English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Brain lesion segmentation provides a valuable tool for clinical diagnosis,and convolutional neural networks (CNNs) have achieved unprecedented success inthe task. Data augmentation is a widely used strategy that improves thetraining of CNNs, and the design of the augmentation method for brain lesionsegmentation is still an open problem. In this work, we propose a simple dataaugmentation approach, dubbed as CarveMix, for CNN-based brain lesionsegmentation. Like other "mix"-based methods, such as Mixup and CutMix,CarveMix stochastically combines two existing labeled images to generate newlabeled samples. Yet, unlike these augmentation strategies based on imagecombination, CarveMix is lesion-aware, where the combination is performed withan attention on the lesions and a proper annotation is created for thegenerated image. Specifically, from one labeled image we carve a region ofinterest (ROI) according to the lesion location and geometry, and the size ofthe ROI is sampled from a probability distribution. The carved ROI thenreplaces the corresponding voxels in a second labeled image, and the annotationof the second image is replaced accordingly as well. In this way, we generatenew labeled images for network training and the lesion information ispreserved. To evaluate the proposed method, experiments were performed on twobrain lesion datasets. The results show that our method improves thesegmentation accuracy compared with other simple data augmentation approaches.

CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation