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

Determining early-stage prognostic markers and stratifying patients foreffective treatment are two key challenges for improving outcomes for melanomapatients. Previous studies have used tumour transcriptome data to stratifypatients into immune subgroups, which were associated with differentialmelanoma specific survival and potential treatment strategies. However,acquiring transcriptome data is a time-consuming and costly process. Moreover,it is not routinely used in the current clinical workflow. Here we attempt toovercome this by developing deep learning models to classify gigapixel H&Estained pathology slides, which are well established in clinical workflows,into these immune subgroups. Previous subtyping approaches have employedsupervised learning which requires fully annotated data, or have only examinedsingle genetic mutations in melanoma patients. We leverage a multiple-instancelearning approach, which only requires slide-level labels and uses an attentionmechanism to highlight regions of high importance to the classification.Moreover, we show that pathology-specific self-supervised models generatebetter representations compared to pathology-agnostic models for improving ourmodel performance, achieving a mean AUC of 0.76 for classifying histopathologyimages as high or low immune subgroups. We anticipate that this method mayallow us to find new biomarkers of high importance and could act as a tool forclinicians to infer the immune landscape of tumours and stratify patients,without needing to carry out additional expensive genetic tests.

Weakly-supervised learning for image-based classification of primary melanomas into genomic immune subgroups