Functional Connectivity-Based Prediction of Autism on Site Harmonized ABIDE Dataset

Overview

Journal IEEE Trans Biomed Eng

Specialties Biomedical Engineering
Biophysics

Date 2021 May 14

PMID 33989150

Citations 23

Authors

Madhura Ingalhalikar

Sumeet Shinde

Arnav Karmarkar

Archith Rajan

D Rangaprakash

Gopikrishna Deshpande

Affiliations

Soon will be listed here.

Abstract

Objective: The larger sample sizes available from multi-site publicly available neuroimaging data repositories makes machine-learning based diagnostic classification of mental disorders more feasible by alleviating the curse of dimensionality. However, since multi-site data are aggregated post-hoc, i.e. they were acquired from different scanners with different acquisition parameters, non-neural inter-site variability may mask inter-group differences that are at least in part neural in origin. Hence, the advantages gained by the larger sample size in the context of machine-learning based diagnostic classification may not be realized.

Methods: We address this issue using harmonization of multi-site neuroimaging data using the ComBat technique, which is based on an empirical Bayes formulation to remove inter-site differences in data distributions, to improve diagnostic classification accuracy. Specifically, we demonstrate this using ABIDE (Autism Brain Imaging Data Exchange) multi-site data for classifying individuals with Autism from healthy controls using resting state fMRI-based functional connectivity data.

Results: Our results show that higher classification accuracies across multiple classification models can be obtained (especially for models based on artificial neural networks) from multi-site data post harmonization with the ComBat technique as compared to without harmonization, outperforming earlier results from existing studies using ABIDE. Furthermore, our network ablation analysis facilitated important insights into autism spectrum disorder pathology and the connectivity in networks shown to be important for classification covaried with verbal communication impairments in Autism.

Conclusion: Multi-site data harmonization using ComBat improves neuroimaging-based diagnostic classification of mental disorders.

Significance: ComBat has the potential to make AI-based clinical decision-support systems more feasible in psychiatry.

Citing Articles

Temporal and spatial variability of large-scale dynamic brain networks in ASD.

Yin S, Sun S, Li J, Feng Y, Zheng L, Chen K Eur Child Adolesc Psychiatry. 2025; .

PMID: 40019496 DOI: 10.1007/s00787-025-02679-9.

Spectral Analysis of Light-Adapted Electroretinograms in Neurodevelopmental Disorders: Classification with Machine Learning.

Constable P, Pinzon-Arenas J, Mercado Diaz L, Lee I, Marmolejo-Ramos F, Loh L Bioengineering (Basel). 2025; 12(1).

PMID: 39851292 PMC: 11761560. DOI: 10.3390/bioengineering12010015.

Extracting interpretable signatures of whole-brain dynamics through systematic comparison.

Bryant A, Aquino K, Parkes L, Fornito A, Fulcher B PLoS Comput Biol. 2024; 20(12):e1012692.

PMID: 39715231 PMC: 11706466. DOI: 10.1371/journal.pcbi.1012692.

Self-supervised graph contrastive learning with diffusion augmentation for functional MRI analysis and brain disorder detection.

Wang X, Fang Y, Wang Q, Yap P, Zhu H, Liu M Med Image Anal. 2024; 101:103403.

PMID: 39637557 PMC: 11875923. DOI: 10.1016/j.media.2024.103403.

Comparison of autism spectrum disorder subtypes based on functional and structural factors.

Wang S, Sun Z, Martinez-Tejada L, Yoshimura N Front Neurosci. 2024; 18:1440222.

PMID: 39429701 PMC: 11486766. DOI: 10.3389/fnins.2024.1440222.

References

Parikh M, Li H, He L . Enhancing Diagnosis of Autism With Optimized Machine Learning Models and Personal Characteristic Data. Front Comput Neurosci. 2019; 13:9. PMC: 6384273. DOI: 10.3389/fncom.2019.00009. View

Johnson W, Li C, Rabinovic A . Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics. 2006; 8(1):118-27. DOI: 10.1093/biostatistics/kxj037. View

Di Martino A, OConnor D, Chen B, Alaerts K, Anderson J, Assaf M . Enhancing studies of the connectome in autism using the autism brain imaging data exchange II. Sci Data. 2017; 4:170010. PMC: 5349246. DOI: 10.1038/sdata.2017.10. View

Fortin J, Parker D, Tunc B, Watanabe T, Elliott M, Ruparel K . Harmonization of multi-site diffusion tensor imaging data. Neuroimage. 2017; 161:149-170. PMC: 5736019. DOI: 10.1016/j.neuroimage.2017.08.047. View

Zhou Y, Shi L, Cui X, Wang S, Luo X . Functional Connectivity of the Caudal Anterior Cingulate Cortex Is Decreased in Autism. PLoS One. 2016; 11(3):e0151879. PMC: 4795711. DOI: 10.1371/journal.pone.0151879. View

Abraham A, Milham M, Di Martino A, Craddock R, Samaras D, Thirion B . Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example. Neuroimage. 2016; 147:736-745. DOI: 10.1016/j.neuroimage.2016.10.045. View

Di Martino A, Yan C, Li Q, Denio E, Castellanos F, Alaerts K . The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol Psychiatry. 2013; 19(6):659-67. PMC: 4162310. DOI: 10.1038/mp.2013.78. View

Ingalhalikar M, Parker W, Bloy L, Roberts T, Verma R . Creating multimodal predictors using missing data: classifying and subtyping autism spectrum disorder. J Neurosci Methods. 2014; 235:1-9. DOI: 10.1016/j.jneumeth.2014.06.030. View

Li H, Parikh N, He L . A Novel Transfer Learning Approach to Enhance Deep Neural Network Classification of Brain Functional Connectomes. Front Neurosci. 2018; 12:491. PMC: 6066582. DOI: 10.3389/fnins.2018.00491. View

10.

Feis R, Smith S, Filippini N, Douaud G, Dopper E, Heise V . ICA-based artifact removal diminishes scan site differences in multi-center resting-state fMRI. Front Neurosci. 2015; 9:395. PMC: 4621866. DOI: 10.3389/fnins.2015.00395. View

11.

Syed M, Yang Z, Hu X, Deshpande G . Investigating Brain Connectomic Alterations in Autism Using the Reproducibility of Independent Components Derived from Resting State Functional MRI Data. Front Neurosci. 2017; 11:459. PMC: 5596295. DOI: 10.3389/fnins.2017.00459. View

12.

Libero L, DeRamus T, Lahti A, Deshpande G, Kana R . Multimodal neuroimaging based classification of autism spectrum disorder using anatomical, neurochemical, and white matter correlates. Cortex. 2015; 66:46-59. PMC: 4782775. DOI: 10.1016/j.cortex.2015.02.008. View

13.

Zhao X, Rangaprakash D, Yuan B, Denney Jr T, Katz J, Dretsch M . Investigating the Correspondence of Clinical Diagnostic Grouping With Underlying Neurobiological and Phenotypic Clusters Using Unsupervised Machine Learning. Front Appl Math Stat. 2018; 4. PMC: 6214192. DOI: 10.3389/fams.2018.00025. View

14.

Retico A, Tosetti M, Muratori F, Calderoni S . Neuroimaging-based methods for autism identification: a possible translational application?. Funct Neurol. 2015; 29(4):231-9. PMC: 4370436. View

15.

OSullivan S, Heinsen H, Grinberg L, Chimelli L, Amaro Jr E, Hilario do Nascimento Saldiva P . The role of artificial intelligence and machine learning in harmonization of high-resolution post-mortem MRI (virtopsy) with respect to brain microstructure. Brain Inform. 2019; 6(1):3. PMC: 6403267. DOI: 10.1186/s40708-019-0096-3. View

16.

Aggarwal P, Gupta A . Multivariate graph learning for detecting aberrant connectivity of dynamic brain networks in autism. Med Image Anal. 2019; 56:11-25. DOI: 10.1016/j.media.2019.05.007. View

17.

Wu G, Liao W, Stramaglia S, Ding J, Chen H, Marinazzo D . A blind deconvolution approach to recover effective connectivity brain networks from resting state fMRI data. Med Image Anal. 2013; 17(3):365-74. DOI: 10.1016/j.media.2013.01.003. View

18.

Fortin J, Cullen N, Sheline Y, Taylor W, Aselcioglu I, Cook P . Harmonization of cortical thickness measurements across scanners and sites. Neuroimage. 2017; 167:104-120. PMC: 5845848. DOI: 10.1016/j.neuroimage.2017.11.024. View

19.

Kassraian-Fard P, Matthis C, Balsters J, Maathuis M, Wenderoth N . Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example. Front Psychiatry. 2016; 7:177. PMC: 5133050. DOI: 10.3389/fpsyt.2016.00177. View

20.

Nielsen J, Zielinski B, Fletcher P, Alexander A, Lange N, Bigler E . Multisite functional connectivity MRI classification of autism: ABIDE results. Front Hum Neurosci. 2013; 7:599. PMC: 3782703. DOI: 10.3389/fnhum.2013.00599. View