Daniel Rueckert

It is shown that predictions on a patient's unseen future data can change significantly if a model observed that same patient's anonymised historical data during training, a phenomenon known as memorisation bias, which exists across diverse data modalities and model architectures, and over prolonged time spans.

Clinical histories are fundamentally irregular and multimodal, yet foundation models have treated them as static or uniformly discrete—until a generative variational transformer trained on 559 million events unified continuous-time forecasting, multi-modal health records, and counterfactual intervention simulation.

CMRVision outperforms existing models in cardiac MRI analysis, achieving remarkable segmentation accuracy and setting a new benchmark for multi-task performance in this domain.

MR-JEPA achieves a remarkable 21-27% reduction in mean absolute error on key cardiac strain tasks compared to existing models, showcasing the power of unified video encoding in medical imaging.

Jointly modeling aleatoric and epistemic uncertainties can dramatically enhance prediction reliability in high-dimensional outputs, outperforming traditional methods.

Identity preservation in counterfactual retinal images varies significantly across editing methods, with paired-training emerging as the most reliable approach.

Achieving high-quality MRI reconstructions at unprecedented undersampling rates by disentangling dynamic contrast and anatomy could revolutionize clinical imaging practices.

Achieving up to 99% of the theoretical maximum speed-up in looped language models could revolutionize inference efficiency in AI applications.

Detectability of findings in 3D CT scans hinges more on physical characteristics than model architecture, revealing a critical bottleneck in diagnostic performance.

PRIME-SVR achieves unprecedented reconstruction quality in fetal brain imaging, enabling the first isotropic T2 maps at previously inaccessible echo times.

Jointly estimating the B0 field and distortion-free images directly from k-space data leads to unprecedented improvements in MRI accuracy and detail fidelity, especially in challenging high b-value scenarios.

Current LLMs falter in delivering reliable medical assistance, exposing a critical gap in their ability to coordinate knowledge, communication, and EHR interactions.