Neuroimaging-based methods for autism identification: a possible translational application?

Abstract

Classification methods based on machine learning (ML) techniques are becoming widespread analysis tools in neuroimaging studies. They have the potential to enhance the diagnostic power of brain data, by assigning a predictive index, either of pathology or of treatment response, to the single subject's acquisition. ML techniques are currently finding numerous applications in psychiatric illness, in addition to the widely studied neurodegenerative diseases. In this review we give a comprehensive account of the use of classification techniques applied to structural magnetic resonance images in autism spectrum disorders (ASDs). Understanding of these highly heterogeneous neurodevelopmental diseases could greatly benefit from additional descriptors of pathology and predictive indices extracted directly from brain data. A perspective is also provided on the future developments necessary to translate ML methods from the field of ASD research into the clinic. KEY WORDS: autism spectrum disorders, brain alterations, machine learning, magnetic resonance imaging, translational research © C I C E d i z i o n i I n t e r n a z i o n a l i Functional Neurology 2014; 29(4): 231-239

Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls

“…Previous reviews include disease-specific surveys such as schizophrenia (Calhoun and Arbabshirani, 2012; Dazzan, 2014; Demirci et al, 2008b; Kambeitz et al, 2015; Veronese et al, 2013; Zarogianni et al, 2013), autism spectrum disorder (Retico et al, 2014, 2013), Alzheimer's disease (Falahati et al, 2014; Klöppel et al, 2008) and in general (Klöppel et al, 2012; Orrù et al, 2012) as well as modality-specific reviews such as machine learning based on fMRI (Sundermann et al, 2014). Also, there are few children specific reviews such as a recent one by Levman et al on multivariate analyses studies in neonatal and pediatric patients (Levman and Takahashi, 2015).…”

Gray Matter Alterations in Young Children with Autism Spectrum Disorders: Comparing Morphometry at the Voxel and Regional Level

“…12 Recently, noninvasive brain imaging methods coupled with advanced image analysis methodologies based on machine learning (ML) techniques were used with the aim of providing an automated classification of neuropsychiatric disorders and thus expediting or confirming their diagnostic process. 13 for a recent review). 13 for a recent review).…”

“…Different pathologies, or different stages or severity of the same pathology, can reflect differently in the brain morphometry. 5,24,25 The classification performances achieved in those studies are extremely variable, 13 reaching sometimes very high values. A typical example is the estimate of the volumes of the hippocampus 14,15 or the medial temporal lobes 16,17 in the study of the Alzheimer's disease.…”

Functional SPECT neuroimaging using machine learning algorithms distinguishes autism spectrum disorder from healthy subjects

“…The application of machine learning algorithms to neuroimaging data offers the potential to improve the precision of the diagnosis through the identification of brain based biomarkers in ASD [7]. These applications involve improving diagnostic capabilities, targeting interventions and monitoring patient outcomes [7,8].…”

“…These applications involve improving diagnostic capabilities, targeting interventions and monitoring patient outcomes [7,8]. Multivariate Analysis has shown promising clinical applicability with regards to diagnosing and characterizing neurodevelopmental disorders such as ASD [8].…”