An interpretable multiparametric radiomics model for the diagnosis of schizophrenia using magnetic resonance imaging of the corpus callosum

Minji Bang,Jinna Kim,Sooyon Kim,Chansik An,Yae Won Park,Jihwan Eom,Sang-Hyuk Lee,Seung-Koo Lee,Sung Soo Ahn

doi:10.1038/s41398-021-01586-2

Abstract

There is a growing need to develop novel strategies for the diagnosis of schizophrenia using neuroimaging biomarkers. We investigated the robustness of the diagnostic model for schizophrenia using radiomic features from T1-weighted and diffusion tensor images of the corpus callosum (CC). A total of 165 participants [86 schizophrenia and 79 healthy controls (HCs)] were allocated to training (N = 115) and test (N = 50) sets. Radiomic features of the CC subregions were extracted from T1-weighted, apparent diffusion coefficient (ADC), and fractional anisotropy (FA) images (N = 1605). Following feature selection, various combinations of classifiers were trained, and Bayesian optimization was adopted in the best performing classifier. Discrimination, calibration, and clinical utility of the model were assessed. An online calculator was constructed to offer the probability of having schizophrenia. SHapley Additive exPlanations (SHAP) was applied to explore the interpretability of the model. We identified 30 radiomic features to differentiate participants with schizophrenia from HCs. The Bayesian optimized model achieved the highest performance, with an area under the curve (AUC), accuracy, sensitivity, and specificity of 0.89 (95% confidence interval: 0.81–0.98), 80.0, 83.3, and 76.9%, respectively, in the test set. The final model offers clinical probability in an online calculator. The model explanation by SHAP suggested that second-order features from the posterior CC were highly associated with the risk of schizophrenia. The multiparametric radiomics model focusing on the CC shows its robustness for the diagnosis of schizophrenia. Radiomic features could be a potential source of biomarkers that support the biomarker-based diagnosis of schizophrenia and improve the understanding of its neurobiology.

Highlights

Schizophrenia is a highly disabling psychiatric disorder with an unclear etiology and pathogenesis
We investigated the robustness of the diagnostic model for schizophrenia using radiomic features from T1-weighted images (T1)-weighted and diffusion tensor images of the corpus callosum (CC)
In the Bayesian optimized model of the training set, the area under the curve (AUC), accuracy, sensitivity, and specificity were 0.90, 81.7, 85.0, and 78.3%, respectively; in the test set, the AUC, accuracy, sensitivity, and specificity were 0.89, 80.0, 83.3, and 76.9%, respectively (Fig. 2A)

Summary

Introduction

Schizophrenia is a highly disabling psychiatric disorder with an unclear etiology and pathogenesis. Structural magnetic resonance imaging (MRI) studies have reported morphological alterations in callosal shape [3, 4] and smaller size of the CC and its subregions [5, 6] in patients with schizophrenia compared to that of healthy controls (HCs). Diffusion tensor imaging (DTI), which allows for the in vivo assessment of microstructural features of the white matter, revealed myelin and axonal alterations of the CC in patients with schizophrenia, which cannot be captured by standard MRI [7]. The latest large-scale collaborative study on white matter abnormalities in schizophrenia showed that a lower fractional anisotropy (FA) and higher apparent diffusion coefficient (ADC) in the CC are among the most reliable findings with a large effect size that differentiated patients with schizophrenia from HCs [8]. Single-value parameters derived from neuroimaging data, which measure the volume, area, or fiber integrity, do not fully capture the subtle and complex neuropathological changes in the CC, underlying the development of schizophrenia

Objectives

Methods

Results

Conclusion