Published in ASMUS - MICCAI 2021 Workshop, 2021
This paper focuses on intraoperative ultrasound segmentation techniques.
Recommended citation: Chalcroft, L.F., et al. (2021). Development and evaluation of intraoperative ultrasound segmentation with negative image frames and multiple observer labels. In ASMUS - MICCAI 2021 Workshop. https://arxiv.org/pdf/2108.04114
Published in Medical Imaging meets NeurIPS 2023 Workshop, 2023
This paper introduces LKA for efficient and robust brain lesion segmentation.
Recommended citation: Chalcroft, L.F., et al. (2023). LKA: Large-kernel Attention for Efficient and Robust Brain Lesion Segmentation. In Medical Imaging meets NeurIPS 2023 Workshop. https://arxiv.org/pdf/2308.07251
Published in Journal of Machine Learning for Biomedical Imaging (MELBA), 2025
This paper explores the use of synthetic data for robust stroke segmentation.
Recommended citation: Chalcroft, L., Pappas, I., Price, C.J., & Ashburner, J. (2025). Synthetic Data for Robust Stroke Segmentation. Journal of Machine Learning for Biomedical Imaging (MELBA), 2025:014. https://www.melba-journal.org/papers/2025:014.html
Published in Nature Communications, 2025
This paper presents DeepISLES, a clinically validated ischemic stroke segmentation model developed from the ISLES’22 challenge.
Recommended citation: de la Rosa, E., Reyes, M., Liew, S.L., et al. (including Chalcroft, L.) (2025). DeepISLES: a clinically validated ischemic stroke segmentation model from the ISLES'22 challenge. Nature Communications, 16, 7357. https://www.nature.com/articles/s41467-025-62373-x
Published in Medical Image Computing and Computer Assisted Intervention – MICCAI 2025, 2025
This paper introduces physics-constrained approaches to generate synthetic quantitative MRI images for robust stroke lesion segmentation across heterogeneous domains.
Recommended citation: Chalcroft, L., Crinion, J., Price, C.J., & Ashburner, J. (2025). Domain-Agnostic Stroke Lesion Segmentation Using Physics-Constrained Synthetic Data. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2025 (pp. 163-173). Springer. https://link.springer.com/chapter/10.1007/978-3-032-04965-0_16
Published in Simulation and Synthesis in Medical Imaging (SASHIMI 2025) - MICCAI Workshop, 2025
This paper presents a sequence-invariant self-supervised framework leveraging quantitative MRI for learning unified 3D representations across different MRI contrasts.
Recommended citation: Chalcroft, L., Crinion, J., Price, C.J., & Ashburner, J. (2025). Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning. In Simulation and Synthesis in Medical Imaging (pp. 63-74). Springer. https://link.springer.com/chapter/10.1007/978-3-032-05573-6_7