Aims and objectives
radiographically measured by a cardiothoracic ratio of greater than 50%,
is a common symptom associated with congestive heart failure .
Given the large size of the heart relative to the view covered by the thoracic X-ray,
its detection should be a relatively easy task for both humans and neural networks.
Cardiomegaly detection thus serves as a useful baseline for the comparison neural network architectures. In 2017,
Wang et al.,
in collaboration with the NIH Clinical Center,...
Methods and materials
A retrospective case-control review on McGill PACS isolated 1346 chest radiographs consisting of 673 cases positive for cardiomegaly and 673 controls.
Cases and controls were manually selected,
balanced and filtered to keep studies with posteroanterior (PA) views only.
Four different convolutional neural network architectures,
The two newest architectures were further ensembled in order to measure the impact of model ensembling on...
The best performing classifier was DenseNet121,
which obtained an AUC of 0.941 without ensembling or transfer learning.
The three other convolutional architectures tested,
and AlexNet respectively had an AUC of 0.936,
0.927 and 0.918 (Figure 2).
Transfer learning boosted these AUC figures to 0.963,
0.932 and 0.929 respectively (Table 1). A majority voting ensemble of 3 DenseNet121 and 2 ResNet50 networks with weights pre-initialized on the NIH dataset obtained an AUC...
Dense (DenseNet121) and residual (ResNet50) deep convolutional neural networks can accurately detect cardiomegaly with an AUC of 0.97 on chest radiographs.
These advanced architectures generalize well on unseen data and significantly improve upon the performance of older CNNs.
Cardiothoracic ratio from postero-anterior chest radiographs: A simple,
reproducible and independent marker of disease severity and outcome in adults with congenital heart disease. Int J Cardiol. 2013;166(2):453-457.
doi:10.1016/J.IJCARD.2011.10.125 Wang X,
ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases.