Gray and white matter structural examination for diagnosis of major depressive disorder and subthreshold depression in adolescents and young adults: a preliminary radiomics analysis

Abstract

Background: Radiomics is an emerging image analysis framework that provides more details than conventional methods. In present study, we aimed to identify structural radiomics features of gray matter (GM) and white matter (WM), and to develop and validate the classification model for major depressive disorder (MDD) and subthreshold depression (StD) diagnosis using radiomics analysis.

Methods: A consecutive cohort of 142 adolescents and young adults, including 43 cases with MDD, 49 cases with StD and 50 healthy controls (HC), were recruited and underwent the three-dimensional T1 weighted imaging (3D-T₁WI) and diffusion tensor imaging (DTI). We extracted radiomics features representing the shape and diffusion properties of GM and WM from all participants. Then, an all-relevant feature selection process embedded in a 10-fold cross-validation framework was used to identify features with significant power for discrimination. Random forest classifiers (RFC) were established and evaluated successively using identified features.

Results: The results showed that a total of 3030 features were extracted after preprocessing, including 2262 shape-related features from each T1-weighted image representing GM morphometry and 768 features from each DTI representing the diffusion properties of WM. 25 features were selected ultimately, including ten features for MDD versus HC, eight features for StD versus HC, and seven features for MDD versus StD. The accuracies and area under curve (AUC) the RFC achieved were 86.75%, 0.93 for distinguishing MDD from HC with significant radiomics features located in the left medial orbitofrontal cortex, right superior and middle temporal regions, right anterior cingulate, left cuneus and hippocampus, 70.51%, 0.69 for discriminating StD from HC within left cuneus, medial orbitofrontal cortex, cerebellar vermis, hippocampus, anterior cingulate and amygdala, right superior and middle temporal regions, and 59.15%, 0.66 for differentiating MDD from StD within left medial orbitofrontal cortex, middle temporal and cuneus, right superior frontal, superior temporal regions and hippocampus, anterior cingulate, respectively.

Conclusion: These findings provide preliminary evidence that radiomics features of brain structure are valid for discriminating MDD and StD subjects from healthy controls. The MRI-based radiomics approach, with further improvement and validation, might be a potential facilitating method to clinical diagnosis of MDD or StD.

Keywords: Machine learning; Magnetic resonance imaging; Major depressive disorder; Radiomics; Subthreshold depression.

Fig. 1

Flowchart of the radiomics process. First, the 3D-T₁WI and DTI images were acquired and preprocessed. Then radiomics features of shape properties of gray matter, diffusion properties of white matter and their distribution metrics i.e., statistical metrics for each labeled region were extracted. Shape properties included local cortical thickness, mean curvature, convexity, geodesic depth, and travel depth. Diffusion properties contained fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD). Distribution metrics consisted of mean, standard deviation (SD), skew, and kurtosis. In the end, flowchart shows features selection and classifier construction. The all-relevant features selection step was embedded in 10-fold cross-validation. Random forest classifiers (RFC) were established and evaluated to discriminate patients with MDD or StD from healthy controls. Abbreviation: MDD, major depressive disorder; StD, subthreshold depression

Fig. 2

Ten radiomics features of sMRI for discriminating MDD and HC with significant radiomics features located in the left medial orbitofrontal, right superior and middle temporal regions, right anterior cingulate, left cuneus and hippocampus. Abbreviation: MDD, major depressive disorder; HC, healthy control

Fig. 3

Eight radiomics features of sMRI for discriminating StD and HC with significant radiomics features located in the left cuneus, medial orbitofrontal, cerebellar vermis, hippocampus, anterior cingulate and amygdala, right superior and middle temporal regions. Abbreviation: StD, subthreshold depression; HC, healthy control

Fig. 4

Seven radiomics features of sMRI for discriminating MDD and StD with significant radiomics features located in the left medial orbitofrontal, middle temporal, cuneus, and right superior frontal, superior temporal regions and hippocampus, anterior cingulate. Abbreviation: MDD, major depressive disorder; StD, subthreshold depression

Fig. 5

Receiver operating characteristic(ROC)curve of the random forest model for discriminating between MDD and HC subjects (blue line), StD and HC subjects (green line) and MDD and StD subjects (red line). Abbreviation: MDD, major depressive disorder; StD, subthreshold depression; HC, healthy control