Abstract #0960

Acquiring and predicting MUlti-dimensional DIffusion (MUDI) data: an open challenge

Marco Pizzolato¹, Marco Palombo², Elisenda Bonet-Carne^2,3, Francesco Grussu^2,4, Andrada Ianus⁵, Fabian Bogusz⁶, Tomasz Pieciak^6,7, Lipeng Ning⁸, Stefano B. Blumberg², Thomy Mertzanidou², Daniel C. Alexander², Maryam Afzali⁹, Santiago Aja-Fernández^7,9, Derek K. Jones^9,10, Carl-Fredrik Westin⁸, Yogesh Rathi⁸, Steven H. Baete^11,12, Lucilio Cordero-Grande¹³, Thilo Ladner¹⁴, Paddy J. Slator², Daan Christiaens^13,15, Jean-Philippe Thiran^1,16, Anthony N. Price¹³, Farshid Sepehrband¹⁷, Fan Zhang⁸, and Jana Hutter¹³

¹Signal Processing Lab (LTS5), École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland, ²Department of Computer Science, Centre for Medical Image Computing, University College London, London, United Kingdom, ³BCNatal Fetal Medicine Research Center, Barcelona, Spain, ⁴Queen Square MS Centre, UCL Queen Square Institute of Neurology, Faculty of Brain Sciences, University College London, London, United Kingdom, ⁵Champalimaud Research, Champalimaud Centre for the Unknown, Lisbon, Portugal, ⁶AGH University of Science and Technology, Kraków, Poland, ⁷Laboratorio de Procesado de Imagen (LPI), Universidad de Valladolid, Valladolid, Spain, ⁸Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States, ⁹Cardiff University Brain Research Imaging Center (CUBRIC), School of Psychology, University of Cardiff, Cardiff, United Kingdom, ¹⁰Mary MacKillop Institute for Health Research, Faculty of Health Sciences, Australian Catholic University, Melbourne, Australia, ¹¹Center for Biomedical Imaging, Dept. of Radiology, New York University School of Medicine, New York, NY, United States, ¹²Center for Advanced Imaging Imaging, Innovation and Research, New York University School of Medicine, New York, NY, United States, ¹³Centre for Medical Engineering, Centre for the Developing Brain, King's College London, London, United Kingdom, ¹⁴Department of Chemistry and Applied Biosciences, ETH Zurich, Zurich, Switzerland, ¹⁵Department of Electrical Engineering (ESAT-PSI), KU Leuven, Leuven, Belgium, ¹⁶Radiology Department, Centre Hospitalier Universitaire Vaudois and University of Lausanne, Lausanne, Switzerland, ¹⁷Laboratory of Neuro Imaging (LONI), USC Stevens Neuroimaging and Informatics Institute, University of Southern California, Los Angeles, CA, United States

The variety of possible combinations of acquisition parameters is key to the versatility of MRI as a diagnostic modality. However, the full exploration of the parameter space defined by b-values, gradient directions, inversion and echo times comes at the expense of the acquisition time. We present the results of an open challenge where different methods were proposed to predict the content of a densely sampled acquisition, which explores such parameter space, from only a subset of parameter combinations. These indicate the possibility of leveraging the redundancy in the data to shorten the acquisition time while minimizing information loss.

This abstract and the presentation materials are available to members only; a login is required.

Join Here