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

Cytopathology report generation is a necessary step for the standardizedexamination of pathology images. However, manually writing detailed reportsbrings heavy workloads for pathologists. To improve efficiency, some existingworks have studied automatic generation of cytopathology reports, mainly byapplying image caption generation frameworks with visual encoders originallyproposed for natural images. A common weakness of these works is that they donot explicitly model the structural information among cells, which is a keyfeature of pathology images and provides significant information for makingdiagnoses. In this paper, we propose a novel graph-based framework calledGNNFormer, which seamlessly integrates graph neural network (GNN) andTransformer into the same framework, for cytopathology report generation. Tothe best of our knowledge, GNNFormer is the first report generation method thatexplicitly models the structural information among cells in pathology images.It also effectively fuses structural information among cells, fine-grainedmorphology features of cells and background features to generate high-qualityreports. Experimental results on the NMI-WSI dataset show that GNNFormer canoutperform other state-of-the-art baselines.

GNNFormer: A Graph-based Framework for Cytopathology Report Generation