Multi-modal Disease Classification in Incomplete Datasets Using Geometric Matrix Completion
In large population-based studies and in clinical routine, tasks like disease diagnosis and progression prediction are inherently based on a rich set of multi-modal data, including imaging and other sensor data, clinical scores, phenotypes, labels and demographics. However, missing features, rater bias and inaccurate measurements are typical ailments of real-life medical datasets. Recently, it has been shown that deep learning with graph convolution neural networks (GCN) can outperform traditional machine learning in disease classification, but missing features remain an open problem. In this work, we follow up on the idea of modeling multi-modal disease classification as a matrix completion problem, with simultaneous classification and non-linear imputation of features. Compared to methods before, we arrange subjects in a graph-structure and solve classification through geometric matrix completion, which simulates a heat diffusion process that is learned and solved with a recurrent neural network. We demonstrate the potential of this method on the ADNI-based TADPOLE dataset and on the task of predicting the transition from MCI to Alzheimer’s disease. With an AUC of 0.950 and classification accuracy of 87%, our approach outperforms standard linear and non-linear classifiers, as well as several state-of-the-art results in related literature, including a recently proposed GCN-based approach.
The study was supported by the German Federal Ministry of Education and Health (BMBF) in connection with the foundation of the German Center for Vertigo and Balance Disorders (DSGZ) (grant number 01 EO 0901).
- 2.Candes, E.J., Recht, B.: Exact low-rank matrix completion via convex optimization. In: 46th Annual Allerton Conference on Communication, Control, and Computing, pp 1–49 (2008)Google Scholar
- 5.Goldberg, A., Recht, B., Xu, J., Nowak, R., Zhu, X.: Transduction with matrix completion: three birds with one stone. In: Advances in Neural Information Processing Systems (NIPS), pp. 757–765 (2010)Google Scholar
- 6.Kalofolias, V., Bresson, X., Bronstein, M., Vandergheynst, P.: Matrix completion on graphs. arXiv:1408.1717 (2014)
- 7.Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. CoRR, arXiv:1609.02907 (2016)
- 9.Monti, F., Bronstein, M.M., Bresson, X.: Geometric matrix completion with recurrent multi-graph neural networks. CoRR, arXiv:1704.06803 (2017)
- 12.Parisot, S., et al.: Spectral graph convolutions for population-based disease prediction. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 177–185. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_21CrossRefGoogle Scholar
- 13.Rao, N., Yu, H.-F., Ravikumar, P., Dhillon, I.S.: Collaborative filtering with graph information: consistency and scalable methods. In: Neural Information Processing Systems (NIPS), pp. 1–9 (2015)Google Scholar
- 14.Srebro, N., Rennie, J.D.M., Jaakkola, T.S.: Maximum-margin matrix factorization. In: Advances in Neural Information Processing Systems (NIPS), pp. 17:1329–17:1336 (2005)Google Scholar
- 15.Thung, K.-H., Adeli, E., Yap, P.-T., Shen, D.: Stability-weighted matrix completion of incomplete multi-modal data for disease diagnosis. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 88–96. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_11CrossRefGoogle Scholar