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 visual examination of tissue biopsy sections is fundamental for cancerdiagnosis, with pathologists analyzing sections at multiple magnifications todiscern tumor cells and their subtypes. However, existing attention-basedmultiple instance learning (MIL) models, used for analyzing Whole Slide Images(WSIs) in cancer diagnostics, often overlook the contextual information oftumor and neighboring tiles, leading to misclassifications. To address this, wepropose the Context-Aware Multiple Instance Learning (CAMIL) architecture.CAMIL incorporates neighbor-constrained attention to consider dependenciesamong tiles within a WSI and integrates contextual constraints as priorknowledge into the MIL model. We evaluated CAMIL on subtyping non-small celllung cancer (TCGA-NSCLC) and detecting lymph node (CAMELYON16) metastasis,achieving test AUCs of 0.959\% and 0.975\%, respectively, outperforming otherstate-of-the-art methods. Additionally, CAMIL enhances model interpretabilityby identifying regions of high diagnostic value.

CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images