Abstract
The convolutional neural network (CNN) is a standard tool for image recognition. To improve the performance of CNNs, it is important to design not only the network architecture but also the preprocessing of the input image. Extracting or enhancing the meaningful features of the input image in the preprocessing stage can help to improve the CNN performance. In this paper, we focus on the use of the well-known image processing filters, such as the edge extraction and denoising, and add the preprocessed images to the input of CNNs. As the optimal filter selection depends on dataset, we develop a joint optimization method of CNN and image processing filter selection. We represent the image processing filter selection by a binary vector and introduce the probability distribution of the vector. To derive the gradient-based optimization algorithm, we compute the gradients of weight and distribution parameters on the expected loss under the distribution. The proposed method is applied to an embryo grading task for in vitro fertilization, where the embryo grade is assigned based on the morphological criterion. The experimental result shows that the proposed method succeeds to reduce the test error by more than 8% compared with the naive CNN models.
K. Uchida, S. Saito and P. D. Pamungkasari—Equal contribution.
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
Akimoto, Y., Shirakawa, S., Yoshinari, N., Uchida, K., Saito, S., Nishida, K.: Adaptive stochastic natural gradient method for one-shot neural architecture search. In: Proceedings of the 36th International Conference on Machine Learning (ICML), vol. 97, pp. 171–180 (2019)
Alfaraj, S., Alzaher, F., Alshwaiaer, S., Ahmed, A.: Pregnancy outcome of day 3 versus day 5 embryo transfer: a retrospective analysis. Asian Pac. J. Reprod. 6(2), 89–92 (2017). https://doi.org/10.12980/apjr.6.20170208
Amari, S.: Natural gradient works efficiently in learning. Neural Comput. 10(2), 251–276 (1998)
Calderon, S., et al.: Assessing the impact of the deceived non local means filter as a preprocessing stage in a convolutional neural network based approach for age estimation using digital hand X-ray images. In: 25th IEEE International Conference on Image Processing (ICIP), pp. 1752–1756 (2018). https://doi.org/10.1109/ICIP.2018.8451191
Chen, T.J., Zheng, W.L., Liu, C.H., Huang, I., Lai, H.H., Liu, M.: Using deep learning with large dataset of microscope images to develop an automated embryo grading system. Fertil. Reprod. 01(01), 51–56 (2019). https://doi.org/10.1142/S2661318219500051
Craciunas, L., et al.: Conventional and modern markers of endometrial receptivity: a systematic review and meta-analysis. Hum. Reprod. Update 25(2), 202–223 (2019). https://doi.org/10.1093/humupd/dmy044
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International Conference on Computer Vision (ICCV), pp. 1026–1034 (2015). https://doi.org/10.1109/ICCV.2015.123
Khan, A., Gould, S., Salzmann, M.: Deep convolutional neural networks for human embryonic cell counting. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 339–348. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46604-0_25
Khosravi, P., et al.: Deep learning enables robust assessment and selection of human Blastocysts after in vitro fertilization. Nat. Partner J. Digit. Med. 02, 21 (2019). https://doi.org/10.1038/s41746-019-0096-y
Lin, M., Chen, Q., Yan, S.: Network in network. In: International Conference on Learning Representations (ICLR) (2014)
Moussavi, F., Wang, Y., Lorenzen, P., Oakley, J., Russakoff, D., Gould, S.: A unified graphical models framework for automated human embryo tracking in time lapse microscopy. In: IEEE 11th International Symposium on Biomedical Imaging, pp. 314–320 (2014)
Racowsky, C., Jackson, K.V., Cekleniak, N.A., Fox, J.H., Hornstein, M.D., Ginsburg, E.S.: The number of eight-cell embryos is a key determinant for selecting day 3 or day 5 transfer. Fertil. Steril. 73(3), 558–564 (2000). https://doi.org/10.1016/S0015-0282(99)00565-8
Shirakawa, S., Iwata, Y., Akimoto, Y.: Dynamic optimization of neural network structures using probabilistic modeling. In: Thirty-Second AAAI Conference on Artificial Intelligence (AAAI), pp. 4074–4082 (2018)
Shota, S., Shirakawa, S., Akimoto, Y.: Embedded feature selection using probabilistic model-based optimization. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion (GECCO), pp. 1922–1925 (2018). https://doi.org/10.1145/3205651.3208227
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR) (2015)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Sutskever, I., Martens, J., Dahl, G., Hinton, G.: On the importance of initialization and momentum in deep learning. In: Proceedings of the 30th International Conference on Machine Learning (ICML), vol. 28, pp. 1139–1147 (2013)
Veeck, L.: An Atlas of Human Gametes and Conceptuses: An Illustrated Reference for Assisted Reproductive Technology. The Parthenon Publishing Group, New York (1999)
Wang, Y., Moussavi, F., Lorenzen, P.: Automated embryo stage classification in time-lapse microscopy video of early human embryo development. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8150, pp. 460–467. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40763-5_57
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Uchida, K. et al. (2019). Joint Optimization of Convolutional Neural Network and Image Preprocessing Selection for Embryo Grade Prediction in In Vitro Fertilization. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2019. Lecture Notes in Computer Science(), vol 11845. Springer, Cham. https://doi.org/10.1007/978-3-030-33723-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-33723-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33722-3
Online ISBN: 978-3-030-33723-0
eBook Packages: Computer ScienceComputer Science (R0)