Learning what to look in chest X-rays with a recurrent visual attention model
This work addresses the challenge of automating radiological diagnosis for medical professionals, though it appears incremental as it builds on existing attention and reinforcement learning methods.
The authors tackled the problem of identifying abnormalities in chest X-rays by developing a recurrent visual attention model that learns to focus on informative regions, achieving results on over 100,000 X-rays for detecting enlarged hearts or medical devices.
X-rays are commonly performed imaging tests that use small amounts of radiation to produce pictures of the organs, tissues, and bones of the body. X-rays of the chest are used to detect abnormalities or diseases of the airways, blood vessels, bones, heart, and lungs. In this work we present a stochastic attention-based model that is capable of learning what regions within a chest X-ray scan should be visually explored in order to conclude that the scan contains a specific radiological abnormality. The proposed model is a recurrent neural network (RNN) that learns to sequentially sample the entire X-ray and focus only on informative areas that are likely to contain the relevant information. We report on experiments carried out with more than $100,000$ X-rays containing enlarged hearts or medical devices. The model has been trained using reinforcement learning methods to learn task-specific policies.