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: [email protected]

My research focuses on computer vision and machine learning, particularly in biomedical applications, with specific interests in vision-language models, causal representation learning, and batch effect correction.

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.

We frame biological batch mitigation as a Domain Generalization problem and propose Adversarial Batch Representation Augmentation (ABRA). ABRA explicitly models batch-wise statistical fluctuations by parameterizing feature statistics as structured uncertainties.

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.

We introduce an innovative approach aimed at minimizing bias across varying bio-batch images by identifying and addressing batch effects in three distinct categories.

We introduce a multi-task framework for automated cell line authentication using deep neural networks on brightfield images.

A novel classifier, namely, Cost-sensitive Boosting Pruning Trees (CBPT), which demonstrates a strong classification ability on two publicly accessible Twitter depression detection datasets..

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.

A novel approach named Context-Aware Network (CANet) for brain glioma segmentation.

© Lei Tong | Last updated: May 2025