{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:01:50Z","timestamp":1790208110711,"version":"4.1.0"},"posted":{"date-parts":[[2025,11,2]]},"group-title":"Neuroscience","reference-count":58,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T00:00:00Z","timestamp":1762041600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"award":["Simons Foundation Autism Research Initiative (SFARI Grant 946867)"],"award-info":[{"award-number":["Simons Foundation Autism Research Initiative (SFARI Grant 946867)"]}],"id":[{"id":"https:\/\/ror.org\/01cmst727","id-type":"ROR","asserted-by":"publisher"}]},{"name":"National Institute of Mental Health","award":["NIMH (R01 MH118500)"],"award-info":[{"award-number":["NIMH (R01 MH118500)"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,21]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Autism Spectrum Disorder (ASD) is a developmental disorder characterized by heterogeneity in social and emotional responses, language, and behavior. Assessments such as the Social Responsiveness Scale (SRS) can quantify this variability but understanding underlying mechanisms and identifying distinct and shared atypical organization and function of brain networks remains a challenge. Convolutional Neural Networks (CNNs) have been used to analyze imaging data. However, the relationship between structural brain changes observed in structural MRI (sMRI), the affected brain functional networks inferred from these structural changes, and their connection to ASD phenotypes and scores still requires systematic investigation. In this study, we used 3D CNNs to conduct a comprehensive analysis of macrostructural changes in ASD. We found consistently dominant involvement of (a) the left hemisphere, (b) the frontal and temporal lobe, and (c) the default mode network and dorsal\/ventral attention networks in ASD. Our systematic AI approach utilized the phenotypic heterogeneity and spectral nature of ASD to uncover significant structural changes across brain regions and functional networks, correlating the structural, functional, and phenotypical heterogeneity of individuals with ASD. This enabled us to identify known and novel global and local brain region and network changes in ASD in relation to phenotypes and clinical scores that can guide diagnostic subtyping.<\/jats:p>\n                <jats:sec>\n                  <jats:title>Teaser (one sentence summary)<\/jats:title>\n                  <jats:p>We used machine learning approaches to characterize the phenotypic and imaging-derived structural heterogeneity of ASD with the aim to identify the brain regions and networks linked to its cognitive and behavioral phenotypes.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.11.02.686152","type":"posted-content","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T08:40:13Z","timestamp":1762159213000},"source":"Crossref","is-referenced-by-count":1,"title":["Structural changes in autism reflect atypical brain network organization and phenotypical heterogeneity: a deep network approach"],"prefix":"10.64898","author":[{"given":"Siddharth","family":"Lokray","sequence":"first","affiliation":[{"name":"Computational Neuroscience and Vision Laboratory, Department of Psychological and Brain Sciences, Boston University, Boston, MA, 02215 United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8834-5104","authenticated-orcid":false,"given":"Basilis","family":"Zikopoulos","sequence":"additional","affiliation":[{"name":"Graduate Program for Neuroscience, Boston University, Boston, MA, United States"},{"name":"Center for Systems Neuroscience, Boston University, Boston, MA, United States"},{"name":"Human Systems Neuroscience Laboratory, Department of Health Sciences, Program in Human Physiology, Boston University, Boston, MA, 02215 United States"},{"name":"Department of Anatomy & Neurobiology, Boston University School of Medicine, Boston, MA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2792-6770","authenticated-orcid":false,"given":"Arash","family":"Yazdanbakhsh","sequence":"additional","affiliation":[{"name":"Computational Neuroscience and Vision Laboratory, Department of Psychological and Brain Sciences, Boston University, Boston, MA, 02215 United States"},{"name":"Graduate Program for Neuroscience, Boston University, Boston, MA, United States"},{"name":"Center for Systems Neuroscience, Boston University, Boston, MA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026092316201380000_2025.11.02.686152v3.1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00196-1"},{"key":"2026092316201380000_2025.11.02.686152v3.2","doi-asserted-by":"publisher","DOI":"10.1126\/science.abm2461"},{"key":"2026092316201380000_2025.11.02.686152v3.3","doi-asserted-by":"crossref","unstructured":"Amaral, David G. , Derek Sayre Andrews , and Christine Wu Nordahl . 2024. \u2018Structural Brain Imaging Biomarkers of Autism Spectrum Disorder\u2019. Pp. 491\u2013509 in.","DOI":"10.1007\/978-3-031-69491-2_17"},{"key":"2026092316201380000_2025.11.02.686152v3.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2007.12.005"},{"key":"2026092316201380000_2025.11.02.686152v3.5","doi-asserted-by":"publisher","DOI":"10.1002\/aur.2875"},{"key":"2026092316201380000_2025.11.02.686152v3.6","doi-asserted-by":"publisher","DOI":"10.1080\/87565640701190841"},{"key":"2026092316201380000_2025.11.02.686152v3.7","doi-asserted-by":"publisher","DOI":"10.1177\/0734282913517525"},{"key":"2026092316201380000_2025.11.02.686152v3.8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.00625"},{"key":"2026092316201380000_2025.11.02.686152v3.9","doi-asserted-by":"crossref","unstructured":"Chaichana, Kaisorn , and Alfredo Qui\u00f1ones-Hinojosa . 2019. Comprehensive Overview of Modern Surgical Approaches to Intrinsic Brain Tumors. Elsevier.","DOI":"10.1016\/B978-0-12-811783-5.05001-1"},{"key":"2026092316201380000_2025.11.02.686152v3.10","doi-asserted-by":"publisher","DOI":"10.1097\/01.wnr.0000239956.45448.4c"},{"key":"2026092316201380000_2025.11.02.686152v3.11","doi-asserted-by":"publisher","DOI":"10.1097\/00004728-199403000-00005"},{"key":"2026092316201380000_2025.11.02.686152v3.12","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.1998.0395"},{"key":"2026092316201380000_2025.11.02.686152v3.13","doi-asserted-by":"publisher","DOI":"10.1002\/aur.2842"},{"key":"2026092316201380000_2025.11.02.686152v3.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.06.010"},{"key":"2026092316201380000_2025.11.02.686152v3.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.pnpbp.2017.07.027"},{"key":"2026092316201380000_2025.11.02.686152v3.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsych.2024.08.008"},{"key":"2026092316201380000_2025.11.02.686152v3.17","doi-asserted-by":"publisher","DOI":"10.1001\/archgenpsychiatry.2011.1251"},{"key":"2026092316201380000_2025.11.02.686152v3.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2009.08.024"},{"key":"2026092316201380000_2025.11.02.686152v3.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021"},{"key":"2026092316201380000_2025.11.02.686152v3.20","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.93.2.719"},{"key":"2026092316201380000_2025.11.02.686152v3.21","doi-asserted-by":"publisher","DOI":"10.1002\/spe.4380211102"},{"key":"2026092316201380000_2025.11.02.686152v3.22","unstructured":"Griffiths, Paul D. , Janet Morris , Jeanne-Claudie Larroche , and Michael Reeves . 2010. Atlas of Fetal and Postnatal Brain MR. Elsevier."},{"key":"2026092316201380000_2025.11.02.686152v3.23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.20317"},{"key":"2026092316201380000_2025.11.02.686152v3.24","doi-asserted-by":"crossref","unstructured":"He, Kaiming , Xiangyu Zhang , Shaoqing Ren , and Jian Sun . 2015. \u2018Deep Residual Learning for Image Recognition\u2019.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026092316201380000_2025.11.02.686152v3.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jchemneu.2021.101925"},{"key":"2026092316201380000_2025.11.02.686152v3.26","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhl006"},{"key":"2026092316201380000_2025.11.02.686152v3.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.03.010"},{"key":"2026092316201380000_2025.11.02.686152v3.28","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1214533110"},{"key":"2026092316201380000_2025.11.02.686152v3.29","doi-asserted-by":"crossref","unstructured":"Khosla, Meenakshi , Keith Jamison , Amy Kuceyeski , and Mert Sabuncu . 2018. \u20183D Convolutional Neural Networks for Classification of Functional Connectomes\u2019.","DOI":"10.1007\/978-3-030-00889-5_16"},{"key":"2026092316201380000_2025.11.02.686152v3.30","doi-asserted-by":"crossref","unstructured":"Li, Xiaoxiao , Nicha C. Dvornek , Xenophon Papademetris , Juntang Zhuang , Lawrence H. Staib , Pamela Ventola , and James S. Duncan . 2018. \u20182-Channel Convolutional 3D Deep Neural Network (2CC3D) for FMRI Analysis: ASD Classification and Feature Learning\u2019. Pp.1252\u201355 in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). IEEE.","DOI":"10.1109\/ISBI.2018.8363798"},{"key":"2026092316201380000_2025.11.02.686152v3.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpsc.2022.01.007"},{"key":"2026092316201380000_2025.11.02.686152v3.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaac.2017.03.013"},{"key":"2026092316201380000_2025.11.02.686152v3.33","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)00115-X"},{"key":"2026092316201380000_2025.11.02.686152v3.34","doi-asserted-by":"publisher","DOI":"10.1007\/BF02172145"},{"key":"2026092316201380000_2025.11.02.686152v3.35","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.10"},{"key":"2026092316201380000_2025.11.02.686152v3.36","doi-asserted-by":"publisher","DOI":"10.1177\/1362361318755318"},{"key":"2026092316201380000_2025.11.02.686152v3.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.mri.2007.08.006"},{"key":"2026092316201380000_2025.11.02.686152v3.38","doi-asserted-by":"publisher","DOI":"10.1002\/mrdd.20141"},{"key":"2026092316201380000_2025.11.02.686152v3.39","unstructured":"NetworkX Developers. 2025. \u2018Spring_layout in NetworkX, Network Analysis in Python\u2019."},{"key":"2026092316201380000_2025.11.02.686152v3.40","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/1357853"},{"key":"2026092316201380000_2025.11.02.686152v3.41","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0777-07.2007"},{"key":"2026092316201380000_2025.11.02.686152v3.42","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcn.2018.12.001"},{"key":"2026092316201380000_2025.11.02.686152v3.43","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2013.08.011"},{"key":"2026092316201380000_2025.11.02.686152v3.44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-86210-6"},{"key":"2026092316201380000_2025.11.02.686152v3.45","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhr162"},{"key":"2026092316201380000_2025.11.02.686152v3.46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2004.07.051"},{"key":"2026092316201380000_2025.11.02.686152v3.47","first-page":"3319","article-title":"Axiomatic Attribution for Deep Networks","volume":"70","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"2026092316201380000_2025.11.02.686152v3.48","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2013.10.001"},{"key":"2026092316201380000_2025.11.02.686152v3.49","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awn099"},{"key":"2026092316201380000_2025.11.02.686152v3.50","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2013.104"},{"key":"2026092316201380000_2025.11.02.686152v3.51","doi-asserted-by":"publisher","DOI":"10.1007\/s00429-017-1450-y"},{"key":"2026092316201380000_2025.11.02.686152v3.52","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsych.2010.07.012"},{"key":"2026092316201380000_2025.11.02.686152v3.53","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.180.2.2068316"},{"key":"2026092316201380000_2025.11.02.686152v3.54","doi-asserted-by":"publisher","DOI":"10.1002\/aur.70135"},{"key":"2026092316201380000_2025.11.02.686152v3.55","doi-asserted-by":"crossref","unstructured":"Zhao, Yu , Fangfei Ge , Shu Zhang , and Tianming Liu . 2018. \u20183D Deep Convolutional Neural Network Revealed the Value of Brain Network Overlap in Differentiating Autism Spectrum Disorder from Healthy Controls\u2019. Pp. 172\u201380 in.","DOI":"10.1007\/978-3-030-00931-1_20"},{"key":"2026092316201380000_2025.11.02.686152v3.56","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2257-10.2010"},{"key":"2026092316201380000_2025.11.02.686152v3.57","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.2004559"},{"key":"2026092316201380000_2025.11.02.686152v3.58","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-018-1904-1"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.11.02.686152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T23:20:22Z","timestamp":1790205622000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.11.02.686152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,2]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1101\/2025.11.02.686152","relation":{},"subject":[],"published":{"date-parts":[[2025,11,2]]},"subtype":"preprint"}}