Comment on Ibrahim et al. The Effects of In-Plane Spatial Resolution on CT-Based Radiomic Features’ Stability with and without ComBat Harmonization. Cancers 2021 13 1848

摘要

We read with great interest the paper by Ibrahim et al. [1], dealing with the harmonization of radiomic feature values extracted from CT images using the ComBat method. Using phantom data, the authors studied the effect of 10 different image resampling methods and ComBat harmonization on the reproducibility of radiomic features. They concluded stating the superiority of resampling methods over harmonization using ComBat. However, we would like to discuss some points in the study that we believe may mislead users of ComBat.