Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers
Abstract 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 bet...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2020-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-020-72475-9 |
| _version_ | 1819023751923105792 |
|---|---|
| author | Harini Veeraraghavan Claire F. Friedman Deborah F. DeLair Josip Ninčević Yuki Himoto Silvio G. Bruni Giovanni Cappello Iva Petkovska Stephanie Nougaret Ines Nikolovski Ahmet Zehir Nadeem R. Abu-Rustum Carol Aghajanian Dmitriy Zamarin Karen A. Cadoo Luis A. Diaz Mario M. Leitao Vicky Makker Robert A. Soslow Jennifer J. Mueller Britta Weigelt Yulia Lakhman |
| author_facet | Harini Veeraraghavan Claire F. Friedman Deborah F. DeLair Josip Ninčević Yuki Himoto Silvio G. Bruni Giovanni Cappello Iva Petkovska Stephanie Nougaret Ines Nikolovski Ahmet Zehir Nadeem R. Abu-Rustum Carol Aghajanian Dmitriy Zamarin Karen A. Cadoo Luis A. Diaz Mario M. Leitao Vicky Makker Robert A. Soslow Jennifer J. Mueller Britta Weigelt Yulia Lakhman |
| author_sort | Harini Veeraraghavan |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-12-21T04:43:53Z |
| format | Article |
| id | doaj.art-039f6ea3eee241349cd91ff919a41db5 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-21T04:43:53Z |
| publishDate | 2020-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-039f6ea3eee241349cd91ff919a41db52022-12-21T19:15:37ZengNature PortfolioScientific Reports2045-23222020-10-0110111010.1038/s41598-020-72475-9Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancersHarini Veeraraghavan0Claire F. Friedman1Deborah F. DeLair2Josip Ninčević3Yuki Himoto4Silvio G. Bruni5Giovanni Cappello6Iva Petkovska7Stephanie Nougaret8Ines Nikolovski9Ahmet Zehir10Nadeem R. Abu-Rustum11Carol Aghajanian12Dmitriy Zamarin13Karen A. Cadoo14Luis A. Diaz15Mario M. Leitao16Vicky Makker17Robert A. Soslow18Jennifer J. Mueller19Britta Weigelt20Yulia Lakhman21Departments of Medical Physics, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterDepartment of Pathology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterDepartment of Pathology, Memorial Sloan Kettering Cancer CenterGynecology Service, Department of Surgery, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterGynecology Service, Department of Surgery, Memorial Sloan Kettering Cancer CenterDepartment of Medicine, Memorial Sloan Kettering Cancer CenterDepartment of Pathology, Memorial Sloan Kettering Cancer CenterGynecology Service, Department of Surgery, Memorial Sloan Kettering Cancer CenterDepartment of Pathology, Memorial Sloan Kettering Cancer CenterBody Imaging Service, Department of Radiology, Memorial Sloan Kettering Cancer CenterAbstract 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.https://doi.org/10.1038/s41598-020-72475-9 |
| spellingShingle | Harini Veeraraghavan Claire F. Friedman Deborah F. DeLair Josip Ninčević Yuki Himoto Silvio G. Bruni Giovanni Cappello Iva Petkovska Stephanie Nougaret Ines Nikolovski Ahmet Zehir Nadeem R. Abu-Rustum Carol Aghajanian Dmitriy Zamarin Karen A. Cadoo Luis A. Diaz Mario M. Leitao Vicky Makker Robert A. Soslow Jennifer J. Mueller Britta Weigelt Yulia Lakhman Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers Scientific Reports |
| title | Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers |
| title_full | Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers |
| title_fullStr | Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers |
| title_full_unstemmed | Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers |
| title_short | Machine learning-based prediction of microsatellite instability and high tumor mutation burden from contrast-enhanced computed tomography in endometrial cancers |
| title_sort | machine learning based prediction of microsatellite instability and high tumor mutation burden from contrast enhanced computed tomography in endometrial cancers |
| url | https://doi.org/10.1038/s41598-020-72475-9 |
| work_keys_str_mv | AT hariniveeraraghavan machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT claireffriedman machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT deborahfdelair machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT josipnincevic machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT yukihimoto machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT silviogbruni machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT giovannicappello machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT ivapetkovska machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT stephanienougaret machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT inesnikolovski machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT ahmetzehir machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT nadeemraburustum machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT carolaghajanian machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT dmitriyzamarin machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT karenacadoo machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT luisadiaz machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT mariomleitao machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT vickymakker machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT robertasoslow machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT jenniferjmueller machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT brittaweigelt machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers AT yulialakhman machinelearningbasedpredictionofmicrosatelliteinstabilityandhightumormutationburdenfromcontrastenhancedcomputedtomographyinendometrialcancers |