Reproducibility and Generalizability in Radiomics Modeling: Possible Strategies in Radiologic and Statistical Perspectives
Ji Eun ParkDepartment of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, KoreaSeo Young ParkDepartment of Clinical Epidemiology and Biostatistics, University of Ulsan College of Medicine, Asan Medical Center, Seoul, KoreaHwa Jung KimUniversity of UlsanHo Sung KimDepartment of Clinical Epidemiology and Biostatistics, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea
2019en
ABI
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.
Identifiers
Citations and references
Cited by 20 references