Abstract
With respect to spatial overlap, CNN-based segmentation of short axis cardiovascular magnetic resonance (CMR) images has achieved a level of performance consistent with inter observer variation. However, conventional training procedures frequently depend on pixel-wise loss functions, limiting optimisation with respect to extended or global features. As a result, inferred segmentations can lack spatial coherence, including spurious connected components or holes. Such results are implausible, violating the anticipated topology of image segments, which is frequently known a priori. Addressing this challenge, published work has employed persistent homology, constructing topological loss functions for the evaluation of image segments against an explicit prior. Building a richer description of segmentation topology by considering all possible labels and label pairs, we extend these losses to the task of multi-class segmentation. These topological priors allow us to resolve all topological errors in a subset of 150 examples from the ACDC short axis CMR training data set, without sacrificing overlap performance .
N. Byrne—Funded by a National Institute for Health Research (NIHR), Doctoral Research Fellowship for this research project. This report presents independent research funded by the NIHR. The views expressed are those of the author(s) and not necessarily those of the NHS, the NIHR or the Department of Health and Social Care. The authors have no conflicts of interest to disclose.
G. Montana and A.P. King—Joint last authors..
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
In \(B^{ij}_{d}\) we divide indices between sub and super scripts to make clear the difference between class labels (i, j) and topological dimension (d), without further significance.
- 3.
We use the union operator (\(\cup \)) to combine individual classes of a multi-class segmentation. When applied to a binary segmentation, \(Y_{i \cup j}\) is the pixel-wise Boolean union of classes i and j. When applied to a probabilistic segmentation, \(\hat{Y}_{i \cup j}\) is the pixel-wise probability of class i or j. We consider the union of a class with itself to be the segmentation of the single class: \(Y_{i \cup j=i} = Y_{i}\) and \(\hat{Y}_{i \cup j=i} = \hat{Y}_{i}\).
References
Avendi, M.R., Kheradvar, A., Jafarkhani, H.: Automatic segmentation of the right ventricle from cardiac MRI using a learning-based approach. Magn. Reson. Med. 78(6), 2439–2448 (2017)
BenTaieb, A., Hamarneh, G.: Topology aware fully convolutional networks for histology gland segmentation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016, Part II. LNCS, vol. 9901, pp. 460–468. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_53
Bernard, O., et al.: Deep learning techniques for automatic MRI cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE Trans. Med. Imaging 37(11), 2514–2525 (2018)
Chen, C., et al.: Deep learning for cardiac image segmentation: a review. Front. Cardiovasc. Med. 7, 25 (2020)
Clough, J.R., Byrne, N., Oksuz, I., Zimmer, V.A., Schnabel, J.A., King, A.P.: A topological loss function for deep-learning based image segmentation using persistent homology. IEEE Trans. Pattern Anal. Mach. Intell., 1 (2020). https://doi.org/10.1109/TPAMI.2020.3013679
Clough, J.R., Oksuz, I., Byrne, N., Schnabel, J.A., King, A.P.: Explicit topological priors for deep-learning based image segmentation using persistent homology. In: Chung, A.C.S., Gee, J.C., Yushkevich, P.A., Bao, S. (eds.) IPMI 2019. LNCS, vol. 11492, pp. 16–28. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20351-1_2
Duan, J., et al.: Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi- task deep learning approach. IEEE Trans. Med. Imaging 38(9), 2151–2164 (2019)
Gabrielsson, R.B., Nelson, B.J., Dwaraknath, A., Skraba, P.: A topology layer for machine learning. In: International Conference on Artificial Intelligence and Statistics, pp. 1553–1563 (2020)
Ganaye, P.-A., Sdika, M., Benoit-Cattin, H.: Semi-supervised learning for segmentation under semantic constraint. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018, Part III. LNCS, vol. 11072, pp. 595–602. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00931-1_68
Haft-Javaherian, M., Villiger, M., Schaffer, C.B., Nishimura, N., Golland, P., Bouma, B.E.: A topological encoding convolutional neural network for segmentation of 3D multiphoton images of brain vasculature using persistent homology. In: Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 990–991 (2020)
He, Y., et al.: Fully convolutional boundary regression for retina OCT segmentation. In: Shen, D., et al. (eds.) MICCAI 2019, Part I. LNCS, vol. 11764, pp. 120–128. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32239-7_14
Isensee, F., Jaeger, P.F., Full, P.M., Wolf, I., Engelhardt, S., Maier-Hein, K.H.: Automatic cardiac disease assessment on cine-MRI via time-series segmentation and domain specific features. In: Pop, M., et al. (eds.) STACOM 2017. LNCS, vol. 10663, pp. 120–129. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75541-0_13
Oktay, O., et al.: Anatomically constrained neural networks (ACNNs): application to cardiac image enhancement and segmentation. IEEE Trans. Med. Imaging 37(2), 384–395 (2018)
Otter, N., Porter, M.A., Tillmann, U., Grindrod, P., Harrington, H.A.: A roadmap for the computation of persistent homology. EPJ Data Sci. 6(1), 1–38 (2017). https://doi.org/10.1140/epjds/s13688-017-0109-5
Painchaud, N., Skandarani, Y., Judge, T., Bernard, O., Lalande, A., Jodoin, P.M.: Cardiac segmentation with strong anatomical guarantees. IEEE Trans. Med. Imaging 39, 3703–3713 (2020)
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, Part III. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ruijsink, B., et al.: Fully automated, quality-controlled cardiac analysis from CMR. JACC Cardiovasc, Imaging (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Byrne, N., Clough, J.R., Montana, G., King, A.P. (2021). A Persistent Homology-Based Topological Loss Function for Multi-class CNN Segmentation of Cardiac MRI. In: Puyol Anton, E., et al. Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges. STACOM 2020. Lecture Notes in Computer Science(), vol 12592. Springer, Cham. https://doi.org/10.1007/978-3-030-68107-4_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-68107-4_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68106-7
Online ISBN: 978-3-030-68107-4
eBook Packages: Computer ScienceComputer Science (R0)