Abstract
Deep convolutional neural networks (CNN) proved to be highly accurate to perform anatomical segmentation of medical images. However, some of the most popular CNN architectures for image segmentation still rely on post-processing strategies (e.g. Conditional Random Fields) to incorporate connectivity constraints into the resulting masks. These post-processing steps are based on the assumption that objects are usually continuous and therefore nearby pixels should be assigned the same object label. Even if it is a valid assumption in general, these methods do not offer a straightforward way to incorporate more complex priors like convexity or arbitrary shape restrictions.
In this work we propose Post-DAE, a post-processing method based on denoising autoencoders (DAE) trained using only segmentation masks. We learn a low-dimensional space of anatomically plausible segmentations, and use it as a post-processing step to impose shape constraints on the resulting masks obtained with arbitrary segmentation methods. Our approach is independent of image modality and intensity information since it employs only segmentation masks for training. This enables the use of anatomical segmentations that do not need to be paired with intensity images, making the approach very flexible. Our experimental results on anatomical segmentation of X-ray images show that Post-DAE can improve the quality of noisy and incorrect segmentation masks obtained with a variety of standard methods, by bringing them back to a feasible space, with almost no extra computational time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We used the public implementation available at https://github.com/lucasb-eyer/pydensecrf with Potts compatibility function and hand-tuned parameters \(\theta _\alpha =17\), \(\theta _\beta =3\), \(\theta _\gamma =3\) chosen using the validation fold. See the implementation website for more details about the aforementioned parameters.
- 2.
The source code and a complete description of the method is publicly available online at: https://github.com/dgriffiths3/ml_segmentation.
References
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). https://doi.org/10.1007/978-3-319-24574-4_28
Kamnitsas, K., et al.: Efficient multi-scale 3d CNN with fully connected CRF for accurate brain lesion segmentation. Med. Image Anal. 36, 61–78 (2017)
Shakeri, M., et al.: Sub-cortical brain structure segmentation using F-CNN’s. In: Proceedings of ISBI (2016)
BenTaieb, A., Hamarneh, G.: Topology aware fully convolutional networks for histology gland segmentation. In: Proceedings of MICCAI (2016)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Oktay, O., et al.: Anatomically constrained neural networks (ACNNs): application to cardiac image enhancement and segmentation. IEEE TMI 37(2), 384–395 (2018)
Ravishankar, H., et al.: Learning and incorporating shape models for semantic segmentation. In: Proceedings of MICCAI (2017)
Vincent, P., et al.: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. JMLR 11, 3371–3408 (2010)
Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: Proceedings of Fourth International Conference on 3D Vision (3DV) (2016)
Chapelle, O., Scholkopf, B., Zien, A.: Semi-Supervised Learning. MIT Press, Cambridge (2009)
Shiraishi, J., et al.: Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am. J. Roentgenol. 174(1), 71–74 (2000)
Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Proceedings of Nips (2011)
Haralick, R.M., Shanmugam, K., et al.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 6, 610–621 (1973)
Acknowledgments
EF is beneficiary of an AXA Research Fund grant. The authors gratefully acknowledge NVIDIA Corporation with the donation of the Titan Xp GPU used for this research, and the support of UNL (CAID-PIC-50420150100098LI) and ANPCyT (PICT 2016-0651).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Larrazabal, A.J., Martinez, C., Ferrante, E. (2019). Anatomical Priors for Image Segmentation via Post-processing with Denoising Autoencoders. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11769. Springer, Cham. https://doi.org/10.1007/978-3-030-32226-7_65
Download citation
DOI: https://doi.org/10.1007/978-3-030-32226-7_65
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32225-0
Online ISBN: 978-3-030-32226-7
eBook Packages: Computer ScienceComputer Science (R0)