Lei Tong

Hello! My name is Lei Tong (Chinese: 童磊), and I am a Research Fellow at the Centre for Artificial Intelligence (CAI) in Data Science & Artificial Intelligence at AstraZeneca (UK), working with Dr. Chen Jin and Dr. Philip Teare. My research focuses on Large Multimodal Generative Models, Deep Causal Learning, and Biomedical Image Analysis.

I obtained my Ph.D. from University of Leicester. Additionally, I collaborate with Dr. Yinhai Wang and Dr. Adam Corrigan from Data Sciences and Quantitative Biology, Discovery Sciences, AstraZeneca. My previous research involved Deep Learning for Unbiased Representation in Cellular Microscopy Imaging.

CV / Google Scholar / Linkedin / Github

Email: lei.tongml01@gmail.com

News

May 2025: One paper accepted by ICML 2025.
Mar 2024: Our paper CLANet has been accepted for publication in Medical Image Analysis. For more details, please read the paper.
Jun 2023: Our latest research work "CLANet: A Comprehensive Framework for Cross-Batch Cell Line Identification Using Brightfield Images" is available on arxiv and the code and the dataset are accessible on github.
Jun 2022: It is a great honor for me to present our work "Transforming cell line authentication with a novel image-based AI method" on the seminar "Science for the Curious" in AstraZeneca.
Jun 2022: Two-weeks internship in Astrazenca and work with UKCCB group.
May 2022: 1 paper has been accepted by Scientific Reports.
Apr 2022: Our work "Depression detection on Twitter" is described in the news: Independent, Yahoo, Metro, .
Mar 2022: 1 paper has been accepted by IEEE trans. on Affective Computing and 1 co-authored paper has appeared on IEEE Trans. on Neural Networks and Learning Systems.
Jan 2022: We have finished the extensive revision on "Cost-sensitive Boosting Pruning Trees for depression detection on Twitter" and opensouced the github repo.
Jun 2021: Two co-authored paper has been accepted by IEEE Trans. on Medical Image and Learning Systems and Science of The Total Environment respectively.

Research

My research is focusing on computer vision and machine learning, especially in biomedical image analysis, domain generalization and ensemble learning.

	Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation Lei Tong, Zhihua Liu, Chaochao Lu, Dino Oglic, Tom Diethe, Philip Teare, Sotirios A. Tsaftaris, Chen Jin Preprint , 2025 arXiv / Project Page We present Causal-Adapter, a modular framework that adapts frozen text-to-image diffusion for counterfactual generation. The method enables causal interventions, consistently propagates their effects to dependent attributes and preserves identity.
	Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation Zhihua Liu, Amrutha Saseendran, Lei Tong, Xilin He, Fariba Yousefi, Nikolay Burlutskiy, Dino Oglic, Tom Diethe, Philip Teare, Huiyu Zhou, Chen Jin ICML International Conference on Machine Learning, 2025 We introduce Segment Anyword, a training-free visual prompt learning framework with test-time inversed adaption for open-set language grounded segmentation, where visual prompts are simultaneously regularized by linguistic structual information.
	CLANet: A Comprehensive Framework for Cross-Batch Cell Line Identification Using Brightfield Images Lei Tong, Adam Corrigan, Navin Rathna Kumar, Kerry Hallbrook, Jonathan Orme, Yinhai Wang, Huiyu Zhou Medical Image Analysis, 2024 code and dataset We introduce an innovative approach aimed at minimizing bias across varying bio-batch images by identifying and addressing batch effects in three distinct categories.
	An automated cell line authentication method for AstraZeneca global cell bank using deep neural networks on brightfield images Lei Tong, Adam Corrigan, Navin Rathna Kumar, Kerry Hallbrook, Jonathan Orme, Yinhai Wang, Huiyu Zhou Scientific Reports, 2022 code We introduce a multi-task framework for automated cell line authentication using deep neural networks on brightfield images.
	Cost-sensitive Boosting Pruning Trees for depression detection on Twitter Lei Tong, Zhihua Liu, Zheheng Jiang, Feixiang Zhou, Long Chen, Jialin Lyu, Xiangrong Zhang, Qianni Zhang, Abdul Sadka, Yinhai Wang, Ling Li, Huiyu Zhou IEEE Trans. on Affective Computing, 2022 code / arXiv A novel classifier, namely, Cost-sensitive Boosting Pruning Trees (CBPT), which demonstrates a strong classification ability on two publicly accessible Twitter depression detection datasets..
	Towards advancing the earthquake forecasting by machine learning of satellite data Pan Xiong, Lei Tong, Kun Zhang, Xuhui Shen, Roberto Battiston, Dimitar Ouzounov, Roberto Iuppa, Danny Crookes, Cheng Long, Huiyu Zhou Science of The Total Environment, 2021 code An AdaBoost-based ensemble framework is proposed to forecast earthquake. Our results support a Lithosphere-Atmosphere-Ionosphere Coupling during earthquakes.
	CANet: Context Aware Network for Brain Glioma Segmentation Zhihua Liu, Lei Tong, Long Chen, Feixiang Zhou, Zheheng Jiang, Qianni Zhang, Yinhai Wang, Caifeng Shan, Ling Li, Huiyu Zhou IEEE Trans. on Medical Imaging, 2021 code / arXiv A novel approach named Context-Aware Network (CANet) for brain glioma segmentation.
	Deep Learning Based Brain Tumor Segmentation: A Survey Zhihua Liu, Lei Tong, Zheheng Jiang, Long Chen, Feixiang Zhou, Qianni Zhang, Xiangrong Zhang, Yaochu Jin, Huiyu Zhou arXiv, 2020 code / arXiv Considering stateof-the-art technologies and their performance, the purpose of this paper is to provide a comprehensive survey of recently developed deep learning based brain tumor segmentation techniques.

Teaching Assistant

2020-2023
CO7214 Service-Oriented Architecture
CO7095 Software Measurement and Quality Assurance
CO4105 Advanced C++ Programming
CO3002 Analysis and Design of Algorithms
CO2102 Database and Domain Modelling
CO1105 Introduction to Object Oriented Programming