Feature Augmented Deep Neural Networks for Segmentation of Cells
In this work, we use a fully convolutional neural network for microscopy cell image segmentation. Rather than designing the network from scratch, we modify an existing network to suit our dataset. We show that improved cell segmentation can be obtained by augmenting the raw images with specialized feature maps such as eigen value of Hessian and wavelet filtered images, for training our network. We also show modality transfer learning, by training a network on phase contrast images and testing on fluorescent images. Finally we show that our network is able to segment irregularly shaped cells. We evaluate the performance of our methods on three datasets consisting of phase contrast, fluorescent and bright-field images.
KeywordsDeep neural network Feature augmentation Cell segmentation Convolutional neural network Unstained cells
This work was supported by the Swedish research council under Grant 2012-4968 (to CW) and the Swedish strategic research program eSSENCE. Image data was kindly provided by Johan Elf at the Department of Cell and Molecular Biology, Computational and Systems Biology, Uppsala University, Sweden and Theresa Vincent at the Department of Physiology and Pharmacology, Karolinska Institutet, Sweden.
- 2.Lin, S.C., Yip, H., Phandthong, R., Davis, B., Talbot, P.: Evaluation of dynamic cell processes and behavior using video bioinformatics tools. In: Bhanu, B., Talbot, P. (eds.) Video Bioinformatics. CB, vol. 22, pp. 167–186. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-23724-4_9 CrossRefGoogle Scholar
- 4.Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431–3440 (2015)Google Scholar
- 6.Chen, H., Qi, X.J., Cheng, J.Z., et al.: Deep contextual networks for neuronal structure segmentation. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 1167–1173 (2016)Google Scholar
- 8.Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012)Google Scholar
- 9.Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. arXiv:1604.06573v1 (2016)
- 10.Wang, P., Li, Z., Hou, Y., et al.: Combining convnets with hand-crafted features for action recognition based on an HMM-SVM classifier. arXiv:1602.00749v1 (2016)
- 12.Liu, B., Wang, M., Foroosh, H., et al.: Sparse convolutional neural networks. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 806–814, June 2015Google Scholar
- 13.Iandola, F.N., Moskewicz, M.W., Ashraf, K., et al.: Squeezenet: alexnet-level accuracy with 50x fewer parameters and \(<\)1mb model size. arXiv:1602.07360v3 (2016)
- 14.Sadanandan, S.K.: CBA segmentation. https://bitbucket.org/sajithks/fastcba/. Accessed 21 May 2016
- 18.Wasilewski, F.: Pywavelets. http://www.pybytes.com/pywavelets/. Accessed 21 May 2016
- 19.Jia, Y., Shelhamer, E., Donahue, J., et al.: Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)