Abstract
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.
Highlights
High-resolution T1-weighted structural three-dimensional brain magnetic resonance imaging (3D-MRI1) is being increasingly used to assess brain morphological changes underlying neuropsychiatric disorders such as Parkinson’s disease, Alzheimer’s disease, and schizophrenia (Goldman et al, 2009; Jubault et al, 2011; Sabuncu et al, 2011)
The subcategory from the visual inspection procedure gets worse in the 3D-magnetic resonance images (MRI), i.e., from none to heavy, as the value for ASF1 correspondingly increases
The subcategory from the visual inspection procedure gets worse in the 3D-MRIs, i.e., from none to heavy, as the value for the ASF2 correspondingly increases
Summary
High-resolution T1-weighted structural three-dimensional brain magnetic resonance imaging (3D-MRI1) is being increasingly used to assess brain morphological changes underlying neuropsychiatric disorders such as Parkinson’s disease, Alzheimer’s disease, and schizophrenia (Goldman et al, 2009; Jubault et al, 2011; Sabuncu et al, 2011). Image artifacts can compromise the utility of 3D-MRI volumes in brain morphometric studies. These artifacts include: (1) a rippling appearance in brain regions behind the orbits resulting from eye movement during acquisition, (2) a broad wave-like pattern near the top of the head resulting from motion induced ghosting of the bright fat in the skull, and (3) an aliasing artifact resulting from the field of view that is smaller than the object, whereby the nose and other facial structures appear overlaid on the posterior structures of the brain. Failure to exclude 3D-MRIs with such image artifacts frequently causes automated morphometric analysis routines to misclassify brain tissue type. This error can be propagated into subsequent analyses involving gray matter intensity, shape, or surface, leading to spurious results. There are very few studies in the literature that directly explored how image quality can affect identification of neuropathology from 3D-MRI (Magnotta et al, 2006; Woodard and Carley-Spencer, 2006)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
