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

Histopathological cancer diagnostics has become more complex, and theincreasing number of biopsies is a challenge for most pathology laboratories.Thus, development of automatic methods for evaluation of histopathologicalcancer sections would be of value. In this study, we used 624 whole slideimages (WSIs) of breast cancer from a Norwegian cohort. We propose a cascadedconvolutional neural network design, called H2G-Net, for semantic segmentationof gigapixel histopathological images. The design involves a detection stageusing a patch-wise method, and a refinement stage using a convolutionalautoencoder. To validate the design, we conducted an ablation study to assessthe impact of selected components in the pipeline on tumour segmentation.Guiding segmentation, using hierarchical sampling and deep heatmap refinement,proved to be beneficial when segmenting the histopathological images. We founda significant improvement when using a refinement network for postprocessingthe generated tumour segmentation heatmaps. The overall best design achieved aDice score of 0.933 on an independent test set of 90 WSIs. The designoutperformed single-resolution approaches, such as cluster-guided, patch-wisehigh-resolution classification using MobileNetV2 (0.872) and a low-resolutionU-Net (0.874). In addition, segmentation on a representative x400 WSI took ~58seconds, using only the CPU. The findings demonstrate the potential ofutilizing a refinement network to improve patch-wise predictions. The solutionis efficient and does not require overlapping patch inference or ensembling.Furthermore, we showed that deep neural networks can be trained using a randomsampling scheme that balances on multiple different labels simultaneously,without the need of storing patches on disk. Future work should involve moreefficient patch generation and sampling, as well as improved clustering.

Hybrid guiding: A multi-resolution refinement approach for semantic segmentation of gigapixel histopathological images