Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio
This work addresses the time-consuming and subjective manual measurement of CTR for clinicians, offering a computer-aided diagnostic tool, though it is incremental as it builds on existing adversarial network methods.
The paper tackled the problem of automating cardiothoracic ratio (CTR) estimation from chest X-rays without needing large annotated datasets, by proposing an unsupervised domain adaptation framework that achieved accurate chest organ segmentation and demonstrated clinical practicability with promising semi-supervised performance on the JSRT dataset.
The cardiothoracic ratio (CTR), a clinical metric of heart size in chest X-rays (CXRs), is a key indicator of cardiomegaly. Manual measurement of CTR is time-consuming and can be affected by human subjectivity, making it desirable to design computer-aided systems that assist clinicians in the diagnosis process. Automatic CTR estimation through chest organ segmentation, however, requires large amounts of pixel-level annotated data, which is often unavailable. To alleviate this problem, we propose an unsupervised domain adaptation framework based on adversarial networks. The framework learns domain invariant feature representations from openly available data sources to produce accurate chest organ segmentation for unlabeled datasets. Specifically, we propose a model that enforces our intuition that prediction masks should be domain independent. Hence, we introduce a discriminator that distinguishes segmentation predictions from ground truth masks. We evaluate our system's prediction based on the assessment of radiologists and demonstrate the clinical practicability for the diagnosis of cardiomegaly. We finally illustrate on the JSRT dataset that the semi-supervised performance of our model is also very promising.