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

Nuclei segmentation is a fundamental task that is critical for variouscomputational pathology applications including nuclei morphology analysis, celltype classification, and cancer grading. Conventional vision-based methods fornuclei segmentation struggle in challenging cases and deep learning approacheshave proven to be more robust and generalizable. However, CNNs require largeamounts of labeled histopathology data. Moreover, conventional CNN-basedapproaches lack structured prediction capabilities which are required todistinguish overlapping and clumped nuclei. Here, we present an approach tonuclei segmentation that overcomes these challenges by utilizing a conditionalgenerative adversarial network (cGAN) trained with synthetic and real data. Wegenerate a large dataset of H&E training images with perfect nucleisegmentation labels using an unpaired GAN framework. This synthetic data alongwith real histopathology data from six different organs are used to train aconditional GAN with spectral normalization and gradient penalty for nucleisegmentation. This adversarial regression framework enforces higher orderconsistency when compared to conventional CNN models. We demonstrate that thisnuclei segmentation approach generalizes across different organs, sites,patients and disease states, and outperforms conventional approaches,especially in isolating individual and overlapping nuclei.

Deep Adversarial Training for Multi-Organ Nuclei Segmentation in Histopathology Images