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

Segmentation of Prostate Cancer (PCa) tissues from Gleason gradedhistopathology images is vital for accurate diagnosis. Although deep learning(DL) based segmentation methods achieve state-of-the-art accuracy, they rely onlarge datasets with manual annotations. We propose a method to synthesize forPCa histopathology images by learning the geometrical relationship betweendifferent disease labels using self-supervised learning. We use a weaklysupervised segmentation approach that uses Gleason score to segment thediseased regions and the resulting segmentation map is used to train a ShapeRestoration Network (ShaRe-Net) to predict missing mask segments in aself-supervised manner. Using DenseUNet as the backbone generator architecturewe incorporate latent variable sampling to inject diversity in the imagegeneration process and thus improve robustness. Experiments on multiplehistopathology datasets demonstrate the superiority of our method overcompeting image synthesis methods for segmentation tasks. Ablation studies showthe benefits of integrating geometry and diversity in generating high-qualityimages, and our self-supervised approach with limited class-labeled dataachieves similar performance as fully supervised learning.

Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation