Publications from the Turing AI Fellowship programme at the University of Oxford
Publications
J Strong, H Rogers, E Sun, AS Todsen, J Ede, C Lumley, N Yeung, H Higham, JA Noble, Human-AI Collaboration in Healthcare: A Scoping Review, npj Digital Medicine 2026.
J Strong, P Saha, Y Ibrahim, C Ouyang, A Noble, Identity-Free Deferral for Unseen Experts, ICLR 2026.
H Lamdouar, AF Wang, X Guo, Q Men, J Lander, AT Papageorghiou, JA Noble, FOCUS: Towards Fetal Obstetric Corrective Ultrasound Guidance, MICCAI 2026.
A. Le et al, US-Bench: benchmarking large vision-language models for ultrasound understanding, ICLR26.
Liang Z, Guo X, Xu W, Ibrahim Y, Voets N, Pretorius PM; Alzheimer’s Disease Neuroimaging Initiative; Noble JA, Kamnitsas K. IterMask3D: Unsupervised anomaly detection and segmentation with test-time iterative mask refinement in 3D brain MRI. Med Image Anal. 2026 Jan;107(Pt A):103763. doi: 10.1016/j.media.2025.103763. Epub 2025 Aug 28. PMID: 40945172.
C Peng, Exploring Neural Collapse in multi-label skewed federated learning, ECCV 2026.
A Le, C Peng, Y Liu and JA Noble, POUR: A Provable Optimal Method for Unlearning Representations via Neural Collapse, CVPR 2026.
A Le, C Peng, H Guo, JA Noble, DECAF: Declustering for Adaptive Representational Unlearning, ICML 2026 Continual Adaptation at Scale: Towards Sustainable AI Workshop.
Pramit Saha, Divyanshu Mishra, Felix Wagner, Konstantinos Kamnitsas, J. Alison Noble, FedExIT - missing class-agnostic semi-supervised federated learning with extreme imbalance tackling scheme Information Fusion, Volume 130, June 2026, 104080 https://doi.org/10.1016/j.inffus.2025.104080
J Strong, Q Men, JA Noble, Trustworthy and Practical AI for Healthcare: A guided deferral system with Large Language Models, The 39th AAAI Conference on Artificial Intelligence (AAAI-25), 2025.
X Guo, M Alsharid, H Zhao, Y Wang, J Lander, AT Papageorghiou, JA Noble, Sonomate: Visually grounded language model for fetal ultrasound understanding and human interaction, Nature Biomedical Engineering, accepted July 2025.
Qianhui Men, He Zhao, Lior Drukker, Aris T. Papageorghiou, J. Alison Noble, ScanAhead: Simplifying standard plane acquisition of fetal head ultrasound, Medical Image Analysis, Volume 104, 2025, 103614, ISSN 1361-8415, https://doi.org/10.1016/j.media.2025.103614
M AlSharid, X Gui, Q Men P Saha, D Mishra, R Ahuja, C Ouyang, JA Noble, On the public dissemination and open sourcing of ultrasound resources, datasets and deep learning models, npj Digital Medicine, 2025.
A Nicolson, E Bradburn, Y Gal, AS Papageorghiou, JA Noble, The Human Factor in explainable artificial intelligence: clinician variability in trust, reliance and performance, npj Digital Medicine (accepted 2025).
Jiazhen Pan, Che Liu, Junde Wu, Fenglin Liu, Jiayuan Zhu, Hongwei Bran Li, Chen Chen, Cheng Ouyang, Daniel Rueckert, MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning. In: Gee, J.C., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2025. MICCAI 2025. Lecture Notes in Computer Science, vol 15966. Springer, Cham. https://doi.org/10.1007/978-3-032-04981-0_32
J Zhu, J Wu, C Ouyang, L Kamnitsas, JA Noble, SPA: Efficient User-Preference Alignment against Uncertainty in Medical Image Segmentation, ICCV25
P Saha, D Mishra, N Hernandez-Cruz, O Patey, AT. Papageorghiou, YM. Asano, and JA Noble. 2025. Self-supervised Normality Learning and Divergence Vector-Guided Model Merging for Zero-Shot Congenital Heart Disease Detection in Fetal Ultrasound Videos. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2025: 28th International Conference, Daejeon, South Korea, September 23–27, 2025, Proceedings, Part VII. Springer-Verlag, Berlin, Heidelberg, 560–571. https://doi.org/10.1007/978-3-032-04981-0_53
P Saha, D, Mishra, F Wagner, K Kamnitsas, JA Noble, FedPIA - Permuting and Integrating Adapters Leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning, AAAI-2025, https://doi.org/10.1609/aaai.v39i19.34228
F Wagner, P Saha, H Anthony. JA Noble, K Kamnitsas, DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging, NeurIPS 2025
Saha, P., Mishra, D., Wagner, F., Kamnitsas, K., & Noble, J. A. (2025). Incongruent Multimodal Federated Learning for Medical Vision and Language-based Multi-label Disease Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(27), 28331-28339. https://doi.org/10.1609/aaai.v39i27.35054
F. Wagner, W Xu, P Saha, Z Liang, D Whitehouse, D Menon, V Newcombe, N Voets, JA Noble, K Kamnitsas, "Feasibility of Federated Learning from Client Databases with Different Brain Diseases and MRI Modalities," 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA, 2025, pp. 357-367, doi: 10.1109/WACV61041.2025.00045.
Pramit Saha, Felix Wagner, Divyanshu Mishra, Can Peng, Anshul Thakur, David Clifton, Konstantinos Kamnitsas, J. Alison Noble, "F3OCUS - Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics," 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2025, pp. 20006-20017, doi: 10.1109/CVPR52734.2025.01863.
J Strong, Q Men, A Noble, Towards Human-AI Collaboration in Healthcare: Guided Deferral Systems with Large Language Models. ICML 2024 Workshop on LLMs and Cognition. https://openreview.net/forum?id=4c5rg9y4me
Hernandez-Cruz N, Saha P, Sarker MMK, Noble JA. Review of Federated Learning and Machine Learning-Based Methods for Medical Image Analysis. Big Data and Cognitive Computing. 2024; 8(9):99. https://doi.org/10.3390/bdcc8090099
X Guo, Q Men, JA Noble, (2024). MMSummary: Multimodal Summary Generation for Fetal Ultrasound Video. In: Linguraru, M.G., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. MICCAI 2024. Lecture Notes in Computer Science, vol 15004. Springer, Cham. https://doi.org/10.1007/978-3-031-72083-3_63
Men, Qianhui and Guo, Xianoqing and Papagerghiou, Aris T. and Noble, J. Alison, Pose-GuidedNet: Automatic Scanning Guidance for Fetal Head Ultrasound from Pose Etimation, MICCAI 2024, pages 700-710 https://doi.org/10.1007/978-3-031-72083-3_65
A Nicolson, Y Gal. A Noble, TextCAVs: Debugging vision models using text, iMIMIC24 (MICCAI Workshop), 2024.
Liang, Z., Guo, X., Noble, J. A., & Kamnitsas, K. (2024, October). Itermask 2: Iterative unsupervised anomaly segmentation via spatial and frequency masking for brain lesions in mri. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 339-348). Cham: Springer Nature Switzerland.
Saha, P., Mishra, D., Noble, J.A. (2023). Rethinking Semi-Supervised Federated Learning: How to Co-train Fully-Labeled and Fully-Unlabeled Client Imaging Data. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14221. Springer, Cham. https://doi.org/10.1007/978-3-031-43895-0_39