Value of the DeepSeek-R1 large language model in extracting structured data from magnetic resonance imaging reports of rectal cancer and assisting in tumor staging

Fan Xie, Li-Zhu Ouyang, Bao-Liang Guo, Xi-Yi Huang, Zi-Wei Liu, Lan-Ni Zhou, Jia-Ling Pan, Li-Wen Wang, Ming Chen, Yun-Jing Li, Qiong-Qi Lin, Xin-Jie Chen, Qiu-Gen Hu, Fu-Sheng Ouyang · 2026

Read Value of the DeepSeek-R1 large language model in extracting structured data from magnetic resonance imaging reports of rectal cancer and assisting in tumor staging by Fan Xie, Li-Zhu Ouyang, Bao-Liang Guo, Xi-Yi Huang, Zi-Wei Liu, Lan-Ni Zhou, Jia-Ling Pan, Li-Wen Wang, Ming Chen, Yun-Jing Li, Qiong-Qi Lin, Xin-Jie Chen, Qiu-Gen Hu, Fu-Sheng Ouyang (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/PMC13350363.txt.

Description

Fan Xie and colleagues tested the DeepSeek-R1 language model in 2026 for turning free-text rectal cancer MRI reports into structured data and helping stage tumours. Structured reports aid treatment planning, but radiologists vary in whether they like writing them.

The study used 465 reports, with 60 spent tuning the task and screening several model families and sizes. The best performer was then judged on staging the tumour's depth and node status, scored for accuracy and speed. If a model can reliably mine old free-text reports, hospitals gain tidy data for research and quality checks without forcing doctors to change how they write.

Catalog record

CREATORFan Xie, Li-Zhu Ouyang, Bao-Liang Guo, Xi-Yi Huang, Zi-Wei Liu, Lan-Ni Zhou, Jia-Ling Pan, Li-Wen Wang, Ming Chen, Yun-Jing Li, Qiong-Qi Lin, Xin-Jie Chen, Qiu-Gen Hu, Fu-Sheng Ouyang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE43196
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13350363

Browse the full library · About the Tower of Babel