Multi‐task diagnosis for autism spectrum disorders using multi‐modality features: A multi‐center study

Abstract

Autism spectrum disorder (ASD) is a neurodevelopment disease characterized by impairment of social interaction, language, behavior and cognitive functions. Up to now, many imaging-based methods for ASD diagnosis have been developed. For example, one may extract abundant features from multi-modality images and then derive a discriminant function to map the selected features toward the disease label. A lot of recent works, however, are limited to single imaging centers. To this end, we propose a novel multi-modality multi-center classification (M3CC) method for ASD diagnosis. We treat the classification of each imaging center as one task. By introducing the task-task and modality-modality regularizations, we solve the classification for all imaging centers simultaneously. Meanwhile, the optimal feature selection and the modeling of the discriminant functions can be jointly conducted for highly accurate diagnosis. Besides, we also present an efficient iterative optimization solution to our formulated problem and further investigate its convergence. Our comprehensive experiments on the ABIDE database show that our proposed method can significantly improve the performance of ASD diagnosis, compared to the existing methods.

Neurobiological support to the diagnosis of ADHD in stimulant‐naïve adults: pattern recognition analyses of MRI data

“…However, because it is difficult to recruit representative populations of stimulant‐naïve ADHD adults from a single‐site, larger ML‐based studies combining data from multiple sites (obtained with the same selection criteria) may be considered as a more feasible alternative . Such multi‐site MRI studies should allow both the testing of diagnostic performance across independent validation samples of adults never treated for ADHD symptoms , and the use of novel multi‐task learning methods suitable for finding disease‐related signatures while handling heterogeneity across different populations and MRI acquisition protocols .…”

Feature Selection and Classification for High-Dimensional Incomplete Multimodal Data

“…Li et al [9,10] proposed a multitask deep learning method for diagnosing Alzheimer's Disease by combining MRI, PET, and Assessment Scale-Cognitive subscale (ADAS-Cog) with the restricted Boltzmann machine. Wang et al [11] explained a novel multimodality multicenter classification method for autism spectrum disorder diagnosis; they regarded the classification of each imaging center as one task and solved the classification for all imaging centers by introducing the task-task and modality-modality regularizations. Liu et al [12] proposed a view-aligned hypergraph learning (VAHL) method and utilized incomplete multimodality data for AD/MCI diagnosis.…”

Low-Rank Representation for Multi-center Autism Spectrum Disorder Identification

“…It was reported that there were 62.2 million ASD cases in the world in 2015 [1]. However, the pathological mechanism of ASD is unclear, and conventional diagnosis of ASD is usually based on symptoms [2], and thus the precise diagnosis is the main challenge in the research literature of ASD.…”