Àá½Ã¸¸ ±â´Ù·Á ÁÖ¼¼¿ä. ·ÎµùÁßÀÔ´Ï´Ù.
KMID : 0880420190200071124
Korean Journal of Radiology
2019 Volume.20 No. 7 p.1124 ~ p.1137
Reproducibility and Generalizability in Radiomics Modeling: Possible Strategies in Radiologic and Statistical Perspectives
Park Ji-Eun

Park Seo-Young
Kim Hwa-Jung
Kim Ho-Sung
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.
KEYWORD
Radiomics, Reproducibility, Generalizability, Machine learning
FullTexts / Linksout information
   
Listed journal information
SCI(E) MEDLINE ÇмúÁøÈïÀç´Ü(KCI) KoreaMed ´ëÇÑÀÇÇÐȸ ȸ¿ø