Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
This addresses the challenge of accurate pneumothorax diagnosis in medical imaging, though it is incremental as it builds on existing CNN methods with a novel ensemble approach.
The paper tackled the problem of detecting pneumothorax in chest radiography, which can be difficult to identify, by proposing an ensemble of convolutional neural networks using multi-sized images, achieving a state-of-the-art AUC of 0.911 on a dataset of over 100,000 images.
Pneumothorax is a relatively common disease, but in some cases, it may be difficult to find with chest radiography. In this paper, we propose a novel method of detecting pneumothorax in chest radiography. We propose an ensemble model of identical convolutional neural networks (CNN) with three different sizes of radiography images. Conventional methods may not properly characterize lost features while resizing large size images into 256 x 256 or 224 x 224 sizes. Our model is evaluated with ChestX-ray dataset which contains over 100,000 chest radiography images. As a result of the experiment, the proposed model showed AUC 0.911, which is the state of the art result in pneumothorax detection. Our method is expected to be effective when applying CNN to large size medical images.