Searching for Pneumothorax in Half a Million Chest X-Ray Images
Antonio Sze-To, Hamid Tizhoosh

TL;DR
This study demonstrates that content-based image retrieval using deep pretrained features can effectively classify pneumothorax in a large dataset of chest X-ray images, offering a promising alternative to traditional classifiers.
Contribution
It is the first to show that deep pretrained features can be used for CBIR to classify pneumothorax in over half a million chest X-ray images.
Findings
Image search achieved promising classification results.
Deep pretrained features outperform traditional classifiers.
First large-scale CBIR study for pneumothorax detection.
Abstract
Pneumothorax, a collapsed or dropped lung, is a fatal condition typically detected on a chest X-ray by an experienced radiologist. Due to shortage of such experts, automated detection systems based on deep neural networks have been developed. Nevertheless, applying such systems in practice remains a challenge. These systems, mostly compute a single probability as output, may not be enough for diagnosis. On the contrary, content-based medical image retrieval (CBIR) systems, such as image search, can assist clinicians for diagnostic purposes by enabling them to compare the case they are examining with previous (already diagnosed) cases. However, there is a lack of study on such attempt. In this study, we explored the use of image search to classify pneumothorax among chest X-ray images. All chest X-ray images were first tagged with deep pretrained features, which were obtained from…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
