Acquiring and Predicting Multidimensional Diffusion (MUDI) Data: An Open Challenge
Pizzolato M, Palombo M, Bonet-Carne E, Tax CM, Grussu F, Ianus A, Bogusz F, Pieciak T, Ning L, Larochelle H, Descoteaux M, Chamberland M, Blumberg SB, Mertzanidou T, Alexander DC, Afzali M, Aja-Fernández S, Jones DK, Westin CF, Rathi Y, Baete SH, Cordero-Grande L, Ladner T, Slator PJ, Hajnal JV, Thiran JP, Price AN, Sepehrband F, Zhang F, Hutter J (2020)
Publication Type: Book chapter / Article in edited volumes
Publication year: 2020
Publisher: Springer Science and Business Media Deutschland GmbH
Series: Mathematics and Visualization
Pages Range: 195-208
DOI: 10.1007/978-3-030-52893-5_17
Abstract
In magnetic resonance imaging (MRI), the image contrast is the result of the subtle interaction between the physicochemical properties of the imaged living tissue and the parameters used for image acquisition. By varying parameters such as the echo time (TE) and the inversion time (TI), it is possible to collect images that capture different expressions of this sophisticated interaction. Sensitization to diffusion-summarized by the b-value-constitutes yet another explorable “dimension” to modify the image contrast, which reflects the degree of dispersion of water in various directions within the tissue microstructure. The full exploration of this multidimensional acquisition parameter space offers the promise of a more comprehensive description of the living tissue but at the expense of lengthy MRI acquisitions, often unfeasible in clinical practice. The harnessing of multidimensional information passes through the use of intelligent sampling strategies for reducing the amount of images to acquire, and the design of methods for exploiting the redundancy in such information. This chapter reports the results of the MUDI challenge, comparing different strategies for predicting the acquired densely sampled multidimensional data from sub-sampled versions of it.
Authors with CRIS profile
Involved external institutions
Technical University of Denmark / Danmarks Tekniske Universitet (DTU)
Denmark (DK)
University College London (UCL)
United Kingdom (GB)
Cardiff University
United Kingdom (GB)
Champalimaud Foundation / Fundação Champalimaud
Portugal (PT)
University of Science and Technology (AGH) / Akademia Górniczo-Hutnicza
Poland (PL)
Veterans Affairs Healthcare System Boston and Harvard Medical School
United States (USA) (US)
Google Ireland Limited
Ireland (IE)
Université de Sherbrooke
Canada (CA)
Universidad de Valladolid
Spain (ES)
New York University (NYU)
United States (USA) (US)
King’s College London
United Kingdom (GB)
Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich
Switzerland (CH)
École Polytechnique Fédérale de Lausanne (EPFL)
Switzerland (CH)
University of Southern California (USC)
United States (USA) (US)
Denmark (DK)
University College London (UCL)
United Kingdom (GB)
Cardiff University
United Kingdom (GB)
Champalimaud Foundation / Fundação Champalimaud
Portugal (PT)
University of Science and Technology (AGH) / Akademia Górniczo-Hutnicza
Poland (PL)
Veterans Affairs Healthcare System Boston and Harvard Medical School
United States (USA) (US)
Google Ireland Limited
Ireland (IE)
Université de Sherbrooke
Canada (CA)
Universidad de Valladolid
Spain (ES)
New York University (NYU)
United States (USA) (US)
King’s College London
United Kingdom (GB)
Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich
Switzerland (CH)
École Polytechnique Fédérale de Lausanne (EPFL)
Switzerland (CH)
University of Southern California (USC)
United States (USA) (US)
How to cite
APA:
Pizzolato, M., Palombo, M., Bonet-Carne, E., Tax, C.M., Grussu, F., Ianus, A.,... Hutter, J. (2020). Acquiring and Predicting Multidimensional Diffusion (MUDI) Data: An Open Challenge. In (pp. 195-208). Springer Science and Business Media Deutschland GmbH.
MLA:
Pizzolato, Marco, et al. "Acquiring and Predicting Multidimensional Diffusion (MUDI) Data: An Open Challenge." Springer Science and Business Media Deutschland GmbH, 2020. 195-208.
BibTeX: Download