English

LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentation

Image and Video Processing 2023-08-21 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Data augmentation has become a de facto component of deep learning-based medical image segmentation methods. Most data augmentation techniques used in medical imaging focus on spatial and intensity transformations to improve the diversity of training images. They are often designed at the image level, augmenting the full image, and do not pay attention to specific abnormalities within the image. Here, we present LesionMix, a novel and simple lesion-aware data augmentation method. It performs augmentation at the lesion level, increasing the diversity of lesion shape, location, intensity and load distribution, and allowing both lesion populating and inpainting. Experiments on different modalities and different lesion datasets, including four brain MR lesion datasets and one liver CT lesion dataset, demonstrate that LesionMix achieves promising performance in lesion image segmentation, outperforming several recent Mix-based data augmentation methods. The code will be released at https://github.com/dogabasaran/lesionmix.

Keywords

Cite

@article{arxiv.2308.09026,
  title  = {LesionMix: A Lesion-Level Data Augmentation Method for Medical Image Segmentation},
  author = {Berke Doga Basaran and Weitong Zhang and Mengyun Qiao and Bernhard Kainz and Paul M. Matthews and Wenjia Bai},
  journal= {arXiv preprint arXiv:2308.09026},
  year   = {2023}
}

Comments

13 pages, 5 figures, 4 tables, MICCAI DALI Workshop 2023

R2 v1 2026-06-28T11:58:01.660Z