Frontiers in Neuroscience (Jul 2022)
Multi-Coil MRI Reconstruction Challenge—Assessing Brain MRI Reconstruction Models and Their Generalizability to Varying Coil Configurations
- Youssef Beauferris,
- Youssef Beauferris,
- Youssef Beauferris,
- Jonas Teuwen,
- Jonas Teuwen,
- Jonas Teuwen,
- Dimitrios Karkalousos,
- Nikita Moriakov,
- Nikita Moriakov,
- Matthan Caan,
- George Yiasemis,
- George Yiasemis,
- Lívia Rodrigues,
- Alexandre Lopes,
- Helio Pedrini,
- Letícia Rittner,
- Maik Dannecker,
- Viktor Studenyak,
- Fabian Gröger,
- Devendra Vyas,
- Shahrooz Faghih-Roohi,
- Amrit Kumar Jethi,
- Jaya Chandra Raju,
- Mohanasankar Sivaprakasam,
- Mohanasankar Sivaprakasam,
- Mike Lasby,
- Mike Lasby,
- Nikita Nogovitsyn,
- Nikita Nogovitsyn,
- Wallace Loos,
- Wallace Loos,
- Wallace Loos,
- Wallace Loos,
- Richard Frayne,
- Richard Frayne,
- Richard Frayne,
- Richard Frayne,
- Roberto Souza,
- Roberto Souza,
- Roberto Souza
Affiliations
- Youssef Beauferris
- (AI)2 Lab, Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada
- Youssef Beauferris
- Biomedical Engineering Graduate Program, University of Calgary, Calgary, AB, Canada
- Youssef Beauferris
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Jonas Teuwen
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, Netherlands
- Jonas Teuwen
- Department of Radiation Oncology, Netherlands Cancer Institute, Amsterdam, Netherlands
- Jonas Teuwen
- Innovation Centre for Artificial Intelligence – Artificial Intelligence for Oncology, University of Amsterdam, Amsterdam, Netherlands
- Dimitrios Karkalousos
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Centre, University of Amsterdam, Amsterdam, Netherlands
- Nikita Moriakov
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, Netherlands
- Nikita Moriakov
- Department of Radiation Oncology, Netherlands Cancer Institute, Amsterdam, Netherlands
- Matthan Caan
- Department of Biomedical Engineering and Physics, Amsterdam University Medical Centre, University of Amsterdam, Amsterdam, Netherlands
- George Yiasemis
- Department of Radiation Oncology, Netherlands Cancer Institute, Amsterdam, Netherlands
- George Yiasemis
- Innovation Centre for Artificial Intelligence – Artificial Intelligence for Oncology, University of Amsterdam, Amsterdam, Netherlands
- Lívia Rodrigues
- Medical Image Computing Lab, School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil
- Alexandre Lopes
- Institute of Computing, University of Campinas, Campinas, Brazil
- Helio Pedrini
- Institute of Computing, University of Campinas, Campinas, Brazil
- Letícia Rittner
- Medical Image Computing Lab, School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil
- Maik Dannecker
- 0Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany
- Viktor Studenyak
- 0Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany
- Fabian Gröger
- 0Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany
- Devendra Vyas
- 0Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany
- Shahrooz Faghih-Roohi
- 0Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany
- Amrit Kumar Jethi
- 1Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India
- Jaya Chandra Raju
- 1Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India
- Mohanasankar Sivaprakasam
- 1Department of Electrical Engineering, Indian Institute of Technology Madras, Chennai, India
- Mohanasankar Sivaprakasam
- 2Healthcare Technology Innovation Centre, Indian Institute of Technology Madras, Chennai, India
- Mike Lasby
- (AI)2 Lab, Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada
- Mike Lasby
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Nikita Nogovitsyn
- 3Centre for Depression and Suicide Studies, St. Michael's Hospital, Toronto, ON, Canada
- Nikita Nogovitsyn
- 4Mood Disorders Program, Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, ON, Canada
- Wallace Loos
- Biomedical Engineering Graduate Program, University of Calgary, Calgary, AB, Canada
- Wallace Loos
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Wallace Loos
- 5Radiology and Clinical Neurosciences, University of Calgary, Calgary, AB, Canada
- Wallace Loos
- 6Seaman Family MR Research Centre, Foothills Medical Center, Calgary, AB, Canada
- Richard Frayne
- Biomedical Engineering Graduate Program, University of Calgary, Calgary, AB, Canada
- Richard Frayne
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Richard Frayne
- 5Radiology and Clinical Neurosciences, University of Calgary, Calgary, AB, Canada
- Richard Frayne
- 6Seaman Family MR Research Centre, Foothills Medical Center, Calgary, AB, Canada
- Roberto Souza
- (AI)2 Lab, Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada
- Roberto Souza
- Biomedical Engineering Graduate Program, University of Calgary, Calgary, AB, Canada
- Roberto Souza
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- DOI
- https://doi.org/10.3389/fnins.2022.919186
- Journal volume & issue
-
Vol. 16
Abstract
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.
Keywords
- machine learning
- magnetic resonance imaging (MRI)
- benchmark
- image reconstruction
- inverse problems
- brain imaging
