Interest in diffusion MRI has exploded over the last two decades! This non-invasive technique provides unique measurements that are sensitive to the microstructure of living tissue. As microscopic tissue alterations are often the earliest signs of disease or regeneration, the variety of clinical applications is expanding rapidly and includes detection of lesions and damaged tissue, grading of cancerous tumors, prognosis of functional impairment and neurosurgical planning. Moreover, fiber tractography gives fundamental new insights into neuroanatomy by enabling us to map the connections between the different regions of the brain.
Computational techniques are key to the continued success and development of diffusion MRI and to its widespread transfer to the clinic. New processing methods are essential for addressing challenges at each stage of the diffusion pipeline: data acquisition, image reconstruction, biophysical modelling, model fitting, tissue microstructure mapping, fiber tracking, connectivity mapping, group studies, etc. In this variety of tasks, optimization methods, statistical inference, methods including machine learning and deep learning, visualization strategies and analysis are examples of current research subjects in the field.
This full-day MICCAI 2019 workshop, now in the twelfth edition, will give a snapshot of the current state of the art. Particular focus will be given to the opportunities that novel approaches such as machine learning techniques provide for computational diffusion MRI inside and outside the brain.