Impact of ComBat harmonization on MRI radiomic-analysis of nasopharyngeal carcinoma: a dual-center study
Wei Pei, Yunyun Wei, Penghao Lai, Lili Mao, Xia Huang, Danke Su, Hai Liao, Shaolu Lu · 2026
Read Impact of ComBat harmonization on MRI radiomic-analysis of nasopharyngeal carcinoma: a dual-center study by Wei Pei, Yunyun Wei, Penghao Lai, Lili Mao, Xia Huang, Danke Su, Hai Liao, Shaolu Lu (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-13193936.txt.
Description
MRI texture features can help predict survival in throat cancer, but scanners at different hospitals speak different dialects. Wei Pei and co-authors test a statistical fix called ComBat in a 2026 two-center study.
The study covered 573 patients with locally advanced cancer of the nasopharynx. One hospital's stronger scanner set the reference; the other's weaker scanner data were adjusted with ComBat. Before adjustment, texture features split clearly by hospital, a sign of batch noise. After adjustment, the features lined up far better. A model mixing texture and clinical factors was then built to predict survival. Harmonized data, the authors suggest, let small centers pool scans with big ones.
Catalog record
| CREATOR | Wei Pei, Yunyun Wei, Penghao Lai, Lili Mao, Xia Huang, Danke Su, Hai Liao, Shaolu Lu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |