Unsupervised learning for concept detection in medical images: a comparative analysis
This work addresses the problem of limited annotations in medical imaging for researchers and practitioners by evaluating unsupervised methods, but it is incremental as it compares existing techniques without introducing new ones.
The paper compared six unsupervised feature learning methods, including traditional and deep learning approaches, for concept detection in medical images using the ImageCLEF 2017 dataset, finding that modern deep learning methods yield more powerful representations than older computer vision techniques, though generative adversarial networks struggle with highly varied data.
As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often scarce and short on annotations. In this paper, we present an assessment of unsupervised feature learning approaches for images in the biomedical literature, which can be applied to automatic biomedical concept detection. Six unsupervised representation learning methods were built, including traditional bags of visual words, autoencoders, and generative adversarial networks. Each model was trained, and their respective feature space evaluated using images from the ImageCLEF 2017 concept detection task. We conclude that it is possible to obtain more powerful representations with modern deep learning approaches, in contrast with previously popular computer vision methods. Although generative adversarial networks can provide good results, they are harder to succeed in highly varied data sets. The possibility of semi-supervised learning, as well as their use in medical information retrieval problems, are the next steps to be strongly considered.