Abstract
This paper addresses the domain shift problem for segmentation. As a solution, we propose OLVA, a novel and lightweight unsupervised domain adaptation method based on a Variational Auto-Encoder (VAE) and Optimal Transport (OT) theory. Thanks to the VAE, our model learns a shared cross-domain latent space that follows a normal distribution, which reduces the domain shift. To guarantee valid segmentations, our shared latent space is designed to model the shape rather than the intensity variations. We further rely on an OT loss to match and align the remaining discrepancy between the two domains in the latent space. We demonstrate OLVA’s effectiveness for the segmentation of multiple cardiac structures on the public Multi-Modality Whole Heart Segmentation (MM-WHS) dataset, where the source domain consists of annotated 3D MR images and the unlabelled target domain of 3D CTs. Our results show remarkable improvements with an additional margin of \(12.5\%\) dice score over concurrent generative training approaches.
This work has been supported in part by the European Regional Development. Fund, the Pays de la Loire region on the Connect Talent scheme (MILCOM Project) and Nantes Métropole (Convention 2017-10470).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ackaouy, A., Courty, N., Vallée, E., Commowick, O., Barillot, C., Galassi, F.: Unsupervised domain adaptation with optimal transport in multi-site segmentation of multiple sclerosis lesions from MRI data. Front. Comput. Neurosci. 14, 19 (2020)
Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: ICLR (2017)
Chen, C., Dou, Q., Chen, H., Qin, J., Heng, P.A.: Synergistic image and feature adaptation: towards cross-modality domain adaptation for medical image segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 865–872 (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. IEEE TMI 39, 2494–2505 (2020)
Courty, N., Flamary, R., Tuia, D., Rakotomamonjy, A.: Optimal transport for domain adaptation. IEEE TPAMI 39, 1853–1865 (2017)
Damodaran, B.B., Kellenberger, B., Flamary, R., Tuia, D., Courty, N.: DeepJDOT: deep joint distribution optimal transport for unsupervised domain adaptation. In: ECCV, pp. 447–463 (2018)
David, S.B., Lu, T., Luu, T., Pál, D.: Impossibility theorems for domain adaptation. In: The Thirteenth AISTATS, pp. 129–136 (2010)
Dou, Q., et al.: PnP-AdaNet: plug-and-play adversarial domain adaptation network at unpaired cross-modality cardiac segmentation. IEEE Access 7, 99065–99076 (2019)
Gonzalez Duque, V., Al Chanti, D., Crouzier, M., Nordez, A., Lacourpaille, L., Mateus, D.: Spatio-temporal consistency and negative label transfer for 3D freehand US segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 710–720. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_69
Heimann, T., Mountney, P., John, M., Ionasec, R.: Learning without labeling: domain adaptation for ultrasound transducer localization. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8151, pp. 49–56. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40760-4_7
Huo, Y., et al.: SynSeg-Net: synthetic segmentation without target modality ground truth. IEEE TMI 38(4), 1016–1025 (2018)
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: CVPR, pp. 1125–1134 (2017)
Kantorovich, L.V.: On the translocation of masses. Dokl. Akad. Nauk. USSR (NS) 37, 199–201 (1942)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes (2014)
Kumagai, A., Iwata, T.: Unsupervised domain adaptation by matching distributions based on the maximum mean discrepancy via unilateral transformations. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 4106–4113 (2019)
Li, F., Li, W., Qin, S., Wang, L.: MDFA-Net: multiscale dual-path feature aggregation network for cardiac segmentation on multi-sequence cardiac MR. KBS 106776 (2021)
Liu, K., Tang, W., Zhou, F., Qiu, G.: Spectral regularization for combating mode collapse in GANs. In: ICCV, pp. 6382–6390 (2019)
Ouyang, C., Kamnitsas, K., Biffi, C., Duan, J., Rueckert, D.: Data efficient unsupervised domain adaptation for cross-modality image segmentation. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11765, pp. 669–677. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32245-8_74
Painchaud, N., Skandarani, Y., Judge, T., Bernard, O., Lalande, A., Jodoin, P.M.: Cardiac segmentation with strong anatomical guarantees. IEEE TMI 39(11), 3703–3713 (2020)
Puybareau, É., et al.: Left atrial segmentation in a few seconds using fully convolutional network and transfer learning. In: Pop, M., et al. (eds.) STACOM 2018. LNCS, vol. 11395, pp. 339–347. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12029-0_37
Redko, I., Courty, N., Flamary, R., Tuia, D.: Optimal transport for multi-source domain adaptation under target shift. In: The 22nd AISTATS, pp. 849–858 (2019)
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
Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: CVPR, pp. 7472–7481 (2018)
Wu, F., Zhuang, X.: CF distance: a new domain discrepancy metric and application to explicit domain adaptation for cross-modality cardiac image segmentation. IEEE TMI 39, 4274–4285 (2020)
Yang, J., et al.: Domain-agnostic learning with anatomy-consistent embedding for cross-modality liver segmentation. In: ICCV Workshops (2019)
Zhuang, X., Shen, J.: Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Med. Image Anal. 31, 77–87 (2016)
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
Al Chanti, D., Mateus, D. (2021). OLVA: Optimal Latent Vector Alignment for Unsupervised Domain Adaptation in Medical Image Segmentation. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12903. Springer, Cham. https://doi.org/10.1007/978-3-030-87199-4_25
Download citation
DOI: https://doi.org/10.1007/978-3-030-87199-4_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87198-7
Online ISBN: 978-3-030-87199-4
eBook Packages: Computer ScienceComputer Science (R0)