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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The development of medical image segmentation using deep learning cansignificantly support doctors' diagnoses. Deep learning needs large amounts ofdata for training, which also requires data augmentation to extend diversityfor preventing overfitting. However, the existing methods for data augmentationof medical image segmentation are mainly based on models which need to updateparameters and cost extra computing resources. We proposed data augmentationmethods designed to train a high accuracy deep learning network for medicalimage segmentation. The proposed data augmentation approaches are calledKeepMask and KeepMix, which can create medical images by better identifying theboundary of the organ with no more parameters. Our methods achieved betterperformance and obtained more precise boundaries for medical image segmentationon datasets. The dice coefficient of our methods achieved 94.15% (3.04% higherthan baseline) on CHAOS and 74.70% (5.25% higher than baseline) on MSD spleenwith Unet.

Mixing Data Augmentation with Preserving Foreground Regions in Medical Image Segmentation