Machine Learning methods for Quantitative Radiomic Biomarkers
Maastricht University · Maastro Clinic · +7 more institutions
Abstract
Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used.…
Citation impact
- FWCI
- 49.36
- Percentile
- 100%
- References
- 42
Authors
5- CPChintan ParmarCorresponding
Maastricht University, Maastro Clinic, Indian Statistical Institute
- PGPatrick Großmann
Dana-Farber Cancer Institute
- JBJohan Bussink
Radboud University Nijmegen, Radboud University Medical Center
- PLPhilippe Lambin
Maastricht University, Maastro Clinic
- HJHugo J.W.L. Aerts
Brigham and Women's Hospital, Harvard University, Dana-Farber Cancer Institute, Dana-Farber Brigham Cancer Center
Topics & keywords
- Radiomics
- Random forest
- Feature selection
- Computer science
- Artificial intelligence
- Machine learning
- Wilcoxon signed-rank test
- Stability (learning theory)
- Good health and well-being