A Guide to ComBat Harmonization of Imaging Biomarkers in Multicenter Studies

The impact of PET image acquisition and reconstruction parameters on SUV measurements or radiomic feature values is widely documented. This scanner effect is detrimental to the design and validation of predictive or prognostic models and limits the use of large multicenter cohorts. To reduce the impact of this scanner effect, the ComBat method has been proposed and is now used in various contexts. The purpose of this article is to explain and illustrate the use of ComBat based on practical examples. We also give examples in which the ComBat assumptions are not met and, thus, in which ComBat should not be used.

Automated summary

The impact of PET image acquisition and reconstruction parameters on SUV measurements or radiomic feature values is discussed in this article. The use of the ComBat method to reduce the scanner effect is explained with practical examples. Situations where the ComBat assumptions are not met and should not be used are also presented.