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

Whole-Slide Imaging allows for the capturing and digitization ofhigh-resolution images of histological specimen. An automated analysis of suchimages using deep learning models is therefore of high demand. The transformerarchitecture has been proposed as a possible candidate for effectivelyleveraging the high-resolution information. Here, the whole-slide image ispartitioned into smaller image patches and feature tokens are extracted fromthese image patches. However, while the conventional transformer allows for asimultaneous processing of a large set of input tokens, the computationaldemand scales quadratically with the number of input tokens and thusquadratically with the number of image patches. To address this problem wepropose a novel cascaded cross-attention network (CCAN) based on thecross-attention mechanism that scales linearly with the number of extractedpatches. Our experiments demonstrate that this architecture is at least on-parwith and even outperforms other attention-based state-of-the-art methods on twopublic datasets: On the use-case of lung cancer (TCGA NSCLC) our model reachesa mean area under the receiver operating characteristic (AUC) of 0.970 $\pm$0.008 and on renal cancer (TCGA RCC) reaches a mean AUC of 0.985 $\pm$ 0.004.Furthermore, we show that our proposed model is efficient in low-data regimes,making it a promising approach for analyzing whole-slide images inresource-limited settings. To foster research in this direction, we make ourcode publicly available on GitHub: XXX.

Cascaded Cross-Attention Networks for Data-Efficient Whole-Slide Image Classification Using Transformers