorms and discussions!


Updates:
Feb, 2024
I will serve as an Area Chair for MICCAI 2024.
Jul, 2023
Two papers on Performance Assessment and Federated Learning are accepted at MICCAI 2023 Workshops.
Jun, 2023
One paper on Robust Learning is accepted at MICCAI 2023.
Jan, 2023
I start to work a Post-Doctoral Researcher in Oxford.
Dec, 2022
PhD viva passed! [Thesis]
Selected Publications (Google Scholar)

Joint Optimization of Class-Specific Training- and Test-Time Data Augmentation in Segmentation,
Zeju Li, Konstantinos Kamnitsas, Qi Dou, Chen Qin, Ben Glocker.
IEEE Transactions on Medical Imaging, 2023.

[Paper][Code]

Context Label Learning: Improving Background Class Representations in Semantic Segmentation,
Zeju Li, Konstantinos Kamnitsas, Cheng Ouyang, Chen Chen, Ben Glocker.
IEEE Transactions on Medical Imaging, 2023.

[Paper][Code]

Estimating Model Performance under Domain Shifts with Class-Specific Confidence Scores,
Zeju Li, Konstantinos Kamnitsas, Mobarakol Islam, Chen Chen, Ben Glocker.
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2022.

[Paper][Code][Dataset]

Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation,
Zeju Li, Konstantinos Kamnitsas, Ben Glocker.
IEEE Transactions on Medical Imaging, 2020.

[Paper][Code]

Encoding CT Anatomy Knowledge for Unpaired Chest X-ray Image Decomposition,
Zeju Li, Han Li, Hu Han, Gonglei Shi, Jiannan Wang, S. Kevin Zhou.
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2019.

[Paper][Code]

DeepVolume: Brain Structure and Spatial Connection-Aware Network for Brain MRI Super-Resolution,
Zeju Li, Jinhua Yu, Yuanyuan Wang, Hanzhang Zhou, Haowei Yang, Zhongwei Qiao.
IEEE Transactions on Cybernetics, 2019.

[Paper][Code]


Academic Services

Teaching Experiences

Academic Talks

MorroBay
Other Interests
  • I enjoy building beautiful things, such as photography, calligraphy and making videos.
  • This is a picture I took while traveling around Morro Bay.

Last update: Mar, 2024
Free track counters