Stability and reproducibility of computed tomography radiomic features extracted from peritumoral regions of lung cancer lesions
Medical Physics2019Vol. 46(11), pp. 5075–5085
Citations Over TimeTop 10% of 2019 papers
Ilke Tunali, Lawrence Hall, Sandy Napel, Dmitry Cherezov, Albert Güveniş, Robert J. Gillies, Matthew B. Schabath
Abstract
This study identified a subset of stable and reproducible CT radiomic features extracted from the peritumoral region of lung lesions. The stable and reproducible features identified in this study could be applied to a feature selection pipeline for CT radiomic analyses. According to our findings, top performing features in survival models were more likely to be stable and reproducible hence, it may be best practice to utilize them to achieve repeatable studies and reduce the chance of overfitting.
Related Papers
- → The coefficient of concordance for vague data(2006)35 cited
- → Reproducibility and location-stability of radiomic features derived from cone-beam computed tomography: a phantom study(2023)4 cited
- → Grado de concordancia interevaluador de la escala «Nursing Activities Score» en cuidados intensivos(2015)3 cited
- → Comparison of methods for final height assessment in adolescents with a normal variant short stature(2017)1 cited
- → Weighted Alternative Coefficient of Concordance(2023)