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/

Zendy Plus

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

Zendy Tools

Zendy Open

The spectacular response observed in clinical trials of immunotherapy inpatients with previously uncurable Melanoma, a highly aggressive form of skincancer, calls for a better understanding of the cancer-immune interface.Computational pathology provides a unique opportunity to spatially dissect suchinterface on digitised pathological slides. Accurate cellular classification isa key to ensure meaningful results, but is often challenging even withstate-of-art machine learning and deep learning methods.  We propose a hierarchical framework, which mirrors the way pathologistsperceive tumour architecture and define tumour heterogeneity to improve cellclassification methods that rely solely on cell nuclei morphology. The SLICsuperpixel algorithm was used to segment and classify tumour regions in lowresolution H&E-stained histological images of melanoma skin cancer to provide aglobal context. Classification of superpixels into tumour, stroma, epidermisand lumen/white space, yielded a 97.7% training set accuracy and 95.7% testingset accuracy in 58 whole-tumour images of the TCGA melanoma dataset. Thesuperpixel classification was projected down to high resolution images toenhance the performance of a single cell classifier, based on cell nuclearmorphological features, and resulted in increasing its accuracy from 86.4% to91.6%. Furthermore, a voting scheme was proposed to use global context asbiological a priori knowledge, pushing the accuracy further to 92.8%.  This study demonstrates how using the global spatial context can accuratelycharacterise the tumour microenvironment and allow us to extend significantlybeyond single-cell morphological classification.

Capturing global spatial context for accurate cell classification in skin cancer histology