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 success of supervised lesion segmentation algorithms using ComputedTomography (CT) exams depends significantly on the quantity and variability ofsamples available for training. While annotating such data constitutes achallenge itself, the variability of lesions in the dataset also depends on theprevalence of different types of lesions. This phenomenon adds an inherent biasto lesion segmentation algorithms that can be diminished, among differentpossibilities, using aggressive data augmentation methods. In this paper, wepresent a method for implanting realistic lesions in CT slices to provide arich and controllable set of training samples and ultimately improving semanticsegmentation network performances for delineating lesions in CT exams. Ourresults show that implanting synthetic lesions not only improves (up to around12\%) the segmentation performance considering different architectures but alsothat this improvement is consistent among different image synthesis networks.We conclude that increasing the variability of lesions synthetically in termsof size, density, shape, and position seems to improve the performance ofsegmentation models for liver lesion segmentation in CT slices.

Implanting Synthetic Lesions for Improving Liver Lesion Segmentation in CT Exams