Abstract
AbstractThe 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.
Funder
DOE | LDRD | Lawrence Berkeley National Laboratory
Publisher
Springer Science and Business Media LLC
Reference39 articles.
1. Bleicher, A. & Conrad, K. We thought it was just a respiratory virus: We were wrong. UCSF Mag. 9. https://magazine.ucsf.edu/we-thought-it-was-just-respiratory-virus (2020).
2. Asseo, K., Fierro, F., Slavutsky, Y., Frasnelli, J. & Niv, M. Y. Tracking covid-19 using taste and smell loss google searches is not a reliable strategy. Sci. Rep. 10, 20527. https://doi.org/10.1038/s41598-020-77316-3 (2020).
3. Ronco, C. & Reis, T. Kidney involvement in COVID-19 and rationale for extracorporeal therapies. Nat. Rev. Nephrol. 16, 308–310. https://doi.org/10.1038/s41581-020-0284-7 (2020).
4. Hope, M. D. et al. A role for CT in COVID-19? What data really tell us so far. Lancet 395, 1189–1190. https://doi.org/10.1016/S0140-6736(20)30728-5 (2020).
5. ACR. American College of Radiology (ACR) recommendations for the use of chest radiography and computed tomography (CT) for suspected COVID-19 infection. https://www.acr.org/Advocacy-and-Economics/ACR-Position-Statements/Recommendations-for-Chest-Radiography-and-CT-for-Suspected-COVID19-Infection (2020).
Cited by
33 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献