About this Research Topic
Artificial intelligence is revolutionizing medical imaging. Machine learning algorithms have met or exceeded human performance in tasks related to acquisition, analysis, and interpretation of images, enabling improved diagnosis, prognosis, and monitoring of disease. Diffusion MRI is widely used in the brain and can provide new insights into neurological conditions such as Alzheimer’s, other dementias, multiple sclerosis, and cancer, ultimately guiding clinical decision making and hence improving patient outcomes.
The application of AI and machine learning to diffusion MRI brings unique challenges: datasets are
large, ground truth data is not typically available, and many algorithms are not readily interpretable. This
Research Topic will showcase how cutting-edge research at the interface between AI and diffusion MRI can
address these challenges, from early-stage studies through to methods with immediate clinical applicability
to neurological diseases.
We seek scientific papers (original research, reviews, perspectives) focused on AI and machine learning applied to diffusion MRI in neuroimaging. We welcome submissions from across, but not limited to, the following areas:
• reconstruction
• segmentation
• microstructure imaging
• model fitting
• supervised learning
• unsupervised learning
• semi-supervised learning
• deep learning
• interpretability
The application of AI and machine learning to diffusion MRI brings unique challenges: datasets are
large, ground truth data is not typically available, and many algorithms are not readily interpretable. This
Research Topic will showcase how cutting-edge research at the interface between AI and diffusion MRI can
address these challenges, from early-stage studies through to methods with immediate clinical applicability
to neurological diseases.
We seek scientific papers (original research, reviews, perspectives) focused on AI and machine learning applied to diffusion MRI in neuroimaging. We welcome submissions from across, but not limited to, the following areas:
• reconstruction
• segmentation
• microstructure imaging
• model fitting
• supervised learning
• unsupervised learning
• semi-supervised learning
• deep learning
• interpretability
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
