Automatic Brain Tumor Segmentation and Overall Survival Prediction Using Machine Learning Algorithms
Purpose: This study was designed to evaluate the ability of a U-net neural net-work to properly identify three regions of a brain tumor and an ELM for the prediction of patient overall survival after gross tumor resection using preoperative MR images.
Methods: 210 GBM patients were used for training, while 66 LGG and GBM patients were used for validation. Multiple preprocessing steps were performed on each patient’s data before loading them into the model. The segmentation model consists of three different U-nets, one for each region of interest. These created segmentations were then analyzed by use of common quantitative metrics with respect to physician created contours. Regarding the patient overall survival prediction, 59 high grade glioma patients with gross total resection (GTR) were provided for training. 28 patients with GTR were used to validate the algorithm.
Results: The average [s.d] DSC for the whole tumor, enhanced tumor, and tumor core contours were 0.882 [0.080], 0.712 [0.294], and 0.769 [0.263], respectively. The average [s.d.] Hausdorff distance were 7.09 [11.57], 4.46 [8.32], and 9.57 [14.08], respectively. The average [s.d.] sensitivity for the whole tumor, enhanced tumor, and tumor core contours were 0.887 [0.126], 0.770 [0.245], and 0.750 [0.293], respectively. The average [s.d.] specificity was 0. 993 [0.005], 0.998 [0.003], 0.998 [0.002], respectively. The predictive power of patient overall survival is 0.607 using an extreme learning machine algorithm.
Conclusion: The U-Net model was very effective in determining accurate location of the whole tumor and segmenting the whole tumor, enhancing tumor and tumor core. The most predictive features of patient overall survival are both age and location of the tumor when all 163 validation cases were utilized.
KeywordsMagnetic resonance imaging Neural network U-net
This study was supported by a Research Scholar Grant, RSG-15-137-01-CCE from the American Cancer Society.
- 4.Toward precision medicine: Building a knowledge network for biomedical research and a new taxonomy of disease. Washington (DC) (2011) Google Scholar
- 7.Bakas, S.,et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-GBM collection. In: The Cancer Imaging Archive (2017)Google Scholar
- 8.Bakas, S., et al.: Segmentation labels and radiomic features for the pre-operative scans of the TCGA-LGG collection. In: The Cancer Imaging Archive (2017)Google Scholar
- 10.Ronneberger, Olaf., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
- 11.Keras, C.F.: Keras. Github Repository (2015)Google Scholar
- 12.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, https://arxiv.org/abs/1811.02629 2018
- 15.Varghese Alex, M.S., Krishnamurthi, G.: Brain tumor segmentation from multi modal MR images using fully convolutional neural network. Spain (2017)Google Scholar
- 16.Amorim, P.H.A.C., Escudero, G.G., Oliveira, D.D.C., Pereira, S.M., Santos, H.M., Scussel, A.A.: 3D u-nets for brain tumor segmentation in MICCAI. Spain (2017)Google Scholar
- 17.Beers, A., et al.: Sequential 3D U-nets for brain tumor segmentation. Spain (2017)Google Scholar
- 18.Feng, X., Meyer, C.: Patch-based 3D U-net for brain tumor segmentation. Spain (2017)Google Scholar
- 19.Rodríguez Colmeiro, R.G., Verrastro, C.A., Grosges, T.: Multimodal brain tumor segmentation using 3D convolutional networks. In: Crimi, A., Bakas, S., Kuijf, H., Menze, B., Reyes, M. (eds.) BrainLes 2017. LNCS, vol. 10670, pp. 226–240. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75238-9_20CrossRefGoogle Scholar
- 20.Baid, U., et al.: Gbm segmentation with 3D U-net and survivalprediction with radiomics. Spain (2018)Google Scholar