 |
International Journal for Research Trends and Innovation
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2456-3315 | Impact factor: 8.14 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
|
Issue: July 2026
Volume 11 | Issue 7
Review Result and Publication of Paper within : 2-3 days
Click Here For more DetailsFor Authors
Forms / Download
Published Issue Details
Editorial Board
Other IMP Links
Facts & Figure
Impact Factor : 8.14
Issue per Year : 12
Volume Published : 11
Issue Published : 122
Article Submitted : 25330
Article Published : 9497
Total Authors : 25208
Total Reviewer : 873
Total Countries : 172
Indexing Partner
Licence
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
Published Paper Details
|
|
| Paper Title: | SSAE-MetaFormer: A Multi-Atlas Transformer Framework for Autism Spectrum Disorder Classification Using Resting-State fMRI |
| Authors Name: | Vinay Marabe , Vaibhav More , Darshan Chandankhede , Sahil Chandankhede , Prof. Kirti Randhe |
| Download E-Certificate: | Download |
| Author Reg. ID: |
IJRTI_213367
|
| Published Paper Id: | IJRTI2606073 |
| Published In: | Volume 11 Issue 6, June-2026 |
| DOI: | |
| Abstract: | Autism Spectrum Disorder (ASD) diagnosis from resting-state functional resting-state functional magnetic resonance imaging (rs-fMRI) remains challenging due to high data dimensionality, small sample sizes, and severe multisite heterogeneity. We propose SSAE-METAFormer V2, a novel deep learning framework that integrates multi-atlas functional connectivity analysis with stacked sparse autoencoder (SSAE) representation learning and transformer-based attention fusion. Our method employs masked self-supervised pretraining on the autoencoder backbone, followed by end-to-end fine-tuning with focal loss and label smoothing. Critically, we evaluate using Leave-One-Site-Out (LOSO) cross-validation — the most rigorous protocol for multi-site neuroimaging data — and optimize hyperparameters via Bayesian search with Optuna. On the ABIDE-I dataset (N = 249 subjects, 14 sites), SSAE-METAFormer V2 achieves 82.61% AUC and 75.90% accuracy under strict LOSO evaluation, with 84.51% AUC on unseen-site crossvalidation. Ablation studies demonstrate that multi-atlas fusion improves performance by 10–15 percentage points over single-atlas baselines, while self-supervised pretraining provides consistent gains across all validation protocols. Compared to recent state-of-the-art methods, including M3ASD (83.21% accuracy), MADE-for-ASD (multi-atlas ensemble), and DAGMNet (91.59% accuracy on multimodal data), our approach offers superior cross-site generalization with significantly fewer parameters and no reliance on structural MRI. The model is deployed in a production FastAPI backend with ~15 ms. GPU inference latency, demonstrating clinical translational potential. |
| Keywords: | Autism Spectrum Disorder, resting-state fMRI, multi-atlas fusion, stacked sparse autoencoder, transformer, self-supervised pretraining, Leave-One-Site-Out crossvalidation, Optuna hyperparameter optimization. |
| Cite Article: | "SSAE-MetaFormer: A Multi-Atlas Transformer Framework for Autism Spectrum Disorder Classification Using Resting-State fMRI ", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2456-3315, Vol.11, Issue 6, page no.a719-a728, June-2026, Available :http://www.ijrti.org/papers/IJRTI2606073.pdf |
| Downloads: | 000135 |
| ISSN: |
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016 An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator |
| Publication Details: |
Published Paper ID: IJRTI2606073
Registration ID:213367
Published In: Volume 11 Issue 6, June-2026
DOI (Digital Object Identifier):
Page No: a719-a728 Country: South Solapur, Maharashatra, India Research Area: Engineering Publisher : IJ Publication Published Paper URL : https://www.ijrti.org/viewpaperforall?paper=IJRTI2606073 Published Paper PDF: https://www.ijrti.org/papers/IJRTI2606073 |
| Share Article: | |
|
Click Here to Download This Article |
|
| Article Preview | |
|
|
|
Major Indexing from www.ijrti.org
| Google Scholar | ResearcherID Thomson Reuters | Mendeley : reference manager | Academia.edu |
| arXiv.org : cornell university library | Research Gate | CiteSeerX | DOAJ : Directory of Open Access Journals |
| DRJI | Index Copernicus International | Scribd | DocStoc |
ISSN Details
 |
 |
|
ISSN: 2456-3315
Impact Factor: 8.14 and ISSN APPROVED,
Journal Starting Year (ESTD) : 2016
DOI (A digital object identifier)
| Providing A digital object identifier by DOI.ONE How to Get DOI? |
Conference
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Important Details
Join RMS/Earn 300
WhatsApp
Click Here
Click Here
Indexing Partner |
|||
| Copyright © 2026 - All Rights Reserved - IJRTI | |||