Abstract
Identification and classification of cell-graph features using graph-neural networks (GNNs) has been shown to be useful in digital pathology. In this work, we consider the role of edge labels in cell-graph modeling, including histological modeling techniques, edge aggregation in GNN architectures, and edge label prediction. We propose EAGNN (Edge Aggregated GNN), a new GNN model that aggregates both node and edge label information to take advantage of topological information about cellular data and facilitate edge label prediction. We introduce new edge label features that improve histological modeling and prediction. We evaluate our EAGNN model for the task of detecting the presence and location of the basement membrane in oral mucosal tissue, as a proof-of-concept application.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Official PyTorch implementation of the EAGNN algorithm is publicly available at https://github.com/aravi11/EAGNN.
- 2.
Note \(S_{uv} = S_{vu}\) and so the proposed method is invariant to node ordering.
- 3.
We kept the limiting criterion equivalent to 300 pixels to avoid long edges in the cell-graph, as the cell density varies across different parts of a tile.
- 4.
The reason for choosing the absolute difference here was to have non-negative entropy difference value. Ablation studies showed that negative cell entropy differences had an adverse effect on the efficiency of the trained model.
- 5.
We used Intelligraph tool for cell annotation, graph construction and results evaluation.
References
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.: The Official Journal of the Computerized Medical Imaging Society 95, 102027 (2022)
Anand, D., Gadiya, S., Sethi, A.: Histographs: graphs in histopathology. In: Medical Imaging 2020: Digital Pathology, vol. 11320, p. 113200O. International Society for Optics and Photonics (2020)
Atwood, J., Towsley, D.: Diffusion-convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Aygüneş, B., Aksoy, S., Cinbiş, R.G., Kösemehmetoğlu, K., Önder, S., Üner, A.: Graph convolutional networks for region of interest classification in breast histopathology. In: Medical Imaging 2020: Digital Pathology, vol. 11320, p. 113200K. International Society for Optics and Photonics (2020)
Bilgin, C., Demir, C., Nagi, C., Yener, B.: Cell-graph mining for breast tissue modeling and classification. In: 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 5311–5314. IEEE (2007)
Cao, L., Lu, Y., Li, C., Yang, W.: Automatic segmentation of pathological glomerular basement membrane in transmission electron microscopy images with random forest stacks. Comput. Math. Methods Med. 2019 (2019)
Clevert, D.A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint arXiv:1511.07289 (2015)
Crichton, G., Guo, Y., Pyysalo, S., Korhonen, A.: Neural networks for link prediction in realistic biomedical graphs: a multi-dimensional evaluation of graph embedding-based approaches. BMC Bioinform. 19(1), 1–11 (2018)
Demir, C., Gultekin, S.H., Yener, B.: Learning the topological properties of brain tumors. IEEE/ACM Trans. Comput. Biol. Bioinf. 2(3), 262–270 (2005)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp. 1263–1272. PMLR (2017)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 315–323. JMLR Workshop and Conference Proceedings (2011)
Gong, L., Cheng, Q.: Exploiting edge features for graph neural networks. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos, CA, USA, pp. 9203–9211. IEEE Computer Society (2019)
Gunduz, C., Yener, B., Gultekin, S.H.: The cell graphs of cancer. Bioinformatics 20(Suppl. 1), i145–i151 (2004)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Hamilton, W.L.: Graph representation learning. Synth. Lect. Artif. Intell. Mach. Learn. 14(3), 1–159 (2020)
Levy, J., Haudenschild, C., Barwick, C., Christensen, B., Vaickus, L.: Topological feature extraction and visualization of whole slide images using graph neural networks. In: BIOCOMPUTING 2021: Proceedings of the Pacific Symposium, pp. 285–296. World Scientific (2020)
Nair, A., et al.: A graph neural network framework for mapping histological topology in oral mucosal tissue. BMC Bioinform. 23(1), 1–21 (2022)
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: International Conference on Machine Learning, pp. 2014–2023. PMLR (2016)
Pasupa, K., Vatathanavaro, S., Tungjitnob, S.: Convolutional neural networks based focal loss for class imbalance problem: a case study of canine red blood cells morphology classification. J. Ambient Intell. Hum. Comput. 1–17 (2020)
Pati, P., et al.: HACT-Net: a hierarchical cell-to-tissue graph neural network for histopathological image classification. In: Sudre, C.H., et al. (eds.) UNSURE/GRAIL -2020. LNCS, vol. 12443, pp. 208–219. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60365-6_20
Studer, L., Wallau, J., Dawson, H., Zlobec, I., Fischer, A.: Classification of intestinal gland cell-graphs using graph neural networks. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 3636–3643. IEEE (2021)
Sureka, M., Patil, A., Anand, D., Sethi, A.: Visualization for histopathology images using graph convolutional neural networks. In: 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE), pp. 331–335. IEEE (2020)
Tollemar, V., et al.: Histopathological grading of oral mucosal chronic graft-versus-host disease: large cohort analysis. Biol. Blood Marrow Transplant. 26(10), 1971–1979 (2020)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018)
Wang, D., Gu, C., Wu, K., Guan, X.: Adversarial neural networks for basal membrane segmentation of microinvasive cervix carcinoma in histopathology images. In: 2017 International Conference on Machine Learning and Cybernetics (ICMLC), vol. 2, pp. 385–389. IEEE (2017)
Wu, H.S., Dikman, S., Gil, J.: A semi-automatic algorithm for measurement of basement membrane thickness in kidneys in electron microscopy images. Comput. Methods Programs Biomed. 97(3), 223–231 (2010)
Yener, B.: Cell-graphs: image-driven modeling of structure-function relationship. Commun. ACM 60(1), 74–84 (2016)
Acknowledgements
The authors acknowledge the clinical and technical assistance of Karin Garming-Lergert, Victor Tollemar and Daniella Nordman (Karolinska Institutet) for collection and preparation of biopsies, and annotations. The study was financed by grants from Region Stockholm ALF Medicine, Styrgruppen KI/Region Stockholm for Research in Odontology and research funds from Karolinska Institutet and KTH.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Ethics Declarations
Ethical approval for the collection and experimental use of tissue samples from patients attending the Department of Maxillofacial Surgery, Karolinska University Hospital (provided written informed consent) or retrieved retrospectively from Stockholm’s Medicine Biobank (Sweden Biobank, access to archived material) has been granted by the Swedish Ethical Review Authority (Etikprövningsmyndigheten). Procedures have been performed according to relevant guidelines, under Registration Numbers 2013/39-31/4, 2014/1184-31/1 and 2019-01295.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hasegawa, T., Arvidsson, H., Tudzarovski, N., Meinke, K., Sugars, R.V., Ashok Nair, A. (2023). Edge-Based Graph Neural Networks for Cell-Graph Modeling and Prediction. In: Frangi, A., de Bruijne, M., Wassermann, D., Navab, N. (eds) Information Processing in Medical Imaging. IPMI 2023. Lecture Notes in Computer Science, vol 13939. Springer, Cham. https://doi.org/10.1007/978-3-031-34048-2_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-34048-2_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34047-5
Online ISBN: 978-3-031-34048-2
eBook Packages: Computer ScienceComputer Science (R0)