CT radiomics-histopathological correlation for mediastinal lymph node staging in non-small cell lung cancer
Judith Legrand, Antoine Decoux, Loïc Duron, Cécile Di-Rocco, Manuel Gargiulo, Pascal Thomas, Armelle Arnoux, Kathia Chaumoitre · 2026
Read CT radiomics-histopathological correlation for mediastinal lymph node staging in non-small cell lung cancer by Judith Legrand, Antoine Decoux, Loïc Duron, Cécile Di-Rocco, Manuel Gargiulo, Pascal Thomas, Armelle Arnoux, Kathia Chaumoitre (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/plos-pone-0355650.txt.
Description
Judith Legrand and fellow doctors test whether texture patterns on chest CT scans can tell whether chest lymph nodes in lung cancer patients truly hold cancer. Node status decides treatment, and scans alone often mislead. The study looked back at about one hundred ten surgical patients whose nodes looked suspect. Up to three nodes per patient were outlined in three dimensions. Texture features were extracted. Two machine learning models were trained across many repeated splits.
The stronger model sorted malignant from harmless nodes modestly well, far from perfect but better than chance. Three texture features recurred in the winning signatures, all capturing how uneven the node tissue looks. Legrand and colleagues present scan texture as a supporting signal for staging, not a replacement for tissue proof.
Catalog record
| CREATOR | Judith Legrand, Antoine Decoux, Loïc Duron, Cécile Di-Rocco, Manuel Gargiulo, Pascal Thomas, Armelle Arnoux, Kathia Chaumoitre |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 23644 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |