Uncertainty-aware automatic TNM staging classification for [18F] Fluorodeoxyglucose PET-CT reports for lung cancer utilising transformer-based language models and multi-task learning
Stephen H Barlow, Sugama Chicklore, Yulan He, Sebastien Ourselin, Thomas Wagner, Anna Barnes, Gary JR Cook · 2024
Read Uncertainty-aware automatic TNM staging classification for [18F] Fluorodeoxyglucose PET-CT reports for lung cancer utilising transformer-based language models and multi-task learning by Stephen H Barlow, Sugama Chicklore, Yulan He, Sebastien Ourselin, Thomas Wagner, Anna Barnes, Gary JR Cook (2024) 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-11657742.txt.
Description
Stephen Barlow and co-authors built a language model system in 2024 that reads lung cancer scan reports and stages the cancer automatically. Staging, called TNM, records tumor size, node spread, and distant spread, but today experts have to read each free-text report by hand. Their classifier adds a fourth task: flagging reports whose stage is ambiguous. About twenty-five hundred reports were labeled by a specialist for training.
The best setup used a clinical language model with all tasks trained together. It matched expert-level scores on the three staging tasks and did well on outside hospital data too. The authors see uses in audits, research cohorts, and decision support. Handling doubtful cases openly is a stated next step.
Catalog record
| CREATOR | Stephen H Barlow, Sugama Chicklore, Yulan He, Sebastien Ourselin, Thomas Wagner, Anna Barnes, Gary JR Cook |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 47 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |