Academic Journal
A multi-atlas ensemble learning framework for autism spectrum disorder diagnosis.
| Title: | A multi-atlas ensemble learning framework for autism spectrum disorder diagnosis. |
|---|---|
| Authors: | Liang S; School of Software, Henan University, Kaifeng 475004, People's Republic of China., Zhang Z; School of Software, Henan University, Kaifeng 475004, People's Republic of China., Du W; Institute for Data Engineering and Sciences, University of Saint Joseph, Macau 999078, People's Republic of China., Gu F; Department of Computer Science, College of Staten Island, The City University of New York, Staten Island, NY 10314, United States of America. |
| Source: | Biomedical physics & engineering express [Biomed Phys Eng Express] 2026 Oct 16; Vol. 12 (5). Date of Electronic Publication: 2026 Oct 16. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: IOP Publishing Ltd Country of Publication: England NLM ID: 101675002 Publication Model: Electronic Cited Medium: Internet ISSN: 2057-1976 (Electronic) Linking ISSN: 20571976 NLM ISO Abbreviation: Biomed Phys Eng Express Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Bristol : IOP Publishing Ltd., [2015]- |
| MeSH Terms: | Magnetic Resonance Imaging*/methods , Autism Spectrum Disorder*/diagnostic imaging , Autism Spectrum Disorder*/diagnosis , Deep Learning*, Brain/diagnostic imaging ; Image Processing, Computer-Assisted/methods ; Neuroimaging/methods ; Humans ; Autoencoder ; Algorithms ; Ensemble Learning ; Female ; Multilayer Perceptrons ; Child ; Male |
| Abstract: | Objective.Clinical autism spectrum disorder (ASD) relies on subjective scales and neuroimaging, with traditional approaches suffering from high subjectivity and insufficient feature extraction, increasing misdiagnoses risk.Approach.To improve the diagnostic accuracy, we propose a multimodal ASD prediction network (APN) that integrates resting-state functional magnetic resonance imaging with non-imaging data. Algorithmically, we first introduce a novel cumulative distribution divergence score (CDDS) feature selection method based on the multi-atlas functional connectivity (FC), which quantifies statistical distributional differences between positive and negative samples, effectively addressing the limitations of the traditionalF-score in overlapping or weakly discriminative features. Building upon this, we adapt existing deep learning (DL) paradigms to construct a deep neural architecture (variational autoencoder-denoising autoencoder (VAEA)), combining a variational autoencoder (VAE), a denoising autoencoder, and a multilayer perceptron. The combination of these modules is non-trivial: the novel CDDS first purifies the high-dimensional feature space, enabling the VAEA to learn robust latent probabilistic representations via unsupervised pre-training without suffering from the curse of dimensionality. This is followed by the supervised fine-tuning to optimize parameters. We further incorporate demographic factors including age, full-scale intelligence quotient, and gender via a late-fusion strategy to prevent them from being overshadowed by imaging features, thereby enhancing the discriminability. FC features from three atlases including AAL, CC400, and Dosenbach160 are weighted and integrated to achieve the effective multi-source fusion.Main results.We conduct 10-fold cross-validations on the Autism Brain Imaging Data Exchange (ABIDE) dataset, and the proposed APN achieves 81.63% accuracy, 81.89% sensitivity and 81.46% specificity, significantly outperforming state-of-the-art methods. Interpretability analysis identifies hippocampus, amygdala, and cingulate gyrus as strongly ASD-associated regions, offering neural mechanistic insights.Significance.This study provides an efficient, objective, and interpretable multimodal DL framework for ASD assisted diagnosis, with substantial clinical application and neuroscience value. (© 2026 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.) |
| Contributed Indexing: | Keywords: ASD; computer-aided diagnosis; ensemble learning; feature selection; multi-atlas |
| Entry Date(s): | Date Created: 20261007 Date Completed: 20261016 Latest Revision: 20261016 |
| Update Code: | 20261016 |
| DOI: | 10.1088/2057-1976/aeb128 |
| PMID: | 42843381 |
| Database: | MEDLINE |
| ISSN: | 2057-1976 |
|---|---|
| DOI: | 10.1088/2057-1976/aeb128 |