Link Search Menu Expand Document

Journal papers

  • Epstein SC, Bray TJP, Hall-Craggs MA, Zhang H (2022), Choice of training label matters: how to best use deep learning for quantitative MRI parameter estimation, arXiv:2205.05587, under review.

    A 2 minute summary of this work is under construction.

  • Epstein SC, Bray TJP, Hall-Craggs MA, Zhang H (2021), Task-driven assessment of experimental designs in diffusion MRI: A computational framework, PLOS ONE 16(10): e0258442.

    See here for a 2 minute summary of this work.

  • Parker CS, Schroder A, Epstein SC, Cole J, Alexander DC, Zhang H (2023), Rician likelihood loss for quantitative MRI using self-supervised deep learning, arXiv:2307.07072, under review.

Conference proceedings

  • Guerreri M, Epstein SC, Azadbakht H, Zhang H (2023), Resolving quantitative MRI model degeneracy with machine learning via training data distribution optimisation (2023), 28th Biennial Information Processing in Medical Imaging (IPMI)

  • Lim JP, Blumberg SB, Narayan N, Epstein SC, Alexander DC, Palombo M, Slator PJ (2022) Fitting a directional microstructure model to diffusion-relaxation MRI data with self-supervised machine learning, COmputational Diffusion MRI - 13th International Workshop

  • Guerreri M, Blumberg SB, Narayan N, Epstein SC, Alexander DC, Palombo M, Slator PJ (2022) Fitting a directional microstructure model to diffusion-relaxation MRI data with self-supervised machine learning, COmputational Diffusion MRI - 13th International Workshop

Conference abstracts

  • Epstein SC, Bray TJP, Hall-Craggs MA, Zhang H. (2023), Do deep learning-based qMRI parameter estimators improve clinical performance? Presented at: 2023 ISMRM & SMRT Annual Meeting & Exhibition.

  • Guerreri M, Epstein SC, Azadbakht H, Zhang H. (2023), Can machine learning resolve model degeneracy in tissue microstructure estimation? Presented at: 2023 ISMRM & SMRT Annual Meeting & Exhibition.

  • Epstein SC, Bray TJP, Hall-Craggs MA, Zhang H. (2022), Quantitative MRI parameter estimation with supervised deep learning: MLE-derived labels outperform groundtruth labels. Presented at: 2022 ISMRM & SMRT Annual Meeting & Exhibition.

  • Epstein SC, Bray TJP, Hall-Craggs MA, Zhang H. (2021), Towards a computational framework for task-driven experimental design. Presented at: 2021 ISMRM & SMRT Annual Meeting & Exhibition.

  • Epstein SC, Bray, TJP, Hall-Craggs, MA, Zhang H. (2020), Variability from complexity: assessing IVIM acquisition schemes through parameter estimation uncertainty. Presented at: 2020 ISMRM & SMRT Annual Meeting & Exhibition.