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

Supervised deep learning methods have achieved considerable success inmedical image analysis, owing to the availability of large-scale andwell-annotated datasets. However, creating such datasets for whole slide images(WSIs) in histopathology is a challenging task due to their gigapixel size. Inrecent years, self-supervised learning (SSL) has emerged as an alternativesolution to reduce the annotation overheads in WSIs, as it does not requirelabels for training. These SSL approaches, however, are not designed forhandling multi-resolution WSIs, which limits their performance in learningdiscriminative image features. In this paper, we propose a Dual-branch SSLFramework for WSI tumour segmentation (DSF-WSI) that can effectively learnimage features from multi-resolution WSIs. Our DSF-WSI connected two branchesand jointly learnt low and high resolution WSIs in a self-supervised manner.Moreover, we introduced a novel Context-Target Fusion Module (CTFM) and amasked jigsaw pretext task to align the learnt multi-resolution features.Furthermore, we designed a Dense SimSiam Learning (DSL) strategy to maximisethe similarity of different views of WSIs, enabling the learnt representationsto be more efficient and discriminative. We evaluated our method using twopublic datasets on breast and liver cancer segmentation tasks. The experimentresults demonstrated that our DSF-WSI can effectively extract robust andefficient representations, which we validated through subsequent fine-tuningand semi-supervised settings. Our proposed method achieved better accuracy thanother state-of-the-art approaches. Code is available athttps://github.com/Dylan-H-Wang/dsf-wsi.

A Dual-branch Self-supervised Representation Learning Framework for Tumour Segmentation in Whole Slide Images