The Diagnostic Value of Deep Learning for Multi-Classification of Rectal Cancer T Staging Based on Regional Attention
Chenyang Qiu, Yihui Xia, Zhiguo Feng, Kaige Liu, Rulei Zhong, Hongwu Liu, Hantao Zhang, Weidong Guo, Shouhong Wan, Wanqin Wang, Bingbing Zou · 2026
Read The Diagnostic Value of Deep Learning for Multi-Classification of Rectal Cancer T Staging Based on Regional Attention by Chenyang Qiu, Yihui Xia, Zhiguo Feng, Kaige Liu, Rulei Zhong, Hongwu Liu, Hantao Zhang, Weidong Guo, Shouhong Wan, Wanqin Wang, Bingbing Zou (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-13206658.txt.
Description
Chenyang Qiu and co-authors test a 2026 deep learning model that stages rectal cancer from CT scans with a focus on the tumour zone. Knowing how deep a tumour has grown, its T stage, guides surgery and care choices. Hand-drawn feature methods can stage such scans, but a model that attends to the lesion zone may do better.
The study drew 500 patients, split into 400 for training and 100 for a check set. Doctors marked the lesion zones by hand on each scan. The focus model sorted early versus late stage with a strong score that beat ten hand-feature models and a clinic-data model. It also beat the best hand-feature model at the full four-stage task. The results back scan models that centre on the lesion zone.
Catalog record
| CREATOR | Chenyang Qiu, Yihui Xia, Zhiguo Feng, Kaige Liu, Rulei Zhong, Hongwu Liu, Hantao Zhang, Weidong Guo, Shouhong Wan, Wanqin Wang, Bingbing Zou |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |