On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types : Chronicles of the MEMENTO challenge
(2021) In NeuroImage 240.- Abstract
Diffusion MRI (dMRI) has become an invaluable tool to assess the microstructural organization of brain tissue. Depending on the specific acquisition settings, the dMRI signal encodes specific properties of the underlying diffusion process. In the last two decades, several signal representations have been proposed to fit the dMRI signal and decode such properties. Most methods, however, are tested and developed on a limited amount of data, and their applicability to other acquisition schemes remains unknown. With this work, we aimed to shed light on the generalizability of existing dMRI signal representations to different diffusion encoding parameters and brain tissue types. To this end, we organized a community challenge - named... (More)
Diffusion MRI (dMRI) has become an invaluable tool to assess the microstructural organization of brain tissue. Depending on the specific acquisition settings, the dMRI signal encodes specific properties of the underlying diffusion process. In the last two decades, several signal representations have been proposed to fit the dMRI signal and decode such properties. Most methods, however, are tested and developed on a limited amount of data, and their applicability to other acquisition schemes remains unknown. With this work, we aimed to shed light on the generalizability of existing dMRI signal representations to different diffusion encoding parameters and brain tissue types. To this end, we organized a community challenge - named MEMENTO, making available the same datasets for fair comparisons across algorithms and techniques. We considered two state-of-the-art diffusion datasets, including single-diffusion-encoding (SDE) spin-echo data from a human brain with over 3820 unique diffusion weightings (the MASSIVE dataset), and double (oscillating) diffusion encoding data (DDE/DODE) of a mouse brain including over 2520 unique data points. A subset of the data sampled in 5 different voxels was openly distributed, and the challenge participants were asked to predict the remaining part of the data. After one year, eight participant teams submitted a total of 80 signal fits. For each submission, we evaluated the mean squared error, the variance of the prediction error and the Bayesian information criteria. The received submissions predicted either multi-shell SDE data (37%) or DODE data (22%), followed by cartesian SDE data (19%) and DDE (18%). Most submissions predicted the signals measured with SDE remarkably well, with the exception of low and very strong diffusion weightings. The prediction of DDE and DODE data seemed more challenging, likely because none of the submissions explicitly accounted for diffusion time and frequency. Next to the choice of the model, decisions on fit procedure and hyperparameters play a major role in the prediction performance, highlighting the importance of optimizing and reporting such choices. This work is a community effort to highlight strength and limitations of the field at representing dMRI acquired with trending encoding schemes, gaining insights into how different models generalize to different tissue types and fiber configurations over a large range of diffusion encodings.
(Less)
- author
- organization
- publishing date
- 2021-10
- type
- Contribution to journal
- publication status
- published
- subject
- in
- NeuroImage
- volume
- 240
- article number
- 118367
- publisher
- Elsevier
- external identifiers
-
- scopus:85110174661
- pmid:34237442
- ISSN
- 1053-8119
- DOI
- 10.1016/j.neuroimage.2021.118367
- language
- English
- LU publication?
- yes
- id
- 3d9f4686-5cdd-423c-8ffc-b9f5eb692e4f
- date added to LUP
- 2021-12-22 14:52:42
- date last changed
- 2024-05-18 21:32:03
@article{3d9f4686-5cdd-423c-8ffc-b9f5eb692e4f,
abstract = {{<p>Diffusion MRI (dMRI) has become an invaluable tool to assess the microstructural organization of brain tissue. Depending on the specific acquisition settings, the dMRI signal encodes specific properties of the underlying diffusion process. In the last two decades, several signal representations have been proposed to fit the dMRI signal and decode such properties. Most methods, however, are tested and developed on a limited amount of data, and their applicability to other acquisition schemes remains unknown. With this work, we aimed to shed light on the generalizability of existing dMRI signal representations to different diffusion encoding parameters and brain tissue types. To this end, we organized a community challenge - named MEMENTO, making available the same datasets for fair comparisons across algorithms and techniques. We considered two state-of-the-art diffusion datasets, including single-diffusion-encoding (SDE) spin-echo data from a human brain with over 3820 unique diffusion weightings (the MASSIVE dataset), and double (oscillating) diffusion encoding data (DDE/DODE) of a mouse brain including over 2520 unique data points. A subset of the data sampled in 5 different voxels was openly distributed, and the challenge participants were asked to predict the remaining part of the data. After one year, eight participant teams submitted a total of 80 signal fits. For each submission, we evaluated the mean squared error, the variance of the prediction error and the Bayesian information criteria. The received submissions predicted either multi-shell SDE data (37%) or DODE data (22%), followed by cartesian SDE data (19%) and DDE (18%). Most submissions predicted the signals measured with SDE remarkably well, with the exception of low and very strong diffusion weightings. The prediction of DDE and DODE data seemed more challenging, likely because none of the submissions explicitly accounted for diffusion time and frequency. Next to the choice of the model, decisions on fit procedure and hyperparameters play a major role in the prediction performance, highlighting the importance of optimizing and reporting such choices. This work is a community effort to highlight strength and limitations of the field at representing dMRI acquired with trending encoding schemes, gaining insights into how different models generalize to different tissue types and fiber configurations over a large range of diffusion encodings.</p>}},
author = {{De Luca, Alberto and Ianus, Andrada and Leemans, Alexander and Palombo, Marco and Shemesh, Noam and Zhang, Hui and Alexander, Daniel C. and Nilsson, Markus and Froeling, Martijn and Biessels, Geert Jan and Zucchelli, Mauro and Frigo, Matteo and Albay, Enes and Sedlar, Sara and Alimi, Abib and Deslauriers-Gauthier, Samuel and Deriche, Rachid and Fick, Rutger and Afzali, Maryam and Pieciak, Tomasz and Bogusz, Fabian and Aja-Fernández, Santiago and Özarslan, Evren and Jones, Derek K. and Chen, Haoze and Jin, Mingwu and Zhang, Zhijie and Wang, Fengxiang and Nath, Vishwesh and Parvathaneni, Prasanna and Morez, Jan and Sijbers, Jan and Jeurissen, Ben and Fadnavis, Shreyas and Endres, Stefan and Rokem, Ariel and Garyfallidis, Eleftherios and Sanchez, Irina and Prchkovska, Vesna and Rodrigues, Paulo and Landman, Bennet A. and Schilling, Kurt G.}},
issn = {{1053-8119}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{NeuroImage}},
title = {{On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types : Chronicles of the MEMENTO challenge}},
url = {{http://dx.doi.org/10.1016/j.neuroimage.2021.118367}},
doi = {{10.1016/j.neuroimage.2021.118367}},
volume = {{240}},
year = {{2021}},
}