Abstract
Learning disease-related representations plays a critical role in image-based cancer diagnosis, due to its trustworthy, interpretable and good generalization power. A good representation should not only be disentangled from the disease-irrelevant features, but also incorporate the information of lesion’s attributes (e.g., shape, margin) that are often identified first during cancer diagnosis clinically. To learn such a representation, we propose a Disentangle Auto-Encoder with Graph Convolutional Network (DAE-GCN), which adopts a disentangling mechanism with the guidance of a GCN model in the AE-based framework. Specifically, we explicitly separate the encoded features into disease-related features and others. Among such features that all participate in image reconstruction, we only employ the disease-related features for disease prediction. Besides, to account for lesions’ attributes, we propose to leverage the attributes and adopt the GCN to learn them during training. Take mammogram mass benign/malignant classification as an example, our DAE-GCN helps improve the performance and the interpretability of cancer prediction, which can be verified by state-of-the-art performance on one public dataset DDSM and three in-house datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We leave the number of ROIs and patients of each dataset and the description about the selection of attributes for DDSM in supplementary.
- 2.
Existing works about DDSM do not publish their splitting way and mention smaller count number of ROIs in DDSM compared with our statistics.
References
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013). https://doi.org/10.1109/TPAMI.2013.50
Bowyer, K., et al.: The digital database for screening mammography. In: Third International Workshop on Digital Mammography, vol. 58, p. 27 (1996)
Burgess, C.P., et al.: Understanding disentangling in \(\beta \)-vae. arXiv preprint arXiv:1804.03599 (2018)
Chen, Z.M., Wei, X.S., Wang, P., Guo, Y.: Multi-label image recognition with graph convolutional networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 5177–5186 (2019)
Ding, J., et al.: Optimizing the peritumoral region size in radiomics analysis for sentinel lymph node status prediction in breast cancer. Acad. Radiol. (2020). https://doi.org/10.1016/j.acra.2020.10.015
Ding, Z., et al.: Guided variational autoencoder for disentanglement learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7920–7929 (2020)
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F.A., Brendel, W.: Imagenet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=Bygh9j09KX
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Kim, S.T., Lee, H., Kim, H.G., Ro, Y.M.: Icadx: interpretable computer aided diagnosis of breast masses. In: Medical Imaging 2018: Computer-Aided Diagnosis, vol. 10575, p. 1057522. International Society for Optics and Photonics (2018). https://doi.org/10.1117/12.2293570
Klingler, S., Wampfler, R., Käser, T., Solenthaler, B., Gross, M.: Efficient feature embeddings for student classification with variational auto-encoders. International Educational Data Mining Society (2017)
Li, H., Chen, D., Nailon, W.H., Davies, M.E., Laurenson, D.I.: Signed laplacian deep learning with adversarial augmentation for improved mammography diagnosis. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11769, pp. 486–494. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32226-7_54
Ridgeway, K.: A survey of inductive biases for factorial representation-learning. arXiv preprint arXiv:1612.05299 (2016)
Sickles, E., D’Orsi, C., Bassett, L.: Acr bi-rads® mammography. acr bi-rads® atlas, breast imaging reporting and data system (2013)
Surendiran, B., Vadivel, A.: Mammogram mass classification using various geometric shape and margin features for early detection of breast cancer. Int. J. Med. Eng. Inf. 4(1), 36–54 (2012). https://doi.org/10.1504/IJMEI.2012.045302
Acknowledgement
This work was supported by MOST-2018AAA0102004, NSFC-61625201 and ZheJiang Province Key Research & Development Program (No. 2020C03073).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, C., Sun, X., Zhang, F., Yu, Y., Wang, Y. (2021). DAE-GCN: Identifying Disease-Related Features for Disease Prediction. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12905. Springer, Cham. https://doi.org/10.1007/978-3-030-87240-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-87240-3_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87239-7
Online ISBN: 978-3-030-87240-3
eBook Packages: Computer ScienceComputer Science (R0)
