Abstract
Quantification of heart geometry is important in the clinical diagnosis of cardiovascular diseases. Changes in geometry are indicative of remodelling processes as the heart tissue adapts to disease. Coronary Computed Tomography Angiography (CCTA) is considered a first line tool for patients at low or intermediate risk of coronary artery disease, while Coronary Magnetic Resonance Angiography (CMRA) is a promising alternative due to the absence of radiation-induced risks and high performance in the evaluation of cardiac geometry. Yet, the accuracy of an image-based diagnosis is susceptible to the quality of volume segmentations. Deep Learning (DL) techniques are gradually being adopted to perform such segmentations and substitute the tedious and manual work performed by physicians. However, practical applications of DL techniques on a large scale are still limited due to their poor adaptability across modalities and patients. Hence, the aim of this work was to develop a pipeline to perform automatic heart segmentation of multiple cardiac imaging scans, addressing the domain shift between MRs (target) and CTs (source). We trained two Domain Adaptation (DA) methods, using Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs), following different training routines, which we refer to as un- and semi- supervised approaches. We also trained a baseline supervised model following state-of-the-art choice of parameters and augmentation. The results showed that DA methods can be significantly boosted by the addition of a few supervised cases, increasing Dice and Hausdorff distance metrics across the main cardiac structures.
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
References
Abdeltawab, H., et al.: A deep learning-based approach for automatic segmentation and quantification of the left ventricle from cardiac cine MR images. Comput. Med. Imaging Grap. 81, 101717 (2020). https://doi.org/10.1016/j.compmedimag.2020.101717
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1–2), 151–175 (2010). https://doi.org/10.1007/s10994-009-5152-4
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)
Bustin, A., et al.: 3D whole-heart isotropic sub-millimeter resolution coronary magnetic resonance angiography with non-rigid motion-compensated PROST. J. Cardiovasc. Magn. Reson. 22(1), 24 (2020). https://doi.org/10.1186/s12968-020-00611-5
Chen, C., et al.: Deep learning for cardiac image segmentation: a review. Front. Cardiovasc. Med. 7, 25 (2020). https://doi.org/10.3389/fcvm.2020.00025
Chen, C., Dou, Q., Chen, H., Qin, J., Heng, P.: Synergistic image and feature adaptation: towards cross-modality domain adaptation for medical image segmentation. In: AAAI (2019)
Chen, C., Dou, Q., Chen, H., Qin, J., Heng, P.A.: Unsupervised bidirectional cross-modality adaptation via deeply synergistic image and feature alignment for medical image segmentation (2020)
Chen, X., Pawlowski, N., Rajchl, M., Glocker, B., Konukoglu, E.: Deep generative models in the real-world: an open challenge from medical imaging. ArXiv abs/1806.05452 (2018)
Consortium, M.: Monai: Medical open network for AI (2022). https://doi.org/10.5281/zenodo.6639453. If you use this software, please cite it using these metadata
Dou, Q., Ouyang, C., Chen, C., Chen, H., Heng, P.: Unsupervised cross-modality domain adaptation of convnets for biomedical image segmentations with adversarial loss. In: IJCAI (2018)
Fedorov, A., et al.: 3D slicer as an image computing platform for the quantitative imaging network. Magn. Reson. Imaging 30(9), 1323–1341 (2012)
Habijan, M., Leventic, H., Galic, I., Babin, D.: Whole heart segmentation from CT images using 3D U-Net architecture. In: 2019 International Conference on Systems, Signals, and Image Processing, 121–126 (2019). https://doi.org/10.1109/IWSSIP.2019.8787253
Isensee, F., Jaeger, P.F., Kohl, S.A.A., Petersen, J., Maier-Hein, K.H.: nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. Methods 18(2), 203–211 (2021). https://doi.org/10.1038/s41592-020-01008-z
Rueckert, D., Sonoda, L., Hayes, C., Hill, D., Leach, M., Hawkes, D.: Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999). https://doi.org/10.1109/42.796284
Skandarani, Y., Painchaud, N., Jodoin, P.M., Lalande, A.: On the effectiveness of GAN generated cardiac MRIs for segmentation. ArXiv abs/2005.09026 (2020)
Wu, F., Zhuang, X.: Unsupervised domain adaptation with variational approximation for cardiac segmentation. CoRR abs/2106.08752 (2021), https://arxiv.org/abs/2106.08752
Xu, H., Niederer, S.A., Williams, S.E., Newby, D.E., Williams, M.C., Young, A.A.: Whole heart anatomical refinement from CCTA using extrapolation and parcellation. In: Ennis, D.B., Perotti, L.E., Wang, V.Y. (eds.) FIMH 2021. LNCS, vol. 12738, pp. 63–70. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-78710-3_7
Yan, W., et al.: The domain shift problem of medical image segmentation and vendor-adaptation by Unet-GAN. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 623–631. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_69
Zhang, T., Yang, J., Zheng, C., Lin, G., Cai, J., Kot, A.C.: Task-in-all domain adaptation for semantic segmentation. In: 2019 IEEE International Conference on Visual Communications and Image Processing, VCIP (2019). https://doi.org/10.1109/VCIP47243.2019.8965736
Zhuang, X., et al.: Evaluation of algorithms for multi-modality whole heart segmentation: an open-access grand challenge. Med. Image Anal. 58, 101537 (2019). https://doi.org/10.1016/j.media.2019.101537
Acknowledgments
Research supported by ESPRC and Siemens Healthineers.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Muffoletto, M. et al. (2022). Comparison of Semi- and Un-Supervised Domain Adaptation Methods for Whole-Heart Segmentation. In: Camara, O., et al. Statistical Atlases and Computational Models of the Heart. Regular and CMRxMotion Challenge Papers. STACOM 2022. Lecture Notes in Computer Science, vol 13593. Springer, Cham. https://doi.org/10.1007/978-3-031-23443-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-23443-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23442-2
Online ISBN: 978-3-031-23443-9
eBook Packages: Computer ScienceComputer Science (R0)
