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

Abstract

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. First, we manually rated quality of N = 784 FreeSurfer-processed T1-weighted scans. Different supervised-learning models were then compared to predict manual quality ratings. 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 a novel unseen dataset (N = 112; mean AUC = 0.95). These outcomes indicate that using Qoala-T in other datasets could greatly reduce the time needed for quality control. More importantly, this procedure could further help to reduce variability related to manual quality control, thereby benefiting the comparability of data quality between studies.