Multimodal MR Images-Based Diagnosis of Early Adolescent Attention-Deficit/Hyperactivity Disorder Using Multiple Kernel Learning.

Xiaocheng Zhou,Hui Lu,Yuanyuan Gui,Manhua Liu,Qingmin Lin,Zixin Wang

doi:10.3389/fnins.2021.710133

Abstract

Attention-deficit/hyperactivity disorder (ADHD) is one of the most common brain diseases among children. The current criteria of ADHD diagnosis mainly depend on behavior analysis, which is subjective and inconsistent, especially for children. The development of neuroimaging technologies, such as magnetic resonance imaging (MRI), drives the discovery of brain abnormalities in structure and function by analyzing multimodal neuroimages for computer-aided diagnosis of brain diseases. This paper proposes a multimodal machine learning framework that combines the Boruta based feature selection and Multiple Kernel Learning (MKL) to integrate the multimodal features of structural and functional MRIs and Diffusion Tensor Images (DTI) for the diagnosis of early adolescent ADHD. The rich and complementary information of the macrostructural features, microstructural properties, and functional connectivities are integrated at the kernel level, followed by a support vector machine classifier for discriminating ADHD from healthy children. Our experiments were conducted on the comorbidity-free ADHD subjects and covariable-matched healthy children aged 9–10 chosen from the Adolescent Brain and Cognitive Development (ABCD) study. This paper is the first work to combine structural and functional MRIs with DTI for early adolescents of the ABCD study. The results indicate that the kernel-level fusion of multimodal features achieves 0.698 of AUC (area under the receiver operating characteristic curves) and 64.3% of classification accuracy for ADHD diagnosis, showing a significant improvement over the early feature fusion and unimodal features. The abnormal functional connectivity predictors, involving default mode network, attention network, auditory network, and sensorimotor mouth network, thalamus, and cerebellum, as well as the anatomical regions in basal ganglia, are found to encode the most discriminative information, which collaborates with macrostructure and diffusion alterations to boost the performances of disorder diagnosis.

Highlights

Attention-deficit/hyperactivity disorder (ADHD) has become one of the most common neurobehavioral disorders among children (Polanczyk et al, 2015)
This work concentrates on the tabulated multiple-type image-based features, including the quantitative brain properties extracted from Structural MRI (sMRI) (T1/2 weighted parts), resting-state fMRI (rsfMRI), and DTI, of the baseline year in release 2.0.1 (Jernigan et al, 2019) for further analysis of ADHD
In our study’s ambiance, condition positive samples are referred to subjects with ADHD, condition negative one’s typical healthy subjects, prediction positive, and negative ones marked by the models

Summary

Introduction

Attention-deficit/hyperactivity disorder (ADHD) has become one of the most common neurobehavioral disorders among children (Polanczyk et al, 2015). In 2016, 9.4% of children and adolescents aging 2–17 in the United States had ever been diagnosed with ADHD, 89.4% of which still kept the diagnosis at present (Danielson et al, 2018). Untreated ADHD can cause substance abuse and tremendous academic, social, and financial/employment burdens on the individual and family (Hamed et al, 2015), reflecting the importance of diagnosing and treating the disorder. The most advanced standard of ADHD diagnosis is symptom-based, according to the Diagnostic and Statistical Manual of Mental Disorders, the 5th edition (Wolraich et al, 2019) (DSM-5), relying on the questionnaires collected from the parents or caregivers for young children. The diagnosis of ADHD requires objective and quantizable evidence

Methods

Results

Conclusion