TY - JOUR
T1 - Multi-Coil MRI Reconstruction Challenge—Assessing Brain MRI Reconstruction Models and Their Generalizability to Varying Coil Configurations
AU - Beauferris, Youssef
AU - Teuwen, Jonas
AU - Karkalousos, Dimitrios
AU - Moriakov, Nikita
AU - Caan, Matthan
AU - Yiasemis, George
AU - Rodrigues, L. via
AU - Lopes, Alexandre
AU - Pedrini, Helio
AU - Rittner, Letícia
AU - Dannecker, Maik
AU - Studenyak, Viktor
AU - Gröger, Fabian
AU - Vyas, Devendra
AU - Faghih-Roohi, Shahrooz
AU - Kumar Jethi, Amrit
AU - Chandra Raju, Jaya
AU - Sivaprakasam, Mohanasankar
AU - Lasby, Mike
AU - Nogovitsyn, Nikita
AU - Loos, Wallace
AU - Frayne, Richard
AU - Souza, Roberto
N1 - Funding Information: RF thanks the Canadian Institutes for Health Research (CIHR, FDN-143298) for supporting the Calgary Normative Study and acquiring the raw datasets. RF and RS thank the Natural Sciences and Engineering Research Council (NSERC - RGPIN/02858-2021 and RGPIN-2021-02867) for providing ongoing operating support for this project. We also acknowledge the infrastructure funding provided by the Canada Foundation of Innovation (CFI). The organizers of the challenge also acknowledge Nvidia for providing a Titan V Graphics Processing Unit and Amazon Web Services for providing computational infrastructure that was used by some of the teams to develop their models. DK and MC were supported by the STAIRS project under the Top Consortium for Knowledge and Innovation-Public, Private Partnership (TKI-PPP) program, co-funded by the PPP Allowance made available by Health Holland, Top Sector Life Sciences & Health. HP thanks the National Council for Scientific and Technological Development (CNPq #309330/2018-1) for the research support grant. LRi also thank the National Council for Scientific and Technological Development (CNPq #313598/2020-7) and São Paulo Research Foundation (FAPESP #2019/21964-4) for the support. Publisher Copyright: Copyright © 2022 Beauferris, Teuwen, Karkalousos, Moriakov, Caan, Yiasemis, Rodrigues, Lopes, Pedrini, Rittner, Dannecker, Studenyak, Gröger, Vyas, Faghih-Roohi, Kumar Jethi, Chandra Raju, Sivaprakasam, Lasby, Nogovitsyn, Loos, Frayne and Souza.
PY - 2022/7/6
Y1 - 2022/7/6
N2 - Deep-learning-based brain magnetic resonance imaging (MRI) reconstruction methods have the potential to accelerate the MRI acquisition process. Nevertheless, the scientific community lacks appropriate benchmarks to assess the MRI reconstruction quality of high-resolution brain images, and evaluate how these proposed algorithms will behave in the presence of small, but expected data distribution shifts. The multi-coil MRI (MC-MRI) reconstruction challenge provides a benchmark that aims at addressing these issues, using a large dataset of high-resolution, three-dimensional, T1-weighted MRI scans. The challenge has two primary goals: (1) to compare different MRI reconstruction models on this dataset and (2) to assess the generalizability of these models to data acquired with a different number of receiver coils. In this paper, we describe the challenge experimental design and summarize the results of a set of baseline and state-of-the-art brain MRI reconstruction models. We provide relevant comparative information on the current MRI reconstruction state-of-the-art and highlight the challenges of obtaining generalizable models that are required prior to broader clinical adoption. The MC-MRI benchmark data, evaluation code, and current challenge leaderboard are publicly available. They provide an objective performance assessment for future developments in the field of brain MRI reconstruction.
AB - Deep-learning-based brain magnetic resonance imaging (MRI) reconstruction methods have the potential to accelerate the MRI acquisition process. Nevertheless, the scientific community lacks appropriate benchmarks to assess the MRI reconstruction quality of high-resolution brain images, and evaluate how these proposed algorithms will behave in the presence of small, but expected data distribution shifts. The multi-coil MRI (MC-MRI) reconstruction challenge provides a benchmark that aims at addressing these issues, using a large dataset of high-resolution, three-dimensional, T1-weighted MRI scans. The challenge has two primary goals: (1) to compare different MRI reconstruction models on this dataset and (2) to assess the generalizability of these models to data acquired with a different number of receiver coils. In this paper, we describe the challenge experimental design and summarize the results of a set of baseline and state-of-the-art brain MRI reconstruction models. We provide relevant comparative information on the current MRI reconstruction state-of-the-art and highlight the challenges of obtaining generalizable models that are required prior to broader clinical adoption. The MC-MRI benchmark data, evaluation code, and current challenge leaderboard are publicly available. They provide an objective performance assessment for future developments in the field of brain MRI reconstruction.
KW - benchmark
KW - brain imaging
KW - image reconstruction
KW - inverse problems
KW - machine learning
KW - magnetic resonance imaging (MRI)
UR - http://www.scopus.com/inward/record.url?scp=85134575253&partnerID=8YFLogxK
U2 - https://doi.org/10.3389/fnins.2022.919186
DO - https://doi.org/10.3389/fnins.2022.919186
M3 - Article
C2 - 35873808
SN - 1662-4548
VL - 16
JO - Frontiers in neuroscience
JF - Frontiers in neuroscience
M1 - 919186
ER -