The new coronavirus unleashed a worldwide pandemic in early 2020, and a fatality rate several times that of the flu. As the number of infections soared, and capabilities for testing lagged behind, chest X-ray (CXR) imaging became more relevant in the early diagnosis and treatment planning for patients with suspected or confirmed COVID-19 infection. In a few weeks, proposed new methods for lung screening using deep learning rapidly appeared, while quality assurance discussions lagged behind. This paper proposes a set of protocols to validate deep learning algorithms, including our ROI Hide-and-Seek protocol, which emphasizes or hides key regions of interest from CXR data. Our protocol allows assessing the classification performance for anomaly detection and its correlation to radiological signatures, an important issue overlooked in several deep learning approaches proposed so far. By running a set of systematic tests over CXR representations using public image datasets, we demonstrate the weaknesses of current techniques and offer perspectives on the advantages and limitations of automated radiography analysis when using heterogeneous data sources.
Sadre, Robbie, et al. "Validating deep learning inference during chest X-ray classification for COVID-19 screening." Scientific Reports, vol. 11, no. 1, Aug. 2021. https://doi.org/10.1038/s41598-021-95561-y
@article{osti_1812409,
author = {Sadre, Robbie and Sundaram, Baskaran and Majumdar, Sharmila and Ushizima, Daniela},
title = {Validating deep learning inference during chest X-ray classification for COVID-19 screening},
annote = {Abstract The new coronavirus unleashed a worldwide pandemic in early 2020, and a fatality rate several times that of the flu. As the number of infections soared, and capabilities for testing lagged behind, chest X-ray (CXR) imaging became more relevant in the early diagnosis and treatment planning for patients with suspected or confirmed COVID-19 infection. In a few weeks, proposed new methods for lung screening using deep learning rapidly appeared, while quality assurance discussions lagged behind. This paper proposes a set of protocols to validate deep learning algorithms, including our ROI Hide-and-Seek protocol, which emphasizes or hides key regions of interest from CXR data. Our protocol allows assessing the classification performance for anomaly detection and its correlation to radiological signatures, an important issue overlooked in several deep learning approaches proposed so far. By running a set of systematic tests over CXR representations using public image datasets, we demonstrate the weaknesses of current techniques and offer perspectives on the advantages and limitations of automated radiography analysis when using heterogeneous data sources.},
doi = {10.1038/s41598-021-95561-y},
url = {https://www.osti.gov/biblio/1812409},
journal = {Scientific Reports},
issn = {ISSN 2045-2322},
number = {1},
volume = {11},
place = {United Kingdom},
publisher = {Nature Publishing Group},
year = {2021},
month = {08}}
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part IIIhttps://doi.org/10.1007/978-3-319-24574-4_28