Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Attentive Transfer Learning via Self-supervised Learning for Cervical Dysplasia Diagnosis

  • Chae, Jinyeong (Dept. of Artificial Intelligence, Dongguk University) ;
  • Zimmermann, Roger (School of Computing, National University of Singapore) ;
  • Kim, Dongho (Dongguk Institute of Convergence Education, Dongguk University) ;
  • Kim, Jihie (Dept. of Artificial Intelligence, Dongguk University)
  • Received : 2021.02.02
  • Accepted : 2021.03.26
  • Published : 2021.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

Keywords

Acknowledgement

This research was supported by the MSIT (Ministry of Science, ICT), Korea (No. 2019-0-01599, High-Potential Individuals Global Training Program) supervised by the Institute for Information and Communications Technology Planning and Evaluation. We would like to express our gratitude to Dr. Mark Schiffman, Division of Cancer Epidemiology & Genetics, US National Cancer Institute, for allowing us to use one of the NCI datasets.

References

  1. M. Arbyn, E. Weiderpass, L. Bruni, S. de Sanjose, M. Saraiya, J. Ferlay, and F. Bray, "Estimates of incidence and mortality of cervical cancer in 2018: a worldwide analysis," The Lancet Global Health, vol. 8, no. 2, pp. e191-e203, 2020. https://doi.org/10.1016/s2214-109x(19)30482-6
  2. T. Xu, H. Zhang, C. Xin, E. Kim, L. R. Long, Z. Xue, S. Antani, and X. Huang, "Multi-feature based benchmark for cervical dysplasia classification evaluation," Pattern Recognition, vol. 63, pp. 468-475, 2017. https://doi.org/10.1016/j.patcog.2016.09.027
  3. Z. Alyafeai and L. Ghouti, "A fully-automated deep learning pipeline for cervical cancer classification," Expert Systems with Applications, vol. 141, article no. 112951, 2020. https://doi.org/10.1016/j.eswa.2019.112951
  4. A. M. Vasudha and M. Juneja, "Cervix cancer classification using colposcopy images by deep learning method," International Journal of Engineering Technology Science and Research, vol. 5, pp. 426-432, 2018.
  5. S. Gidaris, P. Singh, and N. Komodakis, "Unsupervised representation learning by predicting image rotations," in Proceedings of the 6th International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018.
  6. T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, "A simple framework for contrastive learning of visual representations," in Proceedings of the 37th International Conference on Machine Learning (ICML), 2020, pp. 1597-1607.
  7. K. He, H. Fan, Y. Wu, S. Xie, and R. Girshick, "Momentum contrast for unsupervised visual representation learning," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, 2020, pp. 9729-9738.
  8. R. Gorantla, R. K. Singh, R. Pandey, and M. Jain, "Cervical cancer diagnosis using cervixnet: a deep learning approach," in Proceedings of 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), Athens, Greece, 2019, pp. 397-404.
  9. S. Mustafa and M. Dauda, "Evaluating convolution neural network optimization algorithms for classification of cervical cancer macro images," in Proceedings of 2019 15th International Conference on Electronics, Computer and Computation (ICECCO), Abuja, Nigeria, 2019, pp. 1-5.
  10. V. Kudva, K. Prasad, and S. Guruvare, "Transfer learning for classification of uterine cervix images for cervical cancer screening," in Advances in Communication, Signal Processing, VLSI, and Embedded Systems. Singapore: Springer, 2020, pp. 299-312.
  11. ClinicalTrials.gov, "An innovative treatment for cervical precancer (UH3)," 2017 [Online]. Available: https://www.clinicaltrials.gov/ct2/show/NCT03084081.