Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers

To evaluate whether radiomic features from contrast-enhanced computed tomography (CE-CT) can identify DNA mismatch repair deficient (MMR-D) and/or tumor mutational burden-high (TMB-H) endometrial cancers (ECs). Patients who underwent targeted massively parallel sequencing of primary ECs between 2014...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Scientific reports 2020-10, Vol.10 (1), p.17769-17769, Article 17769
Hauptverfasser: Veeraraghavan, Harini, Friedman, Claire F., DeLair, Deborah F., Ninčević, Josip, Himoto, Yuki, Bruni, Silvio G., Cappello, Giovanni, Petkovska, Iva, Nougaret, Stephanie, Nikolovski, Ines, Zehir, Ahmet, Abu-Rustum, Nadeem R., Aghajanian, Carol, Zamarin, Dmitriy, Cadoo, Karen A., Diaz, Luis A., Leitao, Mario M., Makker, Vicky, Soslow, Robert A., Mueller, Jennifer J., Weigelt, Britta, Lakhman, Yulia
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:To evaluate whether radiomic features from contrast-enhanced computed tomography (CE-CT) can identify DNA mismatch repair deficient (MMR-D) and/or tumor mutational burden-high (TMB-H) endometrial cancers (ECs). Patients who underwent targeted massively parallel sequencing of primary ECs between 2014 and 2018 and preoperative CE-CT were included (n = 150). Molecular subtypes of EC were assigned using DNA polymerase epsilon ( POLE ) hotspot mutations and immunohistochemistry-based p53 and MMR protein expression. TMB was derived from sequencing, with > 15.5 mutations-per-megabase as a cut-point to define TMB-H tumors. After radiomic feature extraction and selection, radiomic features and clinical variables were processed with the recursive feature elimination random forest classifier. Classification models constructed using the training dataset (n = 105) were then validated on the holdout test dataset (n = 45). Integrated radiomic-clinical classification distinguished MMR-D from copy number (CN)-low-like and CN-high-like ECs with an area under the receiver operating characteristic curve (AUROC) of 0.78 (95% CI 0.58–0.91). The model further differentiated TMB-H from TMB-low (TMB-L) tumors with an AUROC of 0.87 (95% CI 0.73–0.95). Peritumoral-rim radiomic features were most relevant to both classifications (p ≤ 0.044). Radiomic analysis achieved moderate accuracy in identifying MMR-D and TMB-H ECs directly from CE-CT. Radiomics may provide an adjunct tool to molecular profiling, especially given its potential advantage in the setting of intratumor heterogeneity.
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-72475-9