5 papers
Tokenizer Generator Coupling in Medical Image Generation
Liam Chalcroft
Latent medical image generators usually treat the tokenizer as fixed preprocessing. We test whether this separation is valid in a controlled ChestMNIST study at 64x64, crossing dis…
GAZE: Grounded Agentic Zero-shot Evaluation with Viewer-Level Tools and Literature Retrieval on Rare Brain MRI
Duaa Alim, Mogtaba Alim, Liam Chalcroft
Vision-language models (VLMs) read an image and produce text in a single forward pass, whereas radiologists typically inspect an image several times and consult the literature befo…
Synthetic Data for Robust Stroke Segmentation
Liam Chalcroft, Ioannis Pappas, Cathy J. Price +1
Current deep learning-based approaches to lesion segmentation in neuroimaging often depend on high-resolution images and extensive annotated data, limiting clinical applicability.…
Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning
Liam Chalcroft, Jenny Crinion, Cathy J. Price +1
Self-supervised deep learning has accelerated 2D natural image analysis but remains difficult to translate into 3D MRI, where data are scarce and pre-trained 2D backbones cannot ca…
Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data
Liam Chalcroft, Jenny Crinion, Cathy J. Price +1
Segmenting stroke lesions in MRI is challenging due to diverse acquisition protocols that limit model generalisability. In this work, we introduce two physics-constrained approache…