Automated Quality Assessment of Structural Magnetic Resonance Brain Images Based on a Supervised Machine Learning Algorithm.
Front. Neuroinform.. 2016-12-19; 10:
DOI: 10.3389/fninf.2016.00052
Read on PubMed
Pizarro RA(1), Cheng X(2), Barnett A(3), Lemaitre H(4), Verchinski BA(5), Goldman
AL(5), Xiao E(5), Luo Q(6), Berman KF(7), Callicott JH(8), Weinberger DR(9),
Mattay VS(10).
Author information:
(1)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of HealthBethesda, MD, USA; Department of Biomedical
Engineering, UW-MadisonMadison, WI, USA.
(2)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of HealthBethesda, MD, USA; The Lieber Institute for Brain
DevelopmentBaltimore, MD, USA; Bioinformatics and Computational Biosciences
Branch, Office of Cyber Infrastructure and Computational Biology (OCICB),
National Institute of Allergy and Infectious Diseases (NIAID), National
Institutes of HealthRockville, MD, USA.
(3)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of Health Bethesda, MD, USA.
(4)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of HealthBethesda, MD, USA; NeuroImaging and Psychiatry, UMR
1000, Faculté de Médecine, Institut National de la Santé Et de la Recherche
Médicale, Service Hospitalier Frédéric Joliot, Université Paris-SudOrsay, France.
(5)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of HealthBethesda, MD, USA; The Lieber Institute for Brain
DevelopmentBaltimore, MD, USA.
(6)Behavioral Biology Branch, Walter Reed Army Research Institute Silver Spring,
MD, USA.
(7)Clinical and Translational Neuroscience Branch, National Institute of Mental
Health, National Institutes of Health Bethesda, MD, USA.
(8)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of HealthBethesda, MD, USA; Clinical and Translational
Neuroscience Branch, National Institute of Mental Health, National Institutes of
HealthBethesda, MD, USA.
(9)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of HealthBethesda, MD, USA; The Lieber Institute for Brain
DevelopmentBaltimore, MD, USA; Departments of Psychiatry, Neurology and
Neuroscience, Johns Hopkins University School of MedicineBaltimore, MD, USA; The
Institute of Genetic Medicine, Johns Hopkins University School of
MedicineBaltimore, MD, USA.
(10)Genes, Cognition, and Psychosis Program, National Institute of Mental Health,
National Institutes of HealthBethesda, MD, USA; The Lieber Institute for Brain
DevelopmentBaltimore, MD, USA; Departments of Neurology and Radiology, Johns
Hopkins University School of MedicineBaltimore, MD, USA.
High-resolution three-dimensional magnetic resonance imaging (3D-MRI) is being
increasingly used to delineate morphological changes underlying neuropsychiatric
disorders. Unfortunately, artifacts frequently compromise the utility of 3D-MRI
yielding irreproducible results, from both type I and type II errors. It is
therefore critical to screen 3D-MRIs for artifacts before use. Currently, quality
assessment involves slice-wise visual inspection of 3D-MRI volumes, a procedure
that is both subjective and time consuming. Automating the quality rating of
3D-MRI could improve the efficiency and reproducibility of the procedure. The
present study is one of the first efforts to apply a support vector machine (SVM)
algorithm in the quality assessment of structural brain images, using global and
region of interest (ROI) automated image quality features developed in-house. SVM
is a supervised machine-learning algorithm that can predict the category of test
datasets based on the knowledge acquired from a learning dataset. The performance
(accuracy) of the automated SVM approach was assessed, by comparing the
SVM-predicted quality labels to investigator-determined quality labels. The
accuracy for classifying 1457 3D-MRI volumes from our database using the SVM
approach is around 80%. These results are promising and illustrate the
possibility of using SVM as an automated quality assessment tool for 3D-MRI.