Unsupervised Domain Adaptation for Automatic Estimation of Cardiothoracic Ratio

TL;DR

This paper presents an unsupervised domain adaptation method using adversarial networks to accurately estimate the cardiothoracic ratio from chest X-rays without requiring pixel-level annotations, aiding clinical diagnosis.

Contribution

It introduces a novel adversarial domain adaptation framework that enforces domain-invariant features for automatic segmentation of chest organs in unlabeled data.

Findings

Clinically validated accuracy of CTR estimation

Effective domain adaptation demonstrated on JSRT dataset

Promising semi-supervised performance

Abstract

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.