Reproducibility and Generalizability in Radiomics Modeling: Possible Strategies in Radiologic and Statistical Perspectives

Author: Ji Eun PARK ¹ ; Seo Young PARK ; Hwa Jung KIM ; Ho Sung KIM
Author Information

1. Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea.
Publication Type:Review
Keywords: Radiomics; Reproducibility; Generalizability; Machine learning
MeSH: Machine Learning
From:Korean Journal of Radiology 2019;20(7):1124-1137
CountryRepublic of Korea
Language:English
Abstract: Radiomics, which involves the use of high-dimensional quantitative imaging features for predictive purposes, is a powerful tool for developing and testing medical hypotheses. Radiologic and statistical challenges in radiomics include those related to the reproducibility of imaging data, control of overfitting due to high dimensionality, and the generalizability of modeling. The aims of this review article are to clarify the distinctions between radiomics features and other omics and imaging data, to describe the challenges and potential strategies in reproducibility and feature selection, and to reveal the epidemiological background of modeling, thereby facilitating and promoting more reproducible and generalizable radiomics research.