Multi-Coil MRI Reconstruction Challenge-Assessing Brain MRI Reconstruction Models and Their Generalizability to Varying Coil Configurations

被引：23

作者：

Beauferris, Youssef ^{[1
,2
,3
]}

Teuwen, Jonas ^{[4
,5
,6
]}

Karkalousos, Dimitrios ^{[7
]}

Moriakov, Nikita ^{[4
,5
]}

Caan, Matthan ^{[7
]}

Yiasemis, George ^{[5
,6
]}

Rodrigues, Livia ^{[8
]}

Lopes, Alexandre ^{[9
]}

Pedrini, Helio ^{[9
]}

Rittner, Leticia ^{[8
]}

Dannecker, Maik ^{[10
]}

Studenyak, Viktor ^{[10
]}

Groeger, Fabian ^{[10
]}

Vyas, Devendra ^{[10
]}

Faghih-Roohi, Shahrooz ^{[10
]}

Kumar Jethi, Amrit ^{[11
]}

Chandra Raju, Jaya ^{[11
]}

Sivaprakasam, Mohanasankar ^{[11
,12
]}

Lasby, Mike ^{[1
,3
]}

Nogovitsyn, Nikita ^{[13
,14
]}

Loos, Wallace ^{[2
,3
,15
,16
]}

Frayne, Richard ^{[2
,3
,15
,16
]}

Souza, Roberto ^{[1
,2
,3
]}

机构：

[1] Univ Calgary, AI 2 Lab, Elect & Software Engn, Calgary, AB, Canada

[2] Univ Calgary, Biomed Engn Grad Program, Calgary, AB, Canada

[3] Univ Calgary, Hotchkiss Brain Inst, Calgary, AB, Canada

[4] Radboud Univ Nijmegen Med Ctr, Dept Med Imaging, Nijmegen, Netherlands

[5] Netherlands Canc Inst, Dept Radiat Oncol, Amsterdam, Netherlands

[6] Univ Amsterdam, Innovat Ctr Artificial Intelligence Artificial Int, Amsterdam, Netherlands

[7] Amsterdam Univ Med Ctr, Univ Amsterdam, Dept Biomed Engn & Phys, Amsterdam, Netherlands

[8] Univ Estadual Campinas, Sch Elect & Comp Engn, Med Image Comp Lab, Campinas, Brazil

[9] Univ Estadual Campinas, Inst Comp, Campinas, Brazil

[10] Tech Univ Munich, Comp Aided Med Procedures, Munich, Germany

[11] Indian Inst Technol Madras, Dept Elect Engn, Chennai, India

[12] Indian Inst Technol Madras, Healthcare Technol Innovat Ctr, Chennai, India

[13] St Michaels Hosp, Ctr Depress & Suicide Studies, Toronto, ON, Canada

[14] McMaster Univ, Dept Psychiat & Behav Neurosci, Mood Disorders Program, Hamilton, ON, Canada

[15] Univ Calgary, Radiol & Clin Neurosci, Calgary, AB, Canada

[16] Foothills Med Ctr, Seaman Family MR Res Ctr, Calgary, AB, Canada

来源：

FRONTIERS IN NEUROSCIENCE | 2022年 / 16卷

基金：

加拿大自然科学与工程研究理事会;

关键词：

machine learning; magnetic resonance imaging (MRI); benchmark; image reconstruction; inverse problems; brain imaging; IMAGE-RECONSTRUCTION; NETWORK; CASCADE; SENSE;

D O I：

10.3389/fnins.2022.919186

中图分类号：

Q189 [神经科学];

学科分类号：

071006 ;

摘要：

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.

引用

页数：15

共 63 条

[1] Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deep learning for fast imaging [J].