Decoding Task-Related Functional Brain Imaging Data to Identify Developmental Disorders: The Case of Congenital Amusia

Machine learning classification techniques are frequently applied to structural and resting-state fMRI data to identify brain-based biomarkers for developmental disorders. However, task-related fMRI has rarely been used as a diagnostic tool. Here, we used structural MRI, resting-state connectivity and task-based fMRI data to detect congenital amusia, a pitch-specific developmental disorder. All approaches discriminated amusics from controls in meaningful brain networks at similar levels of accuracy. Interestingly, the classifier outcome was specific to deficit-related neural circuits, as the group classification failed for fMRI data acquired during a verbal task for which amusics were unimpaired. Most importantly, classifier outputs of task-related fMRI data predicted individual behavioral performance on an independent pitch-based task, while this relationship was not observed for structural or resting-state data. These results suggest that task-related imaging data can potentially be used as a powerful diagnostic tool to identify developmental disorders as they allow for the prediction of symptom severity.

[1]  Barbara Tillmann,et al.  Pitch-Responsive Cortical Regions in Congenital Amusia , 2016, The Journal of Neuroscience.

[2]  Vinod Menon,et al.  Functional connectivity in the resting brain: A network analysis of the default mode hypothesis , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Catie Chang,et al.  Applications of Multivariate Pattern Classification Analyses in Developmental Neuroimaging of Healthy and Clinical Populations , 2009, Front. Hum. Neurosci..

[4]  J. Smurzyński,et al.  Pitch identification and discrimination for complex tones with many harmonics , 1990 .

[5]  Hideki Kawahara,et al.  Underlying Principles of a High-quality Speech Manipulation System STRAIGHT and Its Application to Speech Segregation , 2005, Speech Separation by Humans and Machines.

[6]  Damiaan Denys,et al.  Diagnostic neuroimaging markers of obsessive-compulsive disorder: Initial evidence from structural and functional MRI studies , 2019, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[7]  Robert J Zatorre,et al.  Representations of Invariant Musical Categories Are Decodable by Pattern Analysis of Locally Distributed BOLD Responses in Superior Temporal and Intraparietal Sulci. , 2015, Cerebral cortex.

[8]  B. Tillmann,et al.  Altered intrinsic connectivity of the auditory cortex in congenital amusia. , 2016, Journal of neurophysiology.

[9]  Isabelle Peretz,et al.  Morphometry of the amusic brain: a two-site study. , 2006, Brain : a journal of neurology.

[10]  G L Shulman,et al.  INAUGURAL ARTICLE by a Recently Elected Academy Member:A default mode of brain function , 2001 .

[11]  I. Peretz,et al.  Functional MRI evidence of an abnormal neural network for pitch processing in congenital amusia. , 2011, Cerebral cortex.

[12]  Vince D. Calhoun,et al.  Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls , 2017, NeuroImage.

[13]  Alan C. Evans,et al.  Event-Related fMRI of the Auditory Cortex , 1998, NeuroImage.

[14]  Josh H. McDermott,et al.  Cortical Pitch Regions in Humans Respond Primarily to Resolved Harmonics and Are Located in Specific Tonotopic Regions of Anterior Auditory Cortex , 2013, The Journal of Neuroscience.

[15]  I. Peretz,et al.  Specialized neural dynamics for verbal and tonal memory: fMRI evidence in congenital amusia , 2018, Human brain mapping.

[16]  Isabelle Peretz,et al.  Neurobiology of Congenital Amusia , 2016, Trends in Cognitive Sciences.

[17]  Josh H. McDermott,et al.  Distortion products in auditory fMRI research: Measurements and solutions , 2016, NeuroImage.

[18]  V. Williamson,et al.  Memory for pitch in congenital amusia: Beyond a fine-grained pitch discrimination problem , 2010, Memory.

[19]  Karl J. Friston,et al.  Unified segmentation , 2005, NeuroImage.

[20]  Barbara Tillmann,et al.  Does tonality boost short-term memory in congenital amusia? , 2013, Brain Research.

[21]  Barbara Tillmann,et al.  Impaired short-term memory for pitch in congenital amusia , 2016, Brain Research.

[22]  Jérémie Mattout,et al.  Altered retrieval of melodic information in congenital amusia: insights from dynamic causal modeling of MEG data , 2015, Front. Hum. Neurosci..

[23]  Annemarie Seither-Preisler,et al.  Neural Biomarkers for Dyslexia, ADHD, and ADD in the Auditory Cortex of Children , 2016, Front. Neurosci..

[24]  B. Tillmann,et al.  Musical and verbal short‐term memory: insights from neurodevelopmental and neurological disorders , 2018, Annals of the New York Academy of Sciences.

[25]  Rainer Goebel,et al.  Information-based functional brain mapping. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[26]  Lee Friedman,et al.  Report on a multicenter fMRI quality assurance protocol , 2006, Journal of magnetic resonance imaging : JMRI.

[27]  Emmanuel Maby,et al.  Impaired pitch perception and memory in congenital amusia: the deficit starts in the auditory cortex. , 2013, Brain : a journal of neurology.

[28]  Brigitte Landeau,et al.  Morphological brain plasticity induced by musical expertise is accompanied by modulation of functional connectivity at rest , 2014, NeuroImage.

[29]  Gaël Varoquaux,et al.  Cross-validation failure: Small sample sizes lead to large error bars , 2017, NeuroImage.

[30]  M. Ahissar,et al.  Dyslexics’ faster decay of implicit memory for sounds and words is manifested in their shorter neural adaptation , 2017, eLife.

[31]  G. Schlaug,et al.  Tone Deafness: A New Disconnection Syndrome? , 2009, The Journal of Neuroscience.

[32]  I. Peretz,et al.  Varieties of Musical Disorders , 2003, Annals of the New York Academy of Sciences.

[33]  Barbara Tillmann,et al.  Congenital amusia: A short-term memory deficit for non-verbal, but not verbal sounds , 2009, Brain and Cognition.

[34]  Karl J. Friston,et al.  Statistical parametric maps in functional imaging: A general linear approach , 1994 .

[35]  Alan C. Evans,et al.  Cortical Thickness in Congenital Amusia: When Less Is Better Than More , 2007, The Journal of Neuroscience.

[36]  Russell A. Poldrack,et al.  A Coordinate-Based Meta-Analysis of Overlaps in Regional Specialization and Functional Connectivity across Subjective Value and Default Mode Networks , 2017, Front. Neurosci..

[37]  Dina R. Dajani,et al.  Progress and roadblocks in the search for brain-based biomarkers of autism and attention-deficit/hyperactivity disorder , 2017, Translational Psychiatry.

[38]  Martin N. Hebart,et al.  The Decoding Toolbox (TDT): a versatile software package for multivariate analyses of functional imaging data , 2015, Front. Neuroinform..

[39]  Ugur Halici,et al.  A comparative analysis of functional connectivity data in resting and task-related conditions of the brain for disease signature of OCD , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.