Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Graph deep learning detects contextual prognostic biomarkers from whole-slide images

Graph deep learning can be used to detect contextual pathological features within a complex tumour microenvironment. We have shown the use of graph deep learning for predicting the prognosis of patients with tumours, and use it to identify additional contextual prognostic biomarkers for pathologists.

This is a preview of subscription content, access via your institution

Access options

Buy article

Get time limited or full article access on ReadCube.

$32.00

All prices are NET prices.

Fig. 1: Schematic of the TEA-graph model.

References

  1. Ahmedt-Aristizabal, D., Armin, M. A., Denman, S., Fookes, C. & Petersson, L. A survey on graph-based deep learning for computational histopathology. Comput. Med. Imaging Graph. 95, 102027 (2022). A review article that presents the recent trend of GNNs for computational pathology.

    Article  Google Scholar 

  2. Chen, R. J. et al. Whole slide images are 2D point clouds: context-aware survival prediction using patch-based graph convolutional networks. In Medical Image Computing and Computer Assisted Intervention (MICCAI) 339–349 (Springer, 2021). This paper reports GNNs for WSIs.

  3. Yang, H., Li, L., Zhang, L., Tang, J. & Chen, Z. PHGNN: position-aware graph neural network for heterogeneous graph embedding. In Int. Joint Conference on Neural Networks (IJCNN) 1–8 (IEEE, 2021). This paper reports a position-aware GNN.

  4. Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. Proc. 34th Int. Conference on Machine Learning (PMLR) 70, 3319–3328 (2017). This paper reports the IG method.

    Google Scholar 

  5. Hakimi, A. A. et al. An integrated metabolic atlas of clear cell renal cell carcinoma. Cancer Cell 29, 104–116 (2016). This paper reports the metabolic characteristics of clear cell renal cell carcinoma.

    CAS  Article  Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Lee, Y. et al. Derivation of prognostic contextual histopathological features from whole-slide images of tumours via graph deep learning. Nat. Biomed. Eng. https://doi.org/10.1038/s41551-022-00923-0 (2022).

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Graph deep learning detects contextual prognostic biomarkers from whole-slide images. Nat. Biomed. Eng (2022). https://doi.org/10.1038/s41551-022-00927-w

Download citation

  • Published:

  • DOI: https://doi.org/10.1038/s41551-022-00927-w

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing