Leveraging TabTransformer Deep Learning on Conventional MRI Radiomics for Accessible and Interpretable Diagnosis of Autism Spectrum Disorder
Radiomics models leveraging routine MRI sequences demonstrate robust diagnostic utility for ASD. The identified subcortical features, correlating with core symptoms, may serve as viable imaging biomarkers. Future work requires external validation, exploration of automated segmentation, and investigation in larger, multi-center cohorts..
Authors
- Baoxin Qian
- Qingling Chen (ORCID: https://orcid.org/0009-0008-0063-2952)
- Ying Wang (ORCID: https://orcid.org/0000-0002-1407-2668)
- Hongsheng Liu (ORCID: https://orcid.org/0000-0002-1054-5704)
- Guojie Wang (ORCID: https://orcid.org/0000-0003-0059-7882)
- Xiaoling Cao (ORCID: https://orcid.org/0009-0004-4024-2191)
Institutions
- Sun Yat-sen University (CN)
- Capital Medical University (CN)
- Guangzhou Women and Children Medical Center (CN)
- Fifth Affiliated Hospital of Sun Yat-sen University (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Neuropsychiatric Disease and Treatment
- Published
- 2025-12-01
- DOI
- https://doi.org/10.2147/ndt.s550477
- Primary Topic
- Autism Spectrum Disorder Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00