Generalized ComBat harmonization methods for radiomic features with multi-modal distributions and multiple batch effects

Abstract

Radiomic features have a wide range of clinical applications, but variability due to image acquisition factors can affect their performance. The harmonization tool ComBat is a promising solution but is limited by inability to harmonize multimodal distributions, unknown imaging parameters, and multiple imaging parameters. In this study, we propose two methods for addressing these limitations. We propose a sequential method that allows for harmonization of radiomic features by multiple imaging parameters (Nested ComBat). We also employ a Gaussian Mixture Model (GMM)-based method (GMM ComBat) where scans are split into groupings based on the shape of the distribution used for harmonization as a batch effect and subsequent harmonization by a known imaging parameter. These two methods were evaluated on features extracted with CapTK and PyRadiomics from two public lung computed tomography datasets. We found that Nested ComBat exhibited similar performance to standard ComBat in reducing the percentage of features with statistically significant differences in distribution attributable to imaging parameters. GMM ComBat improved harmonization performance over standard ComBat (− 11%, − 10% for Lung3/CAPTK, Lung3/PyRadiomics harmonizing by kernel resolution). Features harmonized with a variant of the Nested method and the GMM split method demonstrated similar c-statistics and Kaplan–Meier curves when used in survival analyses.

Molecular subtype classification of low‐grade gliomas using magnetic resonance imaging‐based radiomics and machine learning

“…We were also unable to collect some data for a complete statistical survey. Also, if the original data can be retrieved from different institutes, ComBat harmonization methods 52 can be employed to harmonize the radiomics features of our data. Moreover, imbalanced data also occurred in our dataset.…”

matRadiomics: A Novel and Complete Radiomics Framework, from Image Visualization to Predictive Model

“…Finally, as a further development, matRadiomics will be improved by adding new automatic and semi-automatic segmentation algorithms, as already reported above [ 24 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ], support for more file formats (e.g., NIfTi) [ 38 ], more advanced harmonization methods [ 39 ], and co-registration of multi-modal images [ 40 ].…”

Long-term effect of childhood trauma: Role of inflammation and white matter in mood disorders

“…To overcome possible biases related to the use of two different scanners we utilized the ComBat approach( Johnson et al, 2007 ) for harmonization of the DTI data. Harmonization tries to control for “batch effects” of data taken using different equipment or at different locations and times and this specific method works by utilizing the Empirical Bayes method to better estimate parameters of location and scale( Eshaghzadeh Torbati et al, 2021 ; Horng et al, 2022 ; Johnson et al, 2007 ). The ComBat model was reconfigured for DTI analysis and has proved to be the most efficient approach for adjusting for inter-scanner and site variability in DTI scans compared to other harmonization techniques ( Fortin et al, 2017 ).…”