Abstract
Semi-supervised learning can reduce the burden of manual label data and improve classification performance by learning with unlabelled data. However, due to the absence of label constraints, unlabelled data is usually ambiguous, which typically results in requiring large datasets to learn the correct feature space distribution. The inherently small sample characteristics of medical image datasets may make semi-supervised learning unstable, which may lead to mixed results and even degrade performance. The domain knowledge (DK) of the physician is of great value for disease diagnosis. In this paper, we propose to promote semi-supervised learning with DK and develop a DScGANS model (DScGAN (dual-path semi-supervised conditional generative adversarial networks) and S3VM (semi-supervised support vector machine)) to diagnose ultrasound thyroid nodules. DScGAN uses DK as a condition and multimodal ultrasound data for training. We concatenate the image representation of DScGAN learning and use it as the input of S3VM. DK will be used as a condition to constrain S3VM for thyroid nodule classification. The experimental results show that our proposed model can effectively avoid mixed results that may occur in semi-supervised learning with a small medical dataset with insufficient labels. Additionally, our model provides stable and advanced diagnostic performance and is potentially integrated into the thyroid ultrasound system.
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
Acharya, U.R., Faust, O., Sree, S.V., et al.: ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform. Comput. Methods Programs Biomed. 107(2), 233–241 (2012)
Park, J.Y., Lee, H.J., Jang, H.W., et al.: A proposal for a thyroid imaging reporting and image system for ultrasound features of thyroid carcinoma. Thyroid 19(11), 1257–1264 (2009)
Hong, Y., et al.: Real-time ultrasound elastography in the differential diagnosis of benign and malignant thyroid nodules. J. Ultrasound Med. 28(7), 861–867 (2009)
Wang, J., Li, S., Song, W., et al.: Learning from weakly-labelled clinical image for automatic thyroid nodule classification in ultrasound images. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 3114–3118. IEEE (2018)
Ding, J., Cheng, H., Huang, J., et al.: Multiple-instance learning with global and local features for thyroid ultrasound image classification. In: 2014 7th International Conference on Biomedical Engineering and Informatics, pp. 66–70. IEEE (2014)
Odena, A.: Semi-supervised learning with generative adversarial networks. arXiv preprint arXiv:1606.01583 (2016)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)
Gu, B., Yuan, X.T., Chen, S., et al.: New incremental learning algorithm for semi-supervised support vector machine. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1475–1484. ACM (2018)
Chapelle, O., Zien, A.: Semi-supervised classification by low density separation. In: AISTATS 2005, pp. 57–64 (2005)
Koundal, D., Vishraj, R., Gupta, S., et al.: An automatic ROI extraction technique for Thyroid Ultrasound image. In: 2015 2nd International Conference on Recent Advances in Engineering & Computational Sciences (RAECS), pp. 1–5. IEEE (2015)
Falcão, A.X., Udupa, J.K., Samarasekera, S., et al.: User-steered image segmentation paradigms: live wire and live lane. Graph. Models Image Process. 60(4), 233–260 (1998)
Fitzgibbon, A., Pilu, M., Fisher, R.B.: Direct least square fitting of ellipses. IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 476–480 (1999)
Wang, H., Yang, Y., Peng, B., et al.: A thyroid nodule classification method based on TI-RADS. In: Ninth International Conference on Digital Image Processing (ICDIP 2017), vol. 10420, pp. 1042041. International Society for Optics and Photonics (2017)
Zhou, J.X., Liu, X., Xu, T.W., et al.: A new fusion approach for content-based image retrieval with color histogram and local directional pattern. Int. J. Mach. Learn. Cybernet. 9(4), 677–689 (2018). https://doi.org/10.1007/s13042-016-0597-9
Acknowledgements
This work is partly supported by the National Natural Science Foundation of China (Grant number 61872261), the Funding Project of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University (Grant No. 2018-VRLAB2018B07), Shanxi Scholarship Council of China (201801D121139) and the Department of Radiology, Shanxi Province Cancer Hospital.
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
Yang, W. et al. (2019). DScGANS: Integrate Domain Knowledge in Training Dual-Path Semi-supervised Conditional Generative Adversarial Networks and S3VM for Ultrasonography Thyroid Nodules Classification. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11767. Springer, Cham. https://doi.org/10.1007/978-3-030-32251-9_61
Download citation
DOI: https://doi.org/10.1007/978-3-030-32251-9_61
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32250-2
Online ISBN: 978-3-030-32251-9
eBook Packages: Computer ScienceComputer Science (R0)
