Abstract
Supervised deep learning approaches provide state-of-the-art performance on medical image classification tasks for disease screening. However, these methods require large labeled datasets that involve resource-intensive expert annotation. Further, disease screening applications have low prevalence of abnormal samples; this class imbalance makes the task more akin to anomaly detection. While the machine learning community has proposed unsupervised deep learning methods for anomaly detection, they have yet to be characterized on medical images where normal vs. anomaly distinctions may be more subtle and variable. In this work, we characterize existing unsupervised anomaly detection methods on retinal fundus images, and find that they require significant fine tuning and offer unsatisfactory performance. We thus propose an efficient and effective transfer-learning based approach for unsupervised anomaly detection. Our method employs a deep convolutional neural network trained on ImageNet as a feature extractor, and subsequently feeds the learned feature representations into an existing unsupervised anomaly detection method. We show that our approach significantly outperforms baselines on two natural image datasets and two retinal fundus image datasets, all with minimal fine-tuning. We further show the ability to leverage very small numbers of labelled anomalies to improve performance. Our work establishes a strong unsupervised baseline for image-based anomaly detection, alongside a flexible and scalable approach for screening applications.
K. Ouardini and H. Yang—Equal contribution.
P. Krishnaswamy and C.-S. Foo—Equal contribution.
Supplementary Material: http://s000.tinyupload.com/?file_id=50006502228459557624.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
References
Andrews, J.T.A., Tanay, T., Morton, E.J., Griffin, L.D.: Transfer representation-learning for anomaly detection. In: ICML Anomaly Detection Workshop (2016)
Azizpour, H., Razavian, A.S., Sullivan, J., Maki, A., Carlsson, S.: Factors of transferability for a generic convnet representation. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1790–1802 (2016)
Bo, Z., et al.: Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018)
Brown, J.M., et al.: Automated diagnosis of plus disease in retinopathy of prematurity using deep convolutional neural networks. JAMA Ophthalmol. 136(7), 803–810 (2018)
Campbell, J.P., Kalpathy-Cramer, J., Dulanto-Reinoso, C.M., Montero-Mendoza, C., et al.: Plus disease in retinopathy of prematurity: a continuous spectrum of vascular abnormality as a basis of diagnostic variability. Ophthalmology 123(11), 2338–2344 (2016)
Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: Advances in Neural Information Processing Systems 31, pp. 9758–9769 (2018)
Gulshan, V., Peng, L., Mega, J.L., Webster, D.R., et al.: Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316(22), 2402–2410 (2016)
Kaggle: Diabetic Retinopathy Detection (2015)
Krause, J., et al.: Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology 125(8), 1264–1272 (2018)
Lecouat, B., Chang, K., Kalpathy-Cramer, J., Krishnaswamy, P., et al.: Semi-supervised deep learning for abnormality classification in retinal images. CoRR abs/1812.07832 (2018)
Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, pp. 413–422 (2008)
Liu, L., Shen, C., van den Hengel, A.: The treasure beneath convolutional layers: cross-convolutional-layer pooling for image classification. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4749–4757, June 2015
Madani, A., Ong, J.R., Tibrewal, A., Mofrad, M.R.K.: Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease. npj Digit. Med. 1(1), 59 (2018)
Ruff, L., Vandermeulen, R., Müller, E., Kloft, M., et al.: Deep one-class classification. In: Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 4393–4402 (2018)
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. CoRR abs/1409.0575 (2014)
Schlegl, T., Seeböck, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 146–157. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59050-9_12
Schölkopf, B., Williamson, R., Smola, A., Shawe-Taylor, J., Platt, J.: Support vector method for novelty detection. In: Proceedings of the 12th International Conference on Neural Information Processing Systems, pp. 582–588 (1999)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, inception-resnet and the impact of residual connections on learning. CoRR abs/1602.07261 (2016)
Zenati, H., Romain, M., Foo, C., Lecouat, B., Chandrasekhar, V.: Adversarially learned anomaly detection. In: 2018 IEEE International Conference on Data Mining (ICDM), pp. 727–736 (2018)
Zhai, S., Cheng, Y., Lu, W., Zhang, Z.: Deep structured energy based models for anomaly detection. In: International Conference on Machine Learning, pp. 1100–1109 (2016)
Acknowledgement
This project was supported by funding from the Deep Learning 2.0 program at the Institute for Infocomm Research (I2R), A*STAR, Singapore; and partially supported by SERC Strategic Funding (A1718g0045) research grants from the US National Institutes of Health (NIH grants R01EY19474, P30EY010572, and K12EY027720) and the US National Science Foundation (NSF grants SCH-1622679 and SCH-1622542); unrestricted departmental funding from the Oregon Health Sciences University, and a Career Development Award from Research to Prevent Blindness (New York, NY). We acknowledge helpful discussions with James M. Brown and Ken Chang (MGH) on datasets and experiment planning.
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
Ouardini, K. et al. (2019). Towards Practical Unsupervised Anomaly Detection on Retinal Images. In: Wang, Q., et al. Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data. DART MIL3ID 2019 2019. Lecture Notes in Computer Science(), vol 11795. Springer, Cham. https://doi.org/10.1007/978-3-030-33391-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-33391-1_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33390-4
Online ISBN: 978-3-030-33391-1
eBook Packages: Computer ScienceComputer Science (R0)
