Feature learning based on visual similarity triplets in medical image analysis: A case study of emphysema in chest CT scans
This addresses the challenge of time-consuming and variable expert annotations in medical imaging, offering a method for non-expert involvement, though it is incremental as it applies an existing triplet approach to a new domain.
The paper tackled the problem of reducing annotation burden and variability in medical image analysis by using visual similarity triplets from non-experts to train CNNs for emphysema extent assessment in chest CT scans, achieving disease-relevant feature representations on 973 images.
Supervised feature learning using convolutional neural networks (CNNs) can provide concise and disease relevant representations of medical images. However, training CNNs requires annotated image data. Annotating medical images can be a time-consuming task and even expert annotations are subject to substantial inter- and intra-rater variability. Assessing visual similarity of images instead of indicating specific pathologies or estimating disease severity could allow non-experts to participate, help uncover new patterns, and possibly reduce rater variability. We consider the task of assessing emphysema extent in chest CT scans. We derive visual similarity triplets from visually assessed emphysema extent and learn a low dimensional embedding using CNNs. We evaluate the networks on 973 images, and show that the CNNs can learn disease relevant feature representations from derived similarity triplets. To our knowledge this is the first medical image application where similarity triplets has been used to learn a feature representation that can be used for embedding unseen test images