Language:

Qoala-T: A supervised-learning tool for quality control of FreeSurfer segmented MRI data

NeuroImage (Orlando, Fla.), 2019-04, Vol.189, p.116-129 [Peer Reviewed Journal]

2019 The Authors ;Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved. ;2019. The Authors ;ISSN: 1053-8119 ;EISSN: 1095-9572 ;DOI: 10.1016/j.neuroimage.2019.01.014 ;PMID: 30633965

Full text available

Citations Cited by

Actions
1. Add to My Research
2. Remove from My Research
3. E-mail
4. Print
5. Permalink
6. Citation
7. EasyBib
8. EndNote
9. RefWorks
10. Delicious
11. Export RIS
12. Export BibTeX

Title:
Qoala-T: A supervised-learning tool for quality control of FreeSurfer segmented MRI data
Author: Klapwijk, Eduard T. ; van de Kamp, Ferdi ; van der Meulen, Mara ; Peters, Sabine ; Wierenga, Lara M.
Subjects: Adolescent ; Adult ; Age ; Autism ; Autism Spectrum Disorder - diagnostic imaging ; Automation ; Brain - diagnostic imaging ; Child ; Conduct Disorder - diagnostic imaging ; Cross-Sectional Studies ; Data processing ; Datasets ; Datasets as Topic ; Development ; FreeSurfer ; Human Development ; Humans ; Learning ; Longitudinal Studies ; Magnetic resonance imaging ; Magnetic Resonance Imaging - methods ; Magnetic Resonance Imaging - standards ; Motion ; Neuroimaging - methods ; Neuroimaging - standards ; NMR ; Nuclear magnetic resonance ; Quality Control ; Random forests ; Ratings & rankings ; Sensitivity and Specificity ; Structural magnetic resonance imaging ; Studies ; Support Vector Machine ; Teenagers ; Young Adult
Is Part Of: NeuroImage (Orlando, Fla.), 2019-04, Vol.189, p.116-129
Description: Performing quality control to detect image artifacts and data-processing errors is crucial in structural magnetic resonance imaging, especially in developmental studies. Currently, many studies rely on visual inspection by trained raters for quality control. The subjectivity of these manual procedures lessens comparability between studies, and with growing study sizes quality control is increasingly time consuming. In addition, both inter-rater as well as intra-rater variability of manual quality control is high and may lead to inclusion of poor quality scans and exclusion of scans of usable quality. In the current study we present the Qoala-T tool, which is an easy and free to use supervised-learning model to reduce rater bias and misclassification in manual quality control procedures using FreeSurfer-processed scans. First, we manually rated quality of N = 784 FreeSurfer-processed T1-weighted scans acquired in three different waves in a longitudinal study. Different supervised-learning models were then compared to predict manual quality ratings using FreeSurfer segmented output data. Results show that the Qoala-T tool using random forests is able to predict scan quality with both high sensitivity and specificity (mean area under the curve (AUC) = 0.98). In addition, the Qoala-T tool was also able to adequately predict the quality of two novel unseen datasets (total N = 872). Finally, analyses of age effects showed that younger participants were more likely to have lower scan quality, underlining that scan quality might confound findings attributed to age effects. These outcomes indicate that this procedure could further help to reduce variability related to manual quality control, thereby benefiting the comparability of data quality between studies. [Display omitted] •Variability of manual quality control procedures reduces comparability among studies.•We introduce Qoala-T to automatically assess quality of FreeSurfer-processed scans.•Scan quality of novel datasets was adequately predicted using the Qoala-T tool.•In three different datasets younger age was associated with lower scan quality.•Qoala-T is publicly available and easy-to-use as an add-on to manual QC.
Publisher: United States: Elsevier Inc
Language: English
Identifier: ISSN: 1053-8119
EISSN: 1095-9572
DOI: 10.1016/j.neuroimage.2019.01.014
PMID: 30633965
Source: ProQuest One Psychology
MEDLINE
Alma/SFX Local Collection
ProQuest Central

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Qoala-T: A supervised-learning tool for quality control of FreeSurfer segmented MRI data

2019 The Authors ;Copyright © 2019 The Authors. Published by Elsevier Inc. All rights reserved. ;2019. The Authors ;ISSN: 1053-8119 ;EISSN: 1095-9572 ;DOI: 10.1016/j.neuroimage.2019.01.014 ;PMID: 30633965

Searching Remote Databases, Please Wait