A robust network architecture to detect normal chest X-ray radiographs
| Autor: | Kiran Kumar Reddy Polaka, Venkateswar Wunnava, Joy T. Wu, DC Reddy, Anup Pillai, Yaniv Gur, Mehdi Moradi, Tanveer Syeda-Mahmood, Chiranjeevi J, Arjun Sharma, Minnekanti Sunil Chowdary, Hassan Ahmad, Ken C. L. Wong |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Ground truth
Network architecture Generalization business.industry Computer science Radiography Image and Video Processing (eess.IV) Pattern recognition Electrical Engineering and Systems Science - Image and Video Processing Overfitting Class (biology) 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine FOS: Electrical engineering electronic engineering information engineering Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | ISBI |
| DOI: | 10.48550/arxiv.2004.06147 |
| Popis: | We propose a novel deep neural network architecture for normalcy detection in chest X-ray images. This architecture treats the problem as fine-grained binary classification in which the normal cases are well-defined as a class while leaving all other cases in the broad class of abnormal. It employs several components that allow generalization and prevent overfitting across demographics. The model is trained and validated on a large public dataset of frontal chest X-ray images. It is then tested independently on images from a clinical institution of differing patient demographics using a three radiologist consensus for ground truth labeling. The model provides an area under ROC curve of 0.96 when tested on 1271 images. We can automatically remove nearly a third of disease-free chest X-ray screening images from the workflow, without introducing any false negatives (100% sensitivity to disease) thus raising the potential of expediting radiology workflows in hospitals in future. Comment: This paper was accepted by IEEE ISBI 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|