Automatically Designing CNN Architectures for Medical Image Segmentation

  • Aliasghar MortaziEmail author
  • Ulas Bagci
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11046)


Deep neural network architectures have traditionally been designed and explored with human expertise in a long-lasting trial-and-error process. This process requires huge amount of time, expertise, and resources. To address this tedious problem, we propose a novel algorithm to optimally find hyperparameters of a deep network architecture automatically. We specifically focus on designing neural architectures for medical image segmentation task. Our proposed method is based on a policy gradient reinforcement learning for which the reward function is assigned a segmentation evaluation utility (i.e., dice index). We show the efficacy of the proposed method with its low computational cost in comparison with the state-of-the-art medical image segmentation networks. We also present a new architecture design, a densely connected encoder-decoder CNN, as a strong baseline architecture to apply the proposed hyperparameter search algorithm. We apply the proposed algorithm to each layer of the baseline architectures. As an application, we train the proposed system on cine cardiac MR images from Automated Cardiac Diagnosis Challenge (ACDC) MICCAI 2017. Starting from a baseline segmentation architecture, the resulting network architecture obtains the state-of-the-art results in accuracy without performing any trial-and-error based architecture design approaches or close supervision of the hyperparameters changes.


Policy gradient Reinforcement learning DenseCNN Cardiac MRI segmentation 


  1. 1.
    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). Scholar
  2. 2.
    Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation, arXiv preprint arXiv:1511.00561 (2015)
  3. 3.
    Mortazi, A., Karim, R., Rhode, K., Burt, J., Bagci, U.: CardiacNET: segmentation of left atrium and proximal pulmonary veins from MRI using multi-view CNN. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 377–385. Springer, Cham (2017). Scholar
  4. 4.
    Zoph, B., Le, Quoc V.: Neural architecture search with reinforcement learning, arXiv preprint arXiv:1611.01578 (2016)
  5. 5.
    Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15(2), 185–212 (2009)CrossRefGoogle Scholar
  6. 6.
    Kohl, N., Stone, P.: Policy gradient reinforcement learning for fast quadrupedal locomotion, In: 2004 IEEE International Conference on Robotics and Automation, Proceedings. ICRA 2004, vol. 3. IEEE (2004)Google Scholar
  7. 7.
    Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. Adv. Neural Inf. Process. Syst. 1057–1063 (2000)Google Scholar
  8. 8.
    Huang, G., Liu, Z., Weinberger, K.Q., van der Maaten, L.: Densely connected convolutional networks, arXiv preprint arXiv:1608.06993
  9. 9.
    Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions (2017)Google Scholar
  10. 10.
    LaLonde, R., Bagci, U.: Capsules for object segmentation, arXiv preprint arXiv:1804.04241 (2018)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Center for Research in Computer Vision (CRCV), University of Central FloridaOrlandoUSA

Personalised recommendations