Skip to main content
main-content
Top

Hint

Swipe to navigate through the chapters of this book

2019 | OriginalPaper | Chapter

Towards Practical Unsupervised Anomaly Detection on Retinal Images

Authors : Khalil Ouardini, Huijuan Yang, Balagopal Unnikrishnan, Manon Romain, Camille Garcin, Houssam Zenati, J. Peter Campbell, Michael F. Chiang, Jayashree Kalpathy-Cramer, Vijay Chandrasekhar, Pavitra Krishnaswamy, Chuan-Sheng Foo

Published in: Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data

Publisher: Springer International Publishing

share
SHARE

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.
Literature
1.
go back to reference Andrews, J.T.A., Tanay, T., Morton, E.J., Griffin, L.D.: Transfer representation-learning for anomaly detection. In: ICML Anomaly Detection Workshop (2016) Andrews, J.T.A., Tanay, T., Morton, E.J., Griffin, L.D.: Transfer representation-learning for anomaly detection. In: ICML Anomaly Detection Workshop (2016)
2.
go back to reference 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) CrossRef 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) CrossRef
3.
go back to reference Bo, Z., et al.: Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018) Bo, Z., et al.: Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. In: International Conference on Learning Representations (2018)
4.
go back to reference 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) CrossRef 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) CrossRef
5.
go back to reference 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) CrossRef 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) CrossRef
6.
go back to reference Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: Advances in Neural Information Processing Systems 31, pp. 9758–9769 (2018) Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: Advances in Neural Information Processing Systems 31, pp. 9758–9769 (2018)
7.
go back to reference 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) CrossRef 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) CrossRef
8.
go back to reference Kaggle: Diabetic Retinopathy Detection (2015) Kaggle: Diabetic Retinopathy Detection (2015)
9.
go back to reference 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) CrossRef 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) CrossRef
10.
go back to reference 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) 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)
11.
go back to reference 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, 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)
12.
go back to reference 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 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
13.
go back to reference 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) CrossRef 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) CrossRef
14.
go back to reference 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) 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)
15.
go back to reference Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. CoRR abs/1409.0575 (2014) Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. CoRR abs/1409.0575 (2014)
17.
go back to reference 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) 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)
18.
go back to reference 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) 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)
19.
go back to reference 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) 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)
20.
go back to reference 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) 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)
Metadata
Title
Towards Practical Unsupervised Anomaly Detection on Retinal Images
Authors
Khalil Ouardini
Huijuan Yang
Balagopal Unnikrishnan
Manon Romain
Camille Garcin
Houssam Zenati
J. Peter Campbell
Michael F. Chiang
Jayashree Kalpathy-Cramer
Vijay Chandrasekhar
Pavitra Krishnaswamy
Chuan-Sheng Foo
Copyright Year
2019
DOI
https://doi.org/10.1007/978-3-030-33391-1_26

Premium Partner