Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data
Abstract
Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data are available in medical applications, access to manually labeled data is very limited. We propose to automatically create auxiliary labels on initially unlabeled data with existing tools and to use them for pre-training. For the subsequent fine-tuning of the network with manually labeled data, we introduce error corrective boosting (ECB), which emphasizes parameter updates on classes with lower accuracy. Furthermore, we introduce SkipDeconv-Net (SD-Net), a new F-CNN architecture for brain segmentation that combines skip connections with the unpooling strategy for upsampling. The SD-Net addresses challenges of severe class imbalance and errors along boundaries. With application to whole-brain MRI T1 scan segmentation, we generate auxiliary labels on a large dataset with FreeSurfer and fine-tune on two datasets with manual annotations. Our results show that the inclusion of auxiliary labels and ECB yields significant improvements. SD-Net segments a 3D scan in 7 s in comparison to 30 h for the closest multi-atlas segmentation method, while reaching similar performance. It also outperforms the latest state-of-the-art F-CNN models.
Notes
Acknowledgement
This work was supported in part by the Faculty of Medicine at LMU (FöFoLe), the Bavarian State Ministry of Education, Science and the Arts in the framework of the Centre Digitisation.Bavaria (ZD.B), the NVIDIA corporation and DAAD (German Academic Exchange Service). The authors would also like to thank Magdalini Paschali for proof reading and feedback.
Supplementary material
References
- 1.Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR 2015, pp. 3431–3440. IEEE (2015)Google Scholar
- 2.Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: ICCV 2015, pp. 1520–1528. IEEE (2015)Google Scholar
- 3.Badrinarayanan, V., Kendall, A., Segnet, C.R.: A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint: 1511.00561 (2015)Google Scholar
- 4.Ronneberger, O., 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). doi: 10.1007/978-3-319-24574-4_28 CrossRefGoogle Scholar
- 5.Milletari, F., Navab, N., Ahmadi, S.A.: V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 3DV, pp. 565–571. IEEE (2016)Google Scholar
- 6.Fischl, B., Salat, D.H., Busa, E., Albert, M., Dieterich, M., Haselgrove, C., Van Der Kouwe, A., Killiany, R., Kennedy, D., Klaveness, S., Montillo, A.: Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron 33(3), 341–55 (2002)CrossRefGoogle Scholar
- 7.Shakeri, M., Tsogkas, S., Ferrante, E., Lippe, S., Kadoury, S., Paragios, N., Kokkinos, I.: Sub-cortical brain structure segmentation using F-CNNs. In: ISBI 2016, pp. 269–272 (2016)Google Scholar
- 8.Dolz, J., Desrosiers, C., Ayed, I.B.: 3D fully convolutional networks for subcortical segmentation in MRI: a large-scale study (2016). arXiv preprint:1612.03925Google Scholar
- 9.Brebisson, A., Montana, G.: Deep neural networks for anatomical brain segmentation. In: CVPR Workshops, pp. 20–28 (2015)Google Scholar
- 10.Wachinger, C., Reuter, M., Klein, T.: DeepNAT: deep convolutional neural network for segmenting neuroanatomy. Neuroimage (2017)Google Scholar
- 11.Shin, H.C., Roth, H.R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., Summers, R.M.: Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. TMI 35(5), 1285–98 (2016)Google Scholar
- 12.Tajbakhsh, N., Shin, J.Y., Gurudu, S.R., Hurst, R.T., Kendall, C.B., Gotway, M.B., Liang, J.: Convolutional neural networks for medical image analysis: full training or fine tuning? TMI 35(5), 1299–1312 (2016)Google Scholar
- 13.Landman, B, Warfield, S.: MICCAI workshop on multiatlas labeling. In: MICCAI Grand Challenge (2012)Google Scholar
- 14.Klein, A., Tourville, J.: 101 labeled brain images and a consistent human cortical labeling protocol. Front. Neurosci. 6, 171 (2012)Google Scholar
- 15.Marcus, D.S., Fotenos, A.F., Csernansky, J.G., Morris, J.C., Buckner, R.L.: Open access series of imaging studies: longitudinal MRI data in nondemented and demented older adults. J. Cog. Neuroscience. 12, 2677–84 (2010)CrossRefGoogle Scholar
- 16.Wang, H., Yushkevich, P.: Multi-atlas segmentation with joint label fusion and corrective learning-an open source implementation. Front. Neuroinform. 7, 27 (2013)Google Scholar
- 17.Asman, A.J., Landman, B.A.: Formulating spatially varying performance in the statistical fusion framework. TMI. 6, 1326–36 (2012)Google Scholar