Semi-supervised learning with generative adversarial networks for chest X-ray classification with ability of data domain adaptation
Ali Madani, Mehdi Moradi, Alexandros Karargyris et al. · IEEE International Symposium on Biomedical Imaging (ISBI) · 2018
Deep learning algorithms require large amounts of labeled data which is difficult to attain for medical imaging. Even if a particular dataset is accessible, a learned classifier struggles to maintain the same level of performance on a different medical imaging dataset from a new or never-seen data source domain. Utilizing generative adversarial networks in a semi-supervised learning architecture, we address both problems of labeled data scarcity and data domain overfitting. For cardiac abnormality classification in chest X-rays, we demonstrate that an order of magnitude less data is required with semi-supervised learning generative adversarial networks than with conventional supervised learning convolutional neural networks. In addition, we demonstrate its robustness across different datasets for similar classification tasks.
Cited by 166 works. doi:10.1109/isbi.2018.8363749
Authors
References
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Generative Adversarial Nets
- Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery
- Semi-Supervised Learning with Deep Generative Models
- Preparing a collection of radiology examinations for distribution and retrieval
- Screening by Chest Radiograph and Lung Cancer Mortality
- Generative Adversarial Networks for Noise Reduction in Low-Dose CT
- Unsupervised Domain Adaptation in Brain Lesion Segmentation with Adversarial Networks
- Semi-Supervised Learning with Generative Adversarial Networks
- Deep MR to CT Synthesis Using Unpaired Data