Deep Learning Versus Classical Regression for Brain Tumor Patient Survival Prediction
Deep learning for regression tasks on medical imaging data has shown promising results. However, compared to other approaches, their power is strongly linked to the dataset size. In this study, we evaluate 3D-convolutional neural networks (CNNs) and classical regression methods with hand-crafted features for survival time regression of patients with high-grade brain tumors. The tested CNNs for regression showed promising but unstable results. The best performing deep learning approach reached an accuracy of \(51.5\%\) on held-out samples of the training set. All tested deep learning experiments were outperformed by a Support Vector Classifier (SVC) using 30 radiomic features. The investigated features included intensity, shape, location and deep features.
The submitted method to the BraTS 2018 survival prediction challenge is an ensemble of SVCs, which reached a cross-validated accuracy of \(72.2\%\) on the BraTS 2018 training set, \(57.1\%\) on the validation set, and \(42.9\%\) on the testing set.
The results suggest that more training data is necessary for a stable performance of a CNN model for direct regression from magnetic resonance images, and that non-imaging clinical patient information is crucial along with imaging information.
KeywordsBrain tumor Survival prediction Regression 3D-Convolutional Neural Networks
We gladly acknowledge the support of the Swiss Cancer League (grant KFS-3979-08-2016) and the Swiss National Science Foundation (grant 169607). We are grateful for the support of the NVIDIA corporation for the donation of a Titan Xp GPU. Calculations were partly performed on UBELIX, the HPC cluster at the University of Bern.
- 4.Bakas, S., Reyes, M., et al.: Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. ArXiv e-prints, November 2018Google Scholar
- 6.Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and regression trees (1984)Google Scholar
- 13.Kinga, D., Adam, J.B.: A method for stochastic optimization. In: International Conference on Learning Representations (ICLR), vol. 5 (2015)Google Scholar
- 26.Wang, G., Li, W., Ourselin, S., Vercauteren, T.: Automatic brain tumor segmentation using cascaded anisotropic convolutional neural networks. In: Crimi, A., Bakas, S., Kuijf, H., Menze, B., Reyes, M. (eds.) BrainLes 2017. LNCS, vol. 10670, pp. 178–190. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75238-9_16CrossRefGoogle Scholar