The Role of Diffusion Tensor MR Imaging (DTI) of the Brain in Diagnosing Autism Spectrum Disorder: Promising Results

Autism spectrum disorder (ASD) is a combination of developmental anomalies that causes social and behavioral impairments, affecting around 2% of US children. Common symptoms include difficulties in communications, interactions, and behavioral disabilities. The onset of symptoms can start in early childhood, yet repeated visits to a pediatric specialist are needed before reaching a diagnosis. Still, this diagnosis is usually subjective, and scores can vary from one specialist to another. Previous literature suggests differences in brain development, environmental, and/or genetic factors play a role in developing autism, yet scientists still do not know exactly the pathology of this disorder. Currently, the gold standard diagnosis of ASD is a set of diagnostic evaluations, such as the Autism Diagnostic Observation Schedule (ADOS) or Autism Diagnostic Interview–Revised (ADI-R) report. These gold standard diagnostic instruments are an intensive, lengthy, and subjective process that involves a set of behavioral and communications tests and clinical history information conducted by a team of qualified clinicians. Emerging advancements in neuroimaging and machine learning techniques can provide a fast and objective alternative to conventional repetitive observational assessments. This paper provides a thorough study of implementing feature engineering tools to find discriminant insights from brain imaging of white matter connectivity and using a machine learning framework for an accurate classification of autistic individuals. This work highlights important findings of impacted brain areas that contribute to an autism diagnosis and presents promising accuracy results. We verified our proposed framework on a large publicly available DTI dataset of 225 subjects from the Autism Brain Imaging Data Exchange-II (ABIDE-II) initiative, achieving a high global balanced accuracy over the 5 sites of up to 99% with 5-fold cross validation. The data used was slightly unbalanced, including 125 autistic subjects and 100 typically developed (TD) ones. The achieved balanced accuracy of the proposed technique is the highest in the literature, which elucidates the importance of feature engineering steps involved in extracting useful knowledge and the promising potentials of adopting neuroimaging for the diagnosis of autism.

[1]  D. Manoach,et al.  Diffusion-weighted imaging evidence of altered white matter development from late childhood to early adulthood in Autism Spectrum Disorder , 2018, NeuroImage: Clinical.

[2]  Ayman El-Baz,et al.  Towards Non-invasive Image-Based Early Diagnosis of Autism , 2015, MICCAI.

[3]  R. Bellman Dynamic Programming , 1957, Science.

[4]  Salem Hannoun,et al.  Pre- and Post-therapy Assessment of Clinical Outcomes and White Matter Integrity in Autism Spectrum Disorder: Pilot Study , 2019, Front. Neurol..

[5]  Julia P. Owen,et al.  White Matter Connectome Edge Density in Children with Autism Spectrum Disorders: Potential Imaging Biomarkers Using Machine-Learning Models , 2019, Brain Connect..

[6]  Joshua B. Ewen,et al.  The Disrupted Connectivity Hypothesis of Autism Spectrum Disorders: Time for the Next Phase in Research. , 2016, Biological psychiatry. Cognitive neuroscience and neuroimaging.

[7]  M. Taylor,et al.  Widespread White Matter Differences in Children and Adolescents with Autism Spectrum Disorder , 2016, Journal of autism and developmental disorders.

[8]  E. Gasparetto,et al.  Diffusion Tensor Imaging Findings in School‐Aged Autistic Children , 2009, Journal of neuroimaging : official journal of the American Society of Neuroimaging.

[9]  Talma Hendler,et al.  Accelerated maturation of white matter in young children with autism: A high b value DWI study , 2007, NeuroImage.

[10]  Fang-Cheng Yeh,et al.  A diffusion spectrum imaging-based tractographic study into the anatomical subdivision and cortical connectivity of the ventral external capsule: uncinate and inferior fronto-occipital fascicles , 2017, Neuroradiology.

[11]  M. Gerstein,et al.  The Development of a Practical Artificial Intelligence Tool for Diagnosing and Evaluating Autism Spectrum Disorder: Multicenter Study , 2020, JMIR medical informatics.

[12]  Andrew L. Alexander,et al.  Diffusion tensor imaging of the corpus callosum in Autism , 2007, NeuroImage.

[13]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[14]  Moo K. Chung,et al.  Diffusion tensor imaging of white matter in the superior temporal gyrus and temporal stem in autism , 2007, Neuroscience Letters.

[15]  Do P. M. Tromp,et al.  Longitudinal development of thalamic and internal capsule microstructure in autism spectrum disorder , 2018, Autism research : official journal of the International Society for Autism Research.

[16]  S. Wakana,et al.  MRI Atlas of Human White Matter , 2005 .

[17]  Gereon R Fink,et al.  Structural brain abnormalities in adolescents with autism spectrum disorder and patients with attention deficit/hyperactivity disorder. , 2007, Journal of child psychology and psychiatry, and allied disciplines.

[18]  Ralph-Axel Müller,et al.  Tract-specific analyses of diffusion tensor imaging show widespread white matter compromise in autism spectrum disorder. , 2011, Journal of child psychology and psychiatry, and allied disciplines.

[19]  Christophe Lenglet,et al.  Network curvature as a hallmark of brain structural connectivity , 2019, Nature Communications.

[20]  Otto Muzik,et al.  A Diffusion Tensor Imaging Study of the Cerebellar Pathways in Children With Autism Spectrum Disorder , 2010, Journal of child neurology.

[21]  A. Estes,et al.  Age-related abnormalities in white matter microstructure in autism spectrum disorders , 2012, Brain Research.

[22]  Martin Styner,et al.  DTI registration in atlas based fiber analysis of infantile Krabbe disease , 2011, NeuroImage.

[23]  M. Reiter,et al.  Diagnostic Classification of Autism using Resting-State fMRI Data and Conditional Random Forest. , 2018, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.

[24]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[25]  R. Hashimoto,et al.  White matter endophenotypes and correlates for the clinical diagnosis of autism spectrum disorder , 2018, Social cognitive and affective neuroscience.

[26]  C. Tempelmann,et al.  Eddy current correction in diffusion‐weighted imaging using pairs of images acquired with opposite diffusion gradient polarity , 2004, Magnetic resonance in medicine.

[27]  Jean Decety,et al.  Atypical development of white matter microstructure in adolescents with autism spectrum disorders , 2010, NeuroImage.

[28]  C. Haselgrove,et al.  Connectivity in Autism: A Review of MRI Connectivity Studies , 2015, Harvard review of psychiatry.

[29]  I. Rapin,et al.  The genetics of autism. , 2004, Pediatrics.

[30]  M. Casanova,et al.  Studying Autism Spectrum Disorder with Structural and Diffusion Magnetic Resonance Imaging: A Survey , 2016, Front. Hum. Neurosci..

[31]  D. Shukla,et al.  White matter compromise of callosal and subcortical fiber tracts in children with autism spectrum disorder: a diffusion tensor imaging study. , 2010, Journal of the American Academy of Child and Adolescent Psychiatry.

[32]  C. Westin,et al.  An introduction to diffusion tensor image analysis. , 2011, Neurosurgery clinics of North America.

[33]  Diane C. Chugani,et al.  Diffusion Tensor Imaging of Frontal Lobe in Autism Spectrum Disorder , 2008, Cerebral cortex.

[34]  J. Rabe-Jabłońska,et al.  [Affective disorders in the fourth edition of the classification of mental disorders prepared by the American Psychiatric Association -- diagnostic and statistical manual of mental disorders]. , 1993, Psychiatria polska.

[35]  Takashi Yamada,et al.  Linked alterations in gray and white matter morphology in adults with high-functioning autism spectrum disorder: A multimodal brain imaging study , 2014, NeuroImage: Clinical.

[36]  L. Lotspeich,et al.  Similar white matter aberrations in children with autism and their unaffected siblings: a diffusion tensor imaging study using tract-based spatial statistics. , 2010, Archives of general psychiatry.

[37]  P J Basser,et al.  New Histological and Physiological Stains Derived from Diffusion‐Tensor MR Images , 1997, Annals of the New York Academy of Sciences.

[38]  Vittorio Murino,et al.  Case-control discrimination through effective brain connectivity , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[39]  M. Falkmer,et al.  Diagnostic procedures in autism spectrum disorders: a systematic literature review , 2013, European Child & Adolescent Psychiatry.

[40]  Sigal Berman,et al.  Anatomical Abnormalities in Autism? , 2016, Cerebral cortex.

[41]  Mert R. Sabuncu,et al.  3D Convolutional Neural Networks for Classification of Functional Connectomes , 2018, DLMIA/ML-CDS@MICCAI.

[42]  Autism diagnosis as a social process , 2021, Autism : the international journal of research and practice.

[43]  Russell Greiner,et al.  A general prediction model for the detection of ADHD and Autism using structural and functional MRI , 2018, PloS one.

[44]  P. Szeszko,et al.  MRI atlas of human white matter , 2006 .

[45]  Ayman El-Baz,et al.  Computer Aided Autism Diagnosis Using Diffusion Tensor Imaging , 2020, IEEE Access.

[46]  Guido Gerig,et al.  Differences in white matter fiber tract development present from 6 to 24 months in infants with autism. , 2012, The American journal of psychiatry.

[47]  A. Franco,et al.  NeuroImage: Clinical , 2022 .

[48]  Ayman El-Baz,et al.  A Personalized Autism Diagnosis CAD System Using a Fusion of Structural MRI and Resting-State Functional MRI Data , 2019, Front. Psychiatry.

[49]  Daniel P. Kennedy,et al.  Enhancing studies of the connectome in autism using the autism brain imaging data exchange II , 2017, Scientific Data.

[50]  B. Leventhal,et al.  The Autism Diagnostic Observation Schedule—Generic: A Standard Measure of Social and Communication Deficits Associated with the Spectrum of Autism , 2000, Journal of autism and developmental disorders.

[51]  Luke Bloy,et al.  Diffusion based abnormality markers of pathology: Toward learned diagnostic prediction of ASD , 2011, NeuroImage.

[52]  Jan K Buitelaar,et al.  Pervasive microstructural abnormalities in autism: a DTI study. , 2011, Journal of psychiatry & neuroscience : JPN.

[53]  Ayman El-Baz,et al.  Autism Imaging and Devices , 2016 .

[54]  A. Couteur,et al.  Autism Diagnostic Interview-Revised: A revised version of a diagnostic interview for caregivers of individuals with possible pervasive developmental disorders , 1994, Journal of autism and developmental disorders.

[55]  L. Lotspeich,et al.  White matter structure in autism: preliminary evidence from diffusion tensor imaging , 2004, Biological Psychiatry.

[56]  A. Alexander,et al.  Diffusion tensor imaging of the brain , 2007, Neurotherapeutics.

[57]  Aixia Guo,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2014 .