图11 心脏和肋骨的相对位置关系示意图
小结一下,本文介绍了三个在医学影像分割问题上深度学习网络的改进思路:1、网络深层抽象信息与底层细节信息共享,用底层信息补充分割细节;2、网络各个层互补信息,通过最大限度的保留网络信息流来提升分割精度;3、将二维卷积操作换为三维卷积操作从而利用图像层间信息互补提升分割精度。不难看出,当前在医学影像分割竞赛上表现出众的三个工作的改进思路都在于扩大参与计算的信息,希望这点能够提供各位读者在改进分割网络时更多的灵感。
对于医学影像分割,深度学习已经有了非常出色的表现,而且越来越多的新思路和新方法用于不断提高分割精度和稳健性,并逐渐减轻医生繁琐的日常工作,降低视觉疲劳的压力,成为临床医生的有力工具。 参考文献
[1]J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 07–12–June, pp. 3431–3440, 2015.
[2]H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, “Pyramid Scene Parsing Network,” 2016.
[3]O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional Networks for Biomedical Image Segmentation,” Miccai, pp. 234–241, 2015.
[4]L. Yu, X. Yang, H. Chen, J. Qin, and P.-A. Heng, “Volumetric ConvNets with Mixed Residual Connections for Automated Prostate Segmentation from 3D MR Images,” Thirty-First AAAI Conf. Artif. Intell., pp. 66–72, 2017.
[5]S. Wu, S. Zhong, and Y. Liu, “Deep residual learning for image steganalysis,” Multimed. Tools Appl., pp. 1–17, 2017.
[6]G. Huang, Y. Sun, Z. Liu, D. Sedra, and K. Weinberger, “Deep Networks with Stochastic Depth,” 2016.
[7]G. Huang, Z. Liu, K. Q. Weinberger, and L. van der Maaten, “Densely Connected Convolutional Networks,” 2016.
[8]L. Yu et al., “Automatic 3D cardiovascular MR segmentation with densely-connected volumetric convnets,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 10434 LNCS, pp. 287–295, 2017.