Enhancing generalization in whole-body MRI-based deep learning models: A novel data augmentation pipeline for cross-platform adaptation

Whole-body magnetic resonance imaging (WB-MRI) is a critical diagnostic tool in clinical practice. However, the manual interpretation of WB-MRI scans is a time-consuming and labor-intensive process. Integrating artificial intelligence (AI) has the potential to streamline these processes, yet the variability in MRI images due to differences in scanner features presents significant challenges for the generalization of AI models across different platforms. This study aims to address these challenges by developing and validating a data augmentation pipeline designed to effectively represent image artifacts from WB-MRI acquisition. The study employs a WB-MRI database to evaluate the generalization power of a segmentation model across platforms, with performance metrics such as the Dice Similarity Coefficient (DSC) and Area Under the Curve (AUC) being reported. The findings suggest that advanced data augmentation techniques can mitigate the impact of scanner variability, thereby enhancing the generalization capabilities of AI models in the context of WB-MRI analysis. • Introduced a novel data augmentation for training AI models in Whole-Body MRI (WB-MRI). • It improves the generalization capacity across scanners from different vendors. • Utilizes specific methods that are adequate for MRI artifacts. • Achieved superior segmentation accuracy compared to other augmentation methods. • It preserves results across platforms.