Dr Chen Chen
School of Computer Science
Lecturer in Computer Vision
+44 114 215 8560
Full contact details
School of Computer Science
Regent Court (DCS)
211 Portobello
Sheffield
S1 4DP
- Profile
-
Dr Chen (Cherise) Chen obtained her MSc and Ph.D. degree in Advanced Computing from Imperial College London, in 2016 and 2022, respectively. From 2022, she worked as a research associate at Imperial College London. During the time at Imperial, she worked closely with Prof. Daniel Rueckert and Dr. Wenjia Bai, on numerous projects with cardiac imaging. She was also a research scientist at HeartFlow. After that, she joined Oxford BioMedIA group, University of Oxford in 2023, working closely with Prof. Vicente Grau. She has engaged in a variety of projects that apply artificial intelligence to cardiac, brain, and prostate imaging.
- Research interests
-
Dr. Chen's research primarily revolves around the intersection of artificial intelligence (AI) and healthcare. Her focus is particularly strong in the domains of medical multi-modal data analysis (e.g, image, signal, text) with machine learning. Her work aims to develop and validate robust, data-efficient, and reliable machine learning algorithms that can enhance the scalability of AI-driven medical data analysis in practical applications.
Please visit her personal website for more information.
- Publications
-
Show: Featured publications All publications
Featured publications
Journal articles
- Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation. IEEE Transactions on Medical Imaging, 42(4), 1095-1106.
- Enhancing MR image segmentation with realistic adversarial data augmentation. Medical Image Analysis, 82, 102597-102597.
- Deep Learning for Cardiac Image Segmentation: A Review. Frontiers in Cardiovascular Medicine, 7.
Preprints
All publications
Books
- Data Augmentation, Labelling, and Imperfections. Springer Nature Switzerland.
Journal articles
- Multi-Center Fetal Brain Tissue Annotation (FeTA) Challenge 2022 Results. IEEE Transactions on Medical Imaging, 1-1.
- Synthetic optical coherence tomography angiographs for detailed retinal vessel segmentation without human annotations. IEEE Transactions on Medical Imaging, 1-1.
- Context Label Learning: Improving Background Class Representations in Semantic Segmentation. IEEE Transactions on Medical Imaging, 42(6), 1885-1896.
- Uncertainty aware training to improve deep learning model calibration for classification of cardiac MR images. Medical Image Analysis, 88, 102861-102861.
- Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation. IEEE Transactions on Medical Imaging, 42(4), 1095-1106.
- Generative myocardial motion tracking via latent space exploration with biomechanics-informed prior. Medical Image Analysis, 83, 102682-102682.
- Enhancing MR image segmentation with realistic adversarial data augmentation. Medical Image Analysis, 82, 102597-102597.
- Cardiac segmentation on late gadolinium enhancement MRI: A benchmark study from multi-sequence cardiac MR segmentation challenge. Medical Image Analysis, 81, 102528-102528.
- Self-Supervised Learning for Few-Shot Medical Image Segmentation. IEEE Transactions on Medical Imaging, 41(7), 1837-1848.
- A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging. Medical Image Analysis, 67, 101832-101832.
- Contrast CT classification of asymptomatic and symptomatic carotids in stroke and transient ischaemic attack with deep learning and interpretability. European Heart Journal, 41(Supplement_2).
- Automatic Cardiothoracic Ratio Calculation With Deep Learning. IEEE Access, 7, 37749-37756.
- Improving the Generalizability of Convolutional Neural Network-Based Segmentation on CMR Images. Frontiers in Cardiovascular Medicine, 7.
- Deep Learning for Cardiac Image Segmentation: A Review. Frontiers in Cardiovascular Medicine, 7.
Chapters
- Whole Heart 3D+T Representation Learning Through Sparse 2D Cardiac MR Images, Lecture Notes in Computer Science (pp. 359-369). Springer Nature Switzerland
Conference proceedings papers
- Embedding Gradient-Based Optimization in Image Registration Networks (pp 56-65)
- Estimating Model Performance Under Domain Shifts with Class-Specific Confidence Scores (pp 693-703)
- MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation (pp 151-161)
- Improved Post-hoc Probability Calibration for Out-of-Domain MRI Segmentation (pp 59-69)
- Uncertainty-Aware Training for Cardiac Resynchronisation Therapy Response Prediction (pp 189-198)
- Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation (pp 14-24)
- Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation (pp 149-159)
- Self-supervision with Superpixels: Training Few-Shot Medical Image Segmentation Without Annotation (pp 762-780)
- Biomechanics-Informed Neural Networks for Myocardial Motion Tracking in MRI (pp 296-306)
- Realistic Adversarial Data Augmentation for MR Image Segmentation (pp 667-677)
- Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction (pp 284-293)
- Deep Generative Model-Based Quality Control for Cardiac MRI Segmentation (pp 88-97)
- Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation (pp 209-219)
- Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction (pp 541-549)
- Learning Shape Priors for Robust Cardiac MR Segmentation from Multi-view Images (pp 523-531)
- Multi-task Learning for Left Atrial Segmentation on GE-MRI (pp 292-301)
Preprints
- Large Language Model-informed ECG Dual Attention Network for Heart Failure Risk Prediction.
- Multi-Center Fetal Brain Tissue Annotation (FeTA) Challenge 2022 Results.
- M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization.
- Pay Attention to the Atlas: Atlas-Guided Test-Time Adaptation Method for Robust 3D Medical Image Segmentation.
- MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation.
- Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation.
- Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation.
- Realistic Adversarial Data Augmentation for MR Image Segmentation.
- Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge.
- Deep learning for cardiac image segmentation: A review.
- Unsupervised Multi-modal Style Transfer for Cardiac MR Segmentation.
- Learning Shape Priors for Robust Cardiac MR Segmentation from Multi-view Images.
- Self-Supervised Learning for Cardiac MR Image Segmentation by Anatomical Position Prediction.
- Improving the generalizability of convolutional neural network-based segmentation on CMR images.
- Multi-Task Learning for Left Atrial Segmentation on GE-MRI.
- Grants
-
Research Grants
- Advancing Cardiac Care through Multi-Modal Data Integration for Precise Scar Mapping, Royal Society, 10/2024 - 09/2025, £19,211, as PI
- Professional activities and memberships
-
Professional activities and memberships
- Associate Editor for Journal of Visual Communication and Image Representation
- Lead organiser of the 3rd MICCAI Workshop on Data Augmentation, Labeling, and Imperfections (DALI), MICCAI 2023
- Co-organiser of CMRxMotion challenge in the STACOM 2022 workshop
- Member of RISE-MICCAI
- Guest lecturer in GirlsWhoML series