Premium
Automatic classification of major depression disorder using arterial spin labeling MRI perfusion measurements
Author(s) -
Ramasubbu Rajamannar,
Brown Elliot Clayton,
Marcil Lorenzo Daniel,
Talai Aron Sahand,
Forkert Nils Daniel
Publication year - 2019
Publication title -
psychiatry and clinical neurosciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.609
H-Index - 74
eISSN - 1440-1819
pISSN - 1323-1316
DOI - 10.1111/pcn.12862
Subject(s) - major depressive disorder , arterial spin labeling , neuroimaging , artificial intelligence , cerebral blood flow , multivariate statistics , support vector machine , medicine , pattern recognition (psychology) , machine learning , computer science , psychiatry , amygdala
Aim Neuroimaging‐based multivariate pattern‐recognition methods have been successfully used to develop diagnostic algorithms to distinguish patients with major depressive disorder (MDD) from healthy controls (HC). We developed and evaluated the accuracy of a multivariate classification method for the differentiation of MDD and HC using cerebral blood flow (CBF) features measured by non‐invasive arterial spin labeling (ASL) MRI. Methods Twenty‐two medication‐free patients with the diagnosis of MDD based on DSM‐IV criteria and 22 HC underwent pseudo‐continuous 3‐D‐ASL imaging to assess CBF. Using an atlas‐based approach, regional CBF was determined in various brain regions and used together with sex and age as classification features. A linear kernel support vector machine was used for feature ranking and selection as well as for the classification of patients with MDD and HC. Permutation testing was used to test for significance of the classification results. Results The automatic classifier based on CBF features showed a statistically significant accuracy of 77.3% ( P = 0.004) with a specificity of 80% and sensitivity of 75% for classification of MDD versus HC. The features that contributed to the classification were sex and regional CBF of the cortical, limbic, and paralimbic regions. Conclusion Machine‐learning models based on CBF measurements are capable of differentiating MDD from HC with high accuracy. The use of larger study cohorts and inclusion of other imaging measures may improve the performance of the classifier to achieve the accuracy required for clinical application.