OTLesMix: Wasserstein Barycenter and Optimal Transport Map for Synthetic Lesion Generation with Diverse Shapes and Locations

Robin Trombetta, Carole Lartizien|August 6, 2026arXiv

Key Takeaway

Using optimal transport to blend medical images creates more realistic and varied synthetic lesions than traditional mixing strategies, leading to better segmentation model performance.

Summary

This paper presents OTLesMix, a data augmentation method that uses optimal transport and Wasserstein barycenters to generate synthetic medical images with diverse lesion shapes and locations. Tested on brain lesion segmentation, it improves model performance by 2.9-6.6 Dice points compared to baseline and outperforms existing mixing-based augmentation methods.

data training evaluation

Key Terms

wasserstein-distance optimal-transport data-augmentation image-synthesis dice-score