Abstract
Automatic segmentation of ventricles and myocardium in late gadolinium-enhanced (LGE) cardiac images is an important assessment for the clinical diagnosis of myocardial infarction. The most segmentation methods rely on the annotation of ventricles and myocardium. However, pathological myocardium in LGE images makes its annotation difficult to be obtained. In this paper, we propose a new deep unsupervised domain adaptation (DUDA) framework, which can effectively solve the segmentation problem of LGE images without any annotations through cross domain based adversarial learning. A CycleGAN network is used to construct the LGE image training set, meanwhile, a encoder and classier is used as a segmentor to generate the prediction mask. To keep our domain adaption model segmentation results consistent, a new loss function named cross-domain consistency loss is introduced. We tested our method on the dataset of the MICCAI2019 Multi-Sequence cardiac MR image Segmentation Challenge. The average dice of the myocardium, left ventricle, and right ventricle segmentation is 0.762, 0.857, and 0.841, respectively. Compared with other domain adaptation methods, our method can well segment myocardium and right ventricle structures in LGE images. Experimental results prove the superiority of our proposed framework and it can effectively help doctors diagnose myocardial infarction faster without any manual intervention in the clinic.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 95–104 (2017)
Cai, J., Zhang, Z., Cui, L., Zheng, Y., Yang, L.: Towards cross-modal organ translation and segmentation: a cycle- and shape-consistent generative adversarial network. Med. Image Anal. 52, 174–184 (2019)
Campello, V.M., MartÃn-Isla, C., Izquierdo, C., Petersen, S.E., Ballester, M.A.G., Lekadir, K.: Combining multi-sequence and synthetic images for improved segmentation of late gadolinium enhancement cardiac MRI. In: Pop, M., et al. (eds.) STACOM 2019. LNCS, vol. 12009, pp. 290–299. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39074-7_31
Chen, C., et al.: Unsupervised multi-modal style transfer for cardiac MR segmentation. In: Pop, M., et al. (eds.) STACOM 2019. LNCS, vol. 12009, pp. 209–219. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39074-7_22
Chen, C., Dou, Q., Chen, H., Heng, P.-A.: Semantic-aware generative adversarial nets for unsupervised domain adaptation in chest x-ray segmentation. In: Shi, Y., Suk, H.-I., Liu, M. (eds.) MLMI 2018. LNCS, vol. 11046, pp. 143–151. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00919-9_17
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: Conference on Artificial Intelligence (AAAI), pp. 865–872 (2019)
Chen, J., Li, H., Zhang, J., Menze, B.: Adversarial convolutional networks with weak domain-transfer for multi-sequence cardiac MR images segmentation. In: Pop, M., et al. (eds.) STACOM 2019. LNCS, vol. 12009, pp. 317–325. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39074-7_34
Chen, Y., Lin, Y., Yang, M., Huang, J.: CrDoCo: pixel-level domain transfer with cross-domain consistency. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1791–1800 (2019)
Dou, Q., et al.: PnP-AdaNet: plug-and-play adversarial domain adaptation network with a benchmark at cross-modality cardiac segmentation. arXiv:1812.07907 (2018)
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: International Joint Conference on Artificial Intelligence, pp. 691–697 (2018)
Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 189–209 (2016)
Han, W.K., Farzaneh-Far, A., Kim, R.J.: Cardiovascular magnetic resonance in patients with myocardial infarction: current and emerging applications. J. Am. Coll. Cardiol. 55(1), 1–16 (2009)
Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: International Conference on Machine Learning (ICML), pp. 1994–2003 (2018)
Huo, Y., Xu, Z., Bao, S., Assad, A., Abramson, R.G., Landman, B.A.: Adversarial synthesis learning enables segmentation without target modality ground truth. In: IEEE Conference on International Symposium on Biomedical Imaging (ISBI), pp. 1217–1220 (2018)
Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5967–5976 (2017)
Joyce, T., Chartsias, A., Tsaftaris, S.A.: Deep multi-class segmentation without ground-truth labels. In: International conference on Medical Imaging with Deep Learning (MIDL) (2018)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning (ICML), pp. 97–105 (2015)
Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Networks 22(2), 199–210 (2011)
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
Tao, X., Wei, H., Xue, W., Ni, D.: Segmentation of multimodal myocardial images using shape-transfer GAN. In: Pop, M., et al. (eds.) STACOM 2019. LNCS, vol. 12009, pp. 271–279. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-39074-7_29
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2962–2971 (2017)
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. arXiv:1412.3474 (2014)
Vesal, S., Ravikumar, N., Maier, A.: Automated multi-sequence cardiac MRI segmentation using supervised domain adaptation. arXiv:1908.07726 (2019)
Yang, J., Dvornek, N.C., Zhang, F., Chapiro, J., Lin, M.D., Duncan, J.S.: Unsupervised domain adaptation via disentangled representations: application to cross-modality liver segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 255–263. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_29
Yu, F., Koltun, V., Funkhouser, T.: Dilated residual networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 636–644 (2017)
Zhang, Y., Miao, S., Mansi, T., Liao, R.: Task driven generative modeling for unsupervised domain adaptation: application to x-ray image segmentation. arXiv:1806.07201 (2018)
Zhang, Z., Yang, L., Zheng, Y.: Translating and segmenting multimodal medical volumes with cycle- and shape-consistency generative adversarial network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9242–9251 (2018)
Zhu, J., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: International Conference on Computer Vision (ICCV), pp. 2242–2251 (2017)
Zhuang, X.: Multivariate mixture model for myocardium segmentation combining multi-source images. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 2933–2946 (2019)
Acknowledgment
This work was supported in part by the National Science Foundation of China (61702003), and in part by the Anhui Provincial Natural Science Foundation (1708085QF143, 1808085MF175). The authors also thank all the anonymous reviewers for their valuable comments and suggestions, which were helpful for improving the quality of the paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, Y., Du, X. (2020). DUDA: Deep Unsupervised Domain Adaptation Learning for Multi-sequence Cardiac MR Image Segmentation. In: Peng, Y., et al. Pattern Recognition and Computer Vision. PRCV 2020. Lecture Notes in Computer Science(), vol 12305. Springer, Cham. https://doi.org/10.1007/978-3-030-60633-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-60633-6_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60632-9
Online ISBN: 978-3-030-60633-6
eBook Packages: Computer ScienceComputer Science (R0)