Transformer-based Siamese multimodal imaging model for predicting pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer
Jing Xu, Xin Chen, Yeting Hu, Suyun Li, Qichun Wei, Sebastian M Dieter, Bohai Feng · 2026
Read Transformer-based Siamese multimodal imaging model for predicting pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer by Jing Xu, Xin Chen, Yeting Hu, Suyun Li, Qichun Wei, Sebastian M Dieter, Bohai Feng (2026) 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-13474779.txt.
Description
Jing Xu and co-authors build a twin-network model that reads MRI scans before and after chemoradiation to call whether a rectal tumor vanished completely. Their 2026 study starts from the prize: a true complete response can spare the patient radical surgery. No reliable noninvasive test for it exists.
Scans and records came from 440 patients at three centers. Hand-built radiomic features, over a thousand, joined deep features drawn from a pretrained network and compressed. The Siamese transformer then fused the two time points. In the held-out validation set it scored 0.789 on the grading curve, ahead of early-fusion learners and single-scan models. Decision and calibration checks, plus survival reads, rounded out the grading.
Catalog record
| CREATOR | Jing Xu, Xin Chen, Yeting Hu, Suyun Li, Qichun Wei, Sebastian M Dieter, Bohai Feng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 35 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |