Optimisation of quantitative brain diffusion-relaxation MRI acquisition protocols with physics-informed machine learning

• Published in: Medical image analysis Vol. 94; p. 103134
• Main Authors: Planchuelo-Gómez, Álvaro, Descoteaux, Maxime, Larochelle, Hugo, Hutter, Jana, Jones, Derek K., Tax, Chantal M.W.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.05.2024
• Subjects: Brain; Diffusion-relaxation; Machine learning; Quantitative MRI; Brain; Quantitative MRI; Diffusion-relaxation; Machine learning
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2024.103134

Diffusion-relaxation MRI aims to extract quantitative measures that characterise microstructural tissue properties such as orientation, size, and shape, but long acquisition times are typically required. This work proposes a physics-informed learning framework to extract an optimal subset of diffusion-relaxation MRI measurements for enabling shorter acquisition times, predict non-measured signals, and estimate quantitative parameters. In vivo and synthetic brain 5D-Diffusion-T1-T2∗-weighted MRI data obtained from five healthy subjects were used for training and validation, and from a sixth participant for testing. One fully data-driven and two physics-informed machine learning methods were implemented and compared to two manual selection procedures and Cramér–Rao lower bound optimisation. The physics-informed approaches could identify measurement-subsets that yielded more consistently accurate parameter estimates in simulations than other approaches, with similar signal prediction error. Five-fold shorter protocols yielded error distributions of estimated quantitative parameters with very small effect sizes compared to estimates from the full protocol. Selected subsets commonly included a denser sampling of the shortest and longest inversion time, lowest echo time, and high b-value. The proposed framework combining machine learning and MRI physics offers a promising approach to develop shorter imaging protocols without compromising the quality of parameter estimates and signal predictions. [Display omitted] •Physics-informed networks were compared to manual selection and CRLB optimisation.•Physics-informed approaches identified subsets that yielded consistently accurate estimates.•Five-fold shorter protocols yielded similar error distributions compared to the full protocol.•Short and long TI, short TE, and high b-values were more densely sampled.•Physics-informed optimisation is adaptable to different tissue models.