Leveraging TabTransformer Deep Learning on Conventional MRI Radiomics for Accessible and Interpretable Diagnosis of Autism Spectrum Disorder
Qingling Chen, Hongsheng Liu, Xiaoling Cao, Baoxin Qian, Guojie Wang, Ying Wang · 2025
Read Leveraging TabTransformer Deep Learning on Conventional MRI Radiomics for Accessible and Interpretable Diagnosis of Autism Spectrum Disorder by Qingling Chen, Hongsheng Liu, Xiaoling Cao, Baoxin Qian, Guojie Wang, Ying Wang (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12701661.txt.
Description
Qingling Chen and co-authors test if traits drawn from standard MRI scans, read by a deep learning model, can help spot autism spectrum disorder in children, in a 2025 study. An easy to reach, easy to read test is a key goal, since expert checks can take long. The team use radiomics, which turns scan images into many measured traits.
The study looks back at 207 children in past records. Of these, 91 have autism and the rest are typical controls. Traits come from four brain parts and two scan types. Three kinds of model are set side by side, among them a transformer model made for table-like data, and all are checked with cross-validation. The team also test links between the scan traits and how strong the signs of autism are, as a search for possible biomarkers.
Catalog record
| CREATOR | Qingling Chen, Hongsheng Liu, Xiaoling Cao, Baoxin Qian, Guojie Wang, Ying Wang |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |