Abstract
Semantic segmentation using convolutional neural networks (CNNs) is the state-of-the-art for many medical segmentation tasks including left ventricle (LV) segmentation in cardiac MR images. However, a drawback is that these CNNs lack explicit shape constraints, occasionally resulting in unrealistic segmentations. In this paper, we perform LV and myocardial segmentation by regression of pose and shape parameters derived from a statistical shape model. The integrated shape model regularizes predicted segmentations and guarantees realistic shapes. Furthermore, in contrast to semantic segmentation, it allows direct calculation of regional measures such as myocardial thickness. We enforce robustness of shape and pose prediction by simultaneously constructing a segmentation distance map during training. We evaluated the proposed method in a fivefold cross validation on a in-house clinical dataset with 75 subjects containing a total of 1539 delineated short-axis slices covering LV from apex to base, and achieved a correlation of 99\(\%\) for LV area, 94\(\%\) for myocardial area, 98\(\%\) for LV dimensions and 88\(\%\) for regional wall thicknesses. The method was additionally validated on the LVQuan18 and LVQuan19 public datasets and achieved state-of-the-art results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
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)
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), 2151–5164 (2019)
Zotti, C., et al.: Convolutional neural network with shape prior applied to cardiac MRI segmentation. IEEE J. Biomed. Health Inform. 23(3), 1119–1128 (2019)
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)
Painchaud, N., Skandarani, Y., Judge, T., Bernard, O., Lalande, A., Jodoin, P.-M.: Cardiac MRI segmentation with strong anatomical guarantees. In: Shen, D., et al. (eds.) MICCAI 2019, Part II. LNCS, vol. 11765, pp. 632–640. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_70
Yue, Q., Luo, X., Ye, Q., Xu, L., Zhuang, X.: Cardiac segmentation from LGE MRI using deep neural network incorporating shape and spatial priors. In: Shen, D., et al. (eds.) MICCAI 2019, Part II. LNCS, vol. 11765, pp. 559–567. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_62
Cootes, T.F., et al.: Active shape models - their training and application. Comput. Vis. Image Underst 61(1), 38–59 (1995)
Attar, R., et al.: 3D cardiac shape prediction with deep neural networks: simultaneous use of images and patient metadata. In: Shen, D., et al. (eds.) MICCAI 2019, Part II. LNCS, vol. 11765, pp. 586–594. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_65
Vigneault, D., et al.: \(\Omega \)-Net (omega-net): fully automatic, multi-view cardiac mr detection, orientation, and segmentation with deep neural networks. Med. Image Anal. 48, 95–106 (2018)
Gessert, N., Schlaefer, A.: Left ventricle quantification using direct regression with segmentation regularization and ensembles of pretrained 2D and 3D CNNs. In: Pop, M., et al. (eds.) STACOM 2019. LNCS, vol. 12009, pp. 375–383. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39074-7_39
Tilborghs, S., Maes, F.: Left ventricular parameter regression from deep feature maps of a jointly trained segmentation CNN. In: Pop, M., et al. (eds.) STACOM 2019. LNCS, vol. 12009, pp. 395–404. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39074-7_41
Cao, L., et al.: Multi-task neural networks for joint hippocampus segmentation and clinical score regression. Multimed. Tools Appl. 77, 29669–29686 (2018)
Kervadec, H., et al.: Boundary loss for highly unbalanced segmentation. In: MIDL 2019, JMLR, vol. 102, pp. 285–296 (2019)
Karimi, D., Salcudean, S.E.: Reducing the Hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Trans. Med. Imaging 39(2), 499–513 (2020)
Dangi, S., et al.: A distance map regularized CNN for cardiac cine MR image segmentation. Med. Phys. 46(12), 5637–5651 (2019)
Li, S., Xue, W.: Left ventricle full quantification hallenge. In: MICCAI 2018. (2018) https://lvquan18.github.io/
Yang, G., et al.: Left ventricle full quantification challenge. In: MICCAI 2019 (2019). https://lvquan19.github.io/
Li, J., Hu, Z.: Left ventricle full quantification using deep layer aggregation based multitask relationship learning. In: Pop, M., et al. (eds.) STACOM 2018. LNCS, vol. 11395, pp. 381–388. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12029-0_41
Corral Acero, J., et al.: Left ventricle quantification with cardiac MRI: deep learning meets statistical models of deformation. In: Pop, M., et al. (eds.) STACOM 2019. LNCS, vol. 12009, pp. 384–394. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39074-7_40
Acknowledgement
Sofie Tilborghs is supported by a Ph.D fellowship of the Research Foundation - Flanders (FWO). The computational resources and services used in this work were provided in part by the VSC (Flemisch Supercomputer Center), funded by the Research Foundation - Flanders (FWO) and the Flemisch Government - department EWI. This research also received funding from the Flemish Government under the “Onderzoeksprogramma Artificiële intelligentie (AI) Vlaanderen” programme and is also partially funded by KU Leuven Internal Funds C24/19/047 (promotor F. Maes).
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
Tilborghs, S., Dresselaers, T., Claus, P., Bogaert, J., Maes, F. (2021). Shape Constrained CNN for Cardiac MR Segmentation with Simultaneous Prediction of Shape and Pose Parameters. 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_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-68107-4_13
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)
