Abstract
Segmentation of the late-stage gadolinium-enhanced magnetic resonance imaging (LGE-MRI) is a critical step in the ablation therapy for atrial fibrillation (AF). In this work, we propose an end-to-end deep learning-based segmentation method for delineating 3D left atrial (LA) structures in multiple domains. The proposed method uses the 6 layers deep U-Net architecture as the segmentation backbone. Curriculum learning is integrated into the deep U-Net architecture, helping the network learn step by step from easy to difficult scene. We have tested normal and strong version of data augmentation methods, to verify the effect of reducing domain shifts. Other techniques like Fourier-based data augmentation and Swin Transformer Block have also been explored to further improve the segmentation performance. The experimental results demonstrate that the strong version of data augmentation method can reduce the domain shifts and achieve more accurate result, with mean Dice score of 0.881 on the validation set of LAScarQS 2022 challenge. The evaluation results demonstrate our method’s effectiveness on left atrial segmentation in multi-sequence cardiac magnetic resonance (CMR) data.
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
Zhuang, Xiahai, et al.: Cardiac segmentation on late gadolinium enhancement MRI: a benchmark study from multi-sequence cardiac MR segmentation challenge. (2020) arXiv preprint arXiv:2006.12434
Liu, Y., Duan, Y., Zeng, T.: Learning multi-level structural information for small organ segmentation. Sig. Process. 193, 108418 (2022)
Yueyun, L., Wang, Y., Duan, Y.: Effective 3D Boundary Learning via a Nonlocal Deformable Network. In: 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI). IEEE (2022)
Liu, L., et al.: Rician noise and intensity nonuniformity correction (NNC) model for MRI data. Biomed. Signal Process. Control 49, 506–519 (2019)
Xia, Q., Yao, Y., Hu, Z., Hao, A.: Automatic 3D Atrial Segmentation from GE-MRIs Using Volumetric Fully Convolutional Networks. In: Pop, M., et al. (eds.) STACOM 2018. LNCS, vol. 11395, pp. 211–220. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12029-0_23
Yang, X., et al.: Combating Uncertainty with Novel Losses for Automatic Left Atrium Segmentation. In: Pop, M., et al. (eds.) STACOM 2018. LNCS, vol. 11395, pp. 246–254. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12029-0_27
Liu, Y., Zhang, M., Zhan, Q., Gu, D., Liu, G.: Two-Stage Method for Segmentation of the Myocardial Scars and Edema on Multi-sequence Cardiac Magnetic Resonance. In: Zhuang, X., Li, L. (eds.) MyoPS 2020. LNCS, vol. 12554, pp. 26–36. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65651-5_3
Parreño, M., Paredes, R., Albiol, A.: Deidentifying MRI data domain by iterative backpropagation. International Workshop on Statistical Atlases and Computational Models of the Heart, Springer, Cham (2020)
Scannell, C.M., Chiribiri, A., Veta, M.: Domain-adversarial learning for multi-Centre, multi-vendor, and multi-disease cardiac MR image segmentation. International Workshop on Statistical Atlases and Computational Models of the Heart, Springer, Cham (2020)
Liu, X., Thermos, S., O’Neil, A., Tsaftaris, S.A.: Semi-supervised Meta-learning with Disentanglement for Domain-Generalised Medical Image Segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12902, pp. 307–317. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87196-3_29
Yoshua, B., et al.: Curriculum learning In: Proceedings of the 26th annual international conference on machine learning 60, p. 6 (2009)
Hengfei, C., et al.: Deep U-Net architecture with curriculum learning for myocardial pathology segmentation in multi-sequence cardiac magnetic resonance images Knowl. Based Syst. 249, 108942 (2022)
Xu, Q., Zhang, R., Zhang, Y., Wang, Y., Tian, Q.: A fourier-based framework for domain generalization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 14383–14392 (2021)
Li, L., Veronika, A.Z., Schnabel, J.A., Zhuang, X.: AtrialJSQnet: a New Framework for Joint Segmentation and Quantification of Left Atrium and Scars Incorporating Spatial and Shape Information. Med. Image Anal. 76, 102303 (2022)
Li, L., Zimmer, V.A., Schnabel, J.A., Zhuang, X.: Medical Image Analysis on Left Atrial LGE MRI for Atrial Fibrillation Studies: A Review. Med. Image Anal. 77, 102360 (2022)
Lei Li, Zimmer, V.A., Schnabel, J.A., Zhuang, X.: AtrialGeneral: domain Generalization for Left Atrial Segmentation of Multi-Center LGE MRIs, MICCAI, 557–566 (2021)
Kaiyang, Z., et al.: Domain generalization with mix style. (2021) arXiv preprint arXiv:2104.02008
Hatamizadeh, A., et al.: SWIN UNETR: SWIN transformers for semantic segmentation of brain tumors in MRI images. (2022) arXiv preprint arXiv:2201.01266
Acknowledgment
The study was supported in part by the National Natural Science Foundation of China under Grants 62271405 and 62171377, in part by the Fundamental Research Funds for the Central Universities under Grant 3102020QD1001, and in part by the Key Research and Development Program of Shaanxi Province under Grant 2022GY-084.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jiang, L., Li, Y., Wang, Y., Cui, H., Xia, Y., Zhang, Y. (2023). Deep U-Net Architecture with Curriculum Learning for Left Atrial Segmentation. In: Zhuang, X., Li, L., Wang, S., Wu, F. (eds) Left Atrial and Scar Quantification and Segmentation. LAScarQS 2022. Lecture Notes in Computer Science, vol 13586. Springer, Cham. https://doi.org/10.1007/978-3-031-31778-1_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-31778-1_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31777-4
Online ISBN: 978-3-031-31778-1
eBook Packages: Computer ScienceComputer Science (R0)
