Semi-Supervised Deep Learning for Abnormality Classification in Retinal Images

Supervised deep learning algorithms have enabled significant performance gains in medical image classification tasks. But these methods rely on large labeled datasets that require resource-intensive expert annotation. Semi-supervised generative adversarial network (GAN) approaches offer a means to learn from limited labeled data alongside larger unlabeled datasets, but have not been applied to discern fine-scale, sparse or localized features that define medical abnormalities. To overcome these limitations, we propose a patch-based semi-supervised learning approach and evaluate performance on classification of diabetic retinopathy from funduscopic images. Our semi-supervised approach achieves high AUC with just 10-20 labeled training images, and outperforms the supervised baselines by upto 15% when less than 30% of the training dataset is labeled. Further, our method implicitly enables interpretation of the SSL predictions. As this approach enables good accuracy, resolution and interpretability with lower annotation burden, it sets the pathway for scalable applications of deep learning in clinical imaging.

[1]  Rajarsi R. Gupta,et al.  Spatial Organization and Molecular Correlation of Tumor-Infiltrating Lymphocytes Using Deep Learning on Pathology Images. , 2018, Cell reports.

[2]  Qiang Chen,et al.  Network In Network , 2013, ICLR.

[3]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[4]  Jonathan Krause,et al.  Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy , 2017, Ophthalmology.

[5]  Aristotelis Tsirigos,et al.  Classification and Mutation Prediction from Non-Small Cell Lung Cancer Histopathology Images using Deep Learning , 2017, bioRxiv.

[6]  Fabrice Mériaudeau,et al.  Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening Research , 2018, Data.

[7]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[8]  Ali Madani,et al.  Deep echocardiography: data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease , 2018, npj Digital Medicine.

[9]  Ronald M. Summers,et al.  Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique , 2016 .

[10]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[14]  Seth A. Smith,et al.  Spinal cord MRI at 7T , 2017, NeuroImage.

[15]  Tanveer F. Syeda-Mahmood,et al.  Semi-supervised learning with generative adversarial networks for chest X-ray classification with ability of data domain adaptation , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[16]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[17]  Gwénolé Quellec,et al.  Deep image mining for diabetic retinopathy screening , 2016, Medical Image Anal..

[18]  Tapani Raiko,et al.  Semi-supervised Learning with Ladder Networks , 2015, NIPS.

[19]  Paul Babyn,et al.  Generative Adversarial Network in Medical Imaging: A Review , 2018, Medical Image Anal..

[20]  Jost Tobias Springenberg,et al.  Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks , 2015, ICLR.