Oral squamous cell carcinoma diagnosis: an interpretable deep learning approach using multi-scale pathological images
Yuchen Cui, Xiaoli Gao, Wei Guo, Ying Jin, Yu Liu, Yixuan Qin, Zuomin Wang · 2026
Read Oral squamous cell carcinoma diagnosis: an interpretable deep learning approach using multi-scale pathological images by Yuchen Cui, Xiaoli Gao, Wei Guo, Ying Jin, Yu Liu, Yixuan Qin, Zuomin Wang (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/PMC13556042.txt.
Description
Yuchen Cui and six colleagues built in 2026 a deep learning system that reads pathology images to diagnose oral squamous cell carcinoma, a common mouth cancer. Diagnosis today leans on a pathologist's eye, which takes time and varies between observers. Their network, PGMA-Net, was designed to work across microscope magnifications, to cope with images from different hospitals, and to explain its decisions.
Guide maps drawn from pathology knowledge steer the model's attention to the tissue features that matter. Extra modules align features across magnifications, rebalance rare classes during training, and adapt the model to new centres. On an internal test set the system scored high on both discrimination and accuracy, and it held up well on an outside set after adaptation. Visualisations show which regions drove each call, a step toward tools clinicians can trust.
Catalog record
| CREATOR | Yuchen Cui, Xiaoli Gao, Wei Guo, Ying Jin, Yu Liu, Yixuan Qin, Zuomin Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47417 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |