A transformer-based multimodal deep learning model for preoperative prediction of Ki-67 expression level in glioma
Liu Liu, Fangfang Hu, Minquan Lai, Xianjing Zhao, Pinggui Lei, Zhenwei Yao, Bing Fan · 2026
Read A transformer-based multimodal deep learning model for preoperative prediction of Ki-67 expression level in glioma by Liu Liu, Fangfang Hu, Minquan Lai, Xianjing Zhao, Pinggui Lei, Zhenwei Yao, Bing Fan (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/PMC13520492.txt.
Description
Liu and colleagues develop in 2026 a transformer-based imaging model that predicts a growth marker called Ki-67 in glioma brain tumours before surgery, using routine MRI scans. Marker level guides prognosis, yet normally requires tissue after an operation or biopsy.
Records for 421 patients with grade 2 to 4 gliomas from two hospitals were split into training, internal check and external check sets. Tumours were outlined in three dimensions on two enhanced scan types. Single-scan and combined models all sorted marker level well, with the combined design then compared against three standard network types. Strong external results support further clinical testing.
Catalog record
| CREATOR | Liu Liu, Fangfang Hu, Minquan Lai, Xianjing Zhao, Pinggui Lei, Zhenwei Yao, Bing Fan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40538 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |