Abstract
U-Net and its variants have played important roles in the field of medical image segmentation. However, U-Nets based on conventional 3 * 3 convolution still have some shortcomings, such as the lack of deformation of receptive field. In addition, due to the limited computing resources and memory space on many machines, the allowed sizes of networks deployed on them are also limited. However, it may not be effective to manually design the architectures of U-Nets. In this paper, a U-Net architecture with diamond atrous convolution (DAU-Net) is presented. Furthermore, a multi-objective neural architecture search method with channel sorting of DAU-Net is proposed to search for the better U-Net architectures. Experimental results on the ISIC 2018 dataset of melanoma segmentation show that the proposed method obtains a series of network architectures with different sizes, and the obtained architectures achieve obvious improvements in term of both model sizes and prediction accuracies compared with several popular and manually designed variants of U-Net.
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
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
Zongwei Zhou, Md., Siddiquee, M.R., Tajbakhsh, N., Liang, J.: UNet++: redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans. Med. Imaging 39(6), 1856–1867 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Huang, G., Liu, Z., Maaten, L.V.D., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700–4708 (2017)
Yu, F., Wang, D., Shelhamer, E., Darrell, T.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2403–2412 (2018)
Lee, C.-Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics, pp. 562–570 (2015)
Oktay, O., et al.: Attention U-Net: learning where to look for the pancreas. arXiv preprint arXiv: 1804.03999 (2018)
Lachinov, D., Vasiliev, E., Turlapov, V.: Glioma segmentation with cascaded UNet. In: Crimi, A., Bakas, S., Kuijf, H., Keyvan, F., Reyes, M., van Walsum, T. (eds.) BrainLes 2018. LNCS, vol. 11384, pp. 189–198. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-11726-9_17
Baldeon-Calisto, M., Lai-Yuen, S.K.: AdaResU-Net: multiobjective adaptive convolutional neural network for medical image segmentation. Neurocomputing 392, 325–340 (2020)
Liashchynskyi, P.B., Liashchynskyi, P.B.: Grid search, random search, genetic algorithm: a big comparison for NAS. arXiv preprint arXiv:1912.06059 (2019)
White, C., Neiswanger, W., Savani, Y.: BANANAS: Bayesian optimization with neural architectures for neural architecture search. arXiv preprint arXiv:1910.11858 (2019)
Zhou, Y., Yen, G.G., Yi, Z.: Evolutionary compression of deep neural networks for biomedical image segmentation. IEEE Trans. Neural Netw. Learn. Syst. 31(8), 2916–2929 (2019)
Weng, Yu., Zhou, T., Li, Y., Qiu, X.: NAS-Unet: neural architecture search for medical image segmentation. IEEE Access 7, 44247–44257 (2019)
Wang, X., et al.: BiX-NAS: searching efficient bi-directional architecture for medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 229–238. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87193-2_22
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)
Deb, K., Jain, H.: An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part I: solving problems with box constraints. IEEE Trans. Evol. Comput. 18(4), 577–601 (2013)
Sun, Y., Wang, H., Xue, B., Jin, Y., Yen, G.G., Zhang, M.: Surrogate-assisted evolutionary deep learning using an end-to-end random forest-based performance predictor. IEEE Trans. Evol. Comput. 24(2), 350–364 (2019)
Jie, H., Shen, L., Albanie, S., Sun, G., Enhua, W.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 2011–2023 (2020)
Acknowledgments
This work was supported in part by the Natural Science Foundation of Guangdong Province, China, under Grant 2020A1515011491 and Grant 2019A1515011792, in part by the Science Research Project of Guangzhou University under Grant YG2020008, in part by the Project of Innovation and Developing Universities of Education Department of Guangdong Province under Grant 2019KTSCX130, in part by the Guangzhou Science and Technology Project under Grant 202102080161,in part by the Guangdong Science and Technology Department, Grant 2019B010154004, and in part by the Fundamental Research Funds for the Central Universities, SCUT, under Grant 2017MS043.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ying, W., Yang, K., Wu, Y., Li, J., Zhou, Z., Huang, B. (2022). Multi-objective Evolutionary Architecture Search of U-Net with Diamond Atrous Convolution. In: Li, K., Liu, Y., Wang, W. (eds) Exploration of Novel Intelligent Optimization Algorithms. ISICA 2021. Communications in Computer and Information Science, vol 1590. Springer, Singapore. https://doi.org/10.1007/978-981-19-4109-2_4
Download citation
DOI: https://doi.org/10.1007/978-981-19-4109-2_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-4108-5
Online ISBN: 978-981-19-4109-2
eBook Packages: Computer ScienceComputer Science (R0)