SoLiD: Segmentation of Clostridioides Difficile Cells in the Presence of Inhomogeneous Illumination Using a Deep Adversarial Network
Segmentation of cells in scanning electron microscopy images is a challenging problem due to the presence of inhomogeneous illumination. Classical pre-processing methods for illumination normalization destroy the texture and add noise to the image. In this paper, we present a deep cell segmentation method using adversarial training that is robust to inhomogeneous illumination. Specifically, we apply a model based on U-net as the segmenter and a deep ConvNet as the discriminator for the adversarial training called SoLiD: “Segmentation of clostridioides difficile cells in the presence of inhomogeneous iLlumInation using a Deep adversarial network”. We also present an image augmentation algorithm to obtain the training images required for SoLid. The results indicate that SoLiD is robust to inhomogeneous illumination. The segmentation performance is compared to the U-net and the dice score is improved by 44%.
KeywordsCell segmentation Deep adversarial training Data augmentation U-net
This work was supported in part by the Hugh Roy and Lillie Cranz Cullen Endowment Fund.
- 1.Dai, W., et al..: SCAN: Structure correcting adversarial network for organ segmentation in chest X-rays. arXiv preprint arXiv:1703.08770 (2017)
- 3.Efros, A.A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: Computer Graphics and Interactive Techniques, pp. 341–346. New York, NY, USA (2001)Google Scholar
- 5.Goodfellow, I., et al.: Generative adversarial nets. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 2672–2680. Montral, Canada (2014)Google Scholar
- 7.Kohl, S., et al.: Adversarial networks for the detection of aggressive prostate cancer. arXiv preprint arXiv:1702.08014 (2017)
- 8.Li, Z., Wang, Y., Yu, J.: Brain tumor segmentation using an adversarial network. In: Proceedings of the International MICCAI Brainlesion Workshop, pp. 123–132. Quebec City, QC, Canada (2017)Google Scholar
- 9.Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the Computer Vision and Pattern Recognition, pp. 3431–3440. Boston, MA (2015)Google Scholar
- 10.Luc, P., Couprie, C., Chintala, S., Verbeek, J.: Semantic segmentation using adversarial networks. In: Proceedings of the NIPS Workshop on Adversarial Training, pp. 1–9. Barcelona, Spain (2016)Google Scholar
- 11.Memariani, A., Nikou, C., Endres, B.T., Bassères, E., Garey, K.W., Kakadiaris, I.A.: DeTEC: detection of touching elongated cells in SEM images. In: Proceedings of the Advances in Visual Computing, pp. 288–297 (2016)Google Scholar
- 12.Memariani, A., Nikou, C., Endres, B., Bassères, E., Garey, K., Kakadiaris, I.A.: DETCIC: detection of elongated touching cells with inhomogeneous illumination using a stack of conditional random fields. In: Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, pp. 574–580 (2018)Google Scholar
- 13.Moeskops, P., Veta, M., Lafarge, M.W., Eppenhof, K.A., Pluim, J.P.: Adversarial training and dilated convolutions for brain MRI segmentation. In: Proceedings of the Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 56–64. Quebec City, QC, Canada (2017)CrossRefGoogle Scholar
- 14.Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Proceedings of the Medical Image Computing and Computer-Assisted Intervention, pp. 234–241. Munich, Germany (2015)Google Scholar