Multimodal MRI-Based Classification of Trauma Survivors with and without Post-Traumatic Stress Disorder.

Qiongmin Zhang,Ling He,Hua Huang,Wei Zhang,Qizhu Wu,Hongru Zhu,Junran Zhang

doi:10.3389/fnins.2016.00292

Abstract

Post-traumatic stress disorder (PTSD) is a debilitating psychiatric disorder. It can be difficult to discern the symptoms of PTSD and obtain an accurate diagnosis. Different magnetic resonance imaging (MRI) modalities focus on different aspects, which may provide complementary information for PTSD discrimination. However, none of the published studies assessed the diagnostic potential of multimodal MRI in identifying individuals with and without PTSD. In the current study, we investigated whether the complementary information conveyed by multimodal MRI scans could be combined to improve PTSD classification performance. Structural and resting-state functional MRI (rs-fMRI) scans were conducted on 17 PTSD patients, 20 trauma-exposed controls without PTSD (TEC) and 20 non-traumatized healthy controls (HC). Gray matter volume (GMV), amplitude of low-frequency fluctuations (ALFF), and regional homogeneity were extracted as classification features, and in order to integrate the information of structural and functional MRI data, the extracted features were combined by a multi-kernel combination strategy. Then a support vector machine (SVM) classifier was trained to distinguish the subjects at individual level. The performance of the classifier was evaluated using the leave-one-out cross-validation (LOOCV) method. In the pairwise comparison of PTSD, TEC, and HC groups, classification accuracies obtained by the proposed approach were 2.70, 2.50, and 2.71% higher than the best single feature way, with the accuracies of 89.19, 90.00, and 67.57% for PTSD vs. HC, TEC vs. HC, and PTSD vs. TEC respectively. The proposed approach could improve PTSD identification at individual level. Additionally, it provides preliminary support to develop the multimodal MRI method as a clinical diagnostic aid.

Highlights

Post-traumatic stress disorder (PTSD) is newly defined as a trauma- and stressor-related disorder in the fifth edition of the Diagnostic and Statistical Manual of mental disorder (DSM-V)
In the comparison of PTSD and trauma-exposed controls without PTSD (TEC), Gray matter volume (GMV) difference mainly included the bilateral middle temporal gyrus, right rolandic operculum, right superior frontal gyrus, and the left postcentral gyrus; amplitude of low-frequency fluctuations (ALFF) difference were shown in the left lingual gyrus and left precuneus gyrus; regional homogeneity (ReHo) difference mainly exhibited in the right precuneus gyrus (Figure 3C; see Supplementary Table 3 for a full list). This is the first study to examine the capability of a machine learning approach to combine different features extracted from structural MRI (sMRI) and resting-state functional MRI (rs-fMRI) data for PTSD, TEC, and healthy controls (HC) discrimination
The results showed that in comparison with single feature method, the feature-combining framework could achieve higher accuracies for all three pairwise classifications among the three groups

Summary

Introduction

Post-traumatic stress disorder (PTSD) is newly defined as a trauma- and stressor-related disorder in the fifth edition of the Diagnostic and Statistical Manual of mental disorder (DSM-V). The prevalence of PTSD among direct victims of disasters ranges between 30 and 40%; lifetime prevalence of PTSD varies from 0.3 to 6.1% in different countries (Javidi and Yadollahie, 2012), and 19% of PTSD patients will attempt suicide (Kessler et al, 1999; Foa et al, 2006) It is of paramount importance for the early diagnosis and appropriate treatment of PTSD. There are no reliable biomarkers that can be used to identify trauma-exposed individuals with and without PTSD at present. The diagnosis of this disorder is still very reliant on the assessment of signs and symptoms, as well as a thorough psychological evaluation.

Objectives

Methods

Results

Conclusion