What does this research mean for the field?

Radiomic features derived from contrast-enhanced thoracic CT scans, specifically those measuring nodal heterogeneity, can predict malignancy in clinically positive mediastinal lymph nodes of non-small cell lung cancer patients. Novelty: ClaimNovelty.INCREMENTAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To evaluate the ability of contrast-enhanced CT radiomic features to predict malignancy in clinically positive mediastinal lymph nodes in non-small cell lung cancer.

September 2, 2026PLoS ONEOpen Access

CT radiomics-histopathological correlation for mediastinal lymph node staging in non-small cell lung cancer

View Full Paper

Ask AI

Bookmark

Authors

JLJudith LegrandCentre National de la Recherche Scientifique ADAntoine DecouxInserm LDLoïc DuronInserm

Discussion

Member takes

Implication

Retrospective cohort study demonstrates that CT radiomics predicts mediastinal lymph node malignancy in non-small cell lung cancer, highlighting the diagnostic value of nodal heterogeneity.

Key Points

To evaluate the ability of contrast-enhanced CT radiomic features to predict malignancy in clinically positive mediastinal lymph nodes in non-small cell lung cancer.
Analyzed a retrospective cohort of 110 patients with clinically node-positive non-small cell lung cancer who underwent surgical resection.
Conducted 3D segmentations of up to three lymph nodes per patient and extracted radiomic features reflecting nodal heterogeneity.
Trained and evaluated Random Forest and XGBoost algorithms across 100 iterations of data splitting into training and test sets.
The Random Forest model achieved an area under the curve (AUC) of 0.703, whereas the XGBoost model achieved an AUC of 0.63.
Three heterogeneity features—RootMeanSquared, Grey Level Co-Occurrence Matrix Imc2, and Grey Level Run Length Matrix RunEntropy—were recurrently selected in the predictive radiomic signatures.

Cite This Study

Legrand et al. (2026) studied this question.

synapsesocial.com/papers/6a97e2eac562ede874ec7492 https://doi.org/10.1371/journal.pone.0355650

View Full Paper

Ask AI

Bookmark

Implication

Retrospective cohort study demonstrates that CT radiomics predicts mediastinal lymph node malignancy in non-small cell lung cancer, highlighting the diagnostic value of nodal heterogeneity.

CT radiomics-histopathological correlation for mediastinal lymph node staging in non-small cell lung cancer

Discussion

Member takes

Implication

Key Points

Cite This Study

CT radiomics-histopathological correlation for mediastinal lymph node staging in non-small cell lung cancer

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider