Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: Glioblastoma, lymphoma, and metastasis - 23/05/23
Abstract |
Background and purpose |
To investigate the diagnostic performance of fully automated radiomics-based models for multiclass classification of a single enhancing brain tumor among glioblastoma, central nervous system lymphoma, and metastasis.
Materials and methods |
The training and test sets were comprised of 538 cases (300 glioblastomas, 73 lymphomas, and 165 metastases) and 169 cases (101 glioblastomas, 29 lymphomas, and 39 metastases), respectively. After fully automated segmentation, radiomic features were extracted. Three conventional machine learning classifiers, including least absolute shrinkage and selection operator (LASSO), adaptive boosting (Adaboost), and support vector machine with the linear kernel (SVC), combined with one of four feature selection methods, including forward sequential feature selection, F score, mutual information, and LASSO, were trained. Additionally, one ensemble classifier based on the three classifiers was used. The diagnostic performance of the optimized models was tested in the test set using the accuracy, F1-macro score, and the area under the receiver operating characteristic curve (AUCROC).
Results |
The best performance was achieved when the LASSO was used as a feature selection method. In the test set, the best performance was achieved by the ensemble classifier, showing an accuracy of 76.3% (95% CI, 70.0–82.7), a F1-macro score of 0.704, and an AUCROC of 0.878.
Conclusion |
Our fully automated radiomics-based models for multiclass classification might be useful for differential diagnosis of a single enhancing brain tumor with a good diagnostic performance and generalizability.
Le texte complet de cet article est disponible en PDF.Graphical abstract |
Highlights |
• | Fully automated radiomics-based models for multiclass classification among glioblastoma, CNS lymphoma, and metastasis presenting as a single enhancing tumor might be useful for differential diagnosis. |
• | In the test set, the best performance of the radiomics-based machine learning models showed an accuracy of 76.3% (95% CI, 70.0–82.7), a F1-macro score of 0.704, and an AUCROC of 0.878. |
• | Fully automated radiomics-based machine learning models demonstrated a good diagnostic performance and generalizability for multiclass differential diagnosis. |
Keywords : Radiomics, Brain tumor, Machine learning, Glioblastoma, Central nervous system lymphoma, Brain metastasis
Abbreviations : LASSO, Adaboost, SVC, AUCROC, CNS, SHAP
Plan
Vol 50 - N° 4
P. 388-395 - juin 2023 Retour au numéroBienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?