Abstract
Accurate segmentation of neonatal brain MR images is critical for studying early brain development. Recently, supervised learning-based methods, i.e., using convolutional neural networks (CNNs), have been successfully applied to infant brain segmentation. Although these CNN-based methods have achieved reasonable segmentation results on the testing subjects acquired with similar imaging protocol as the training subjects, they are typically not able to produce reasonable results for the testing subjects acquired with different imaging protocols. To address this practical issue, in this paper, we propose leveraging a cycle-consistent generative adversarial network (CycleGAN) to transfer each testing image (of a new dataset/cross-dataset) into the domain of training data, thus obtaining the transferred testing image with similar intensity appearance as the training images. Then, a densely-connected U-Net based segmentation model, which has been trained on the training data, can be utilized to robustly segment each transferred testing image. Experimental results demonstrate the superior performance of our proposed method, over existing methods, on segmenting cross-dataset of neonatal brain MR images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shen, D., et al.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19(3), 221–248 (2017)
Wang, L., et al.: LINKS: Learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images. NeuroImage 108(3), 160–172 (2015)
Moeskops, P., et al.: Automatic segmentation of MR brain images with a convolutional neural network. IEEE Trans. Med. Imaging 35(5), 1252–1261 (2016)
Nie, D., et al.: 3-D fully convolutional networks for multimodal isointense infant brain image segmentation. IEEE Trans. Cybern. 99(2), 1–14 (2018)
Li, G., et al.: Computational neuroanatomy of baby brains: a review. NeuroImage 185(1), 906–925 (2018)
Zhu, J., et al.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: CVPR (2017)
Sled, J.G., et al.: A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans. Med. Imaging 17(1), 87–97 (1998)
Wang, L., et al.: Volume-based analysis of 6-month-old infant brain MRI for autism biomarker identification and early diagnosis. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11072, pp. 411–419. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00931-1_47
He, K., et al.: Deep residual learning for image recognition. In: CVPR (2016)
Milletari, F., et al.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: Fourth International Conference on 3D Vision (2016)
Litjens, G., et al.: Evaluation of prostate segmentation algorithms for MRI: the PROMISE12 challenge. Med. Image Anal. 18(2), 359–373 (2014)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, J. et al. (2019). CNS: CycleGAN-Assisted Neonatal Segmentation Model for Cross-Datasets. In: Zhang, D., Zhou, L., Jie, B., Liu, M. (eds) Graph Learning in Medical Imaging. GLMI 2019. Lecture Notes in Computer Science(), vol 11849. Springer, Cham. https://doi.org/10.1007/978-3-030-35817-4_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-35817-4_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-35816-7
Online ISBN: 978-3-030-35817-4
eBook Packages: Computer ScienceComputer Science (R0)