Hello. I 've read a few articles regarding the Harmonization at feature level in Radiomics. The reason for using Harmonization methods is the need to remove the variability in Radiomic feature values () which is the result of the technical variability across scans, including heterogeneity in the imaging protocol, variations in the scanning parameters and differences in the scanner manufacturers. By harmonizing the Radiomic features, it is possible to combine large-scale imaging studies to increase the power of statistical analyses to test common biological hypothesis. There are several Harmonization methods [1] such as ComBat, global scaling and functional normalization. Some like ComBat was initially used as a harmonization method for genomic features. Is harmonization also applied in the case of Pathomic features?

[1] Fortin, J. P., Parker, D., Tunç, B., Watanabe, T., Elliott, M. A., Ruparel, K., ... & Schultz, R. T. (2017). Harmonization of multi-site diffusion tensor imaging data. Neuroimage, 161, 149-170.

More Constantinos Spanakis's questions See All
Similar questions and discussions