Abstract
AbstractArtificial intelligence (AI) researchers and radiologists have recently reported AI systems that accurately detect COVID-19 in chest radiographs. However, the robustness of these systems remains unclear. Using state-of-the-art techniques in explainable AI, we demonstrate that recent deep learning systems to detect COVID-19 from chest radiographs rely on confounding factors rather than medical pathology, creating an alarming situation in which the systems appear accurate, but fail when tested in new hospitals.
Publisher
Cold Spring Harbor Laboratory
Reference44 articles.
1. Mossa-Basha, M. et al. Policies and guidelines for COVID-19 preparedness: Experiences from the University of Washington. Radiology, 201326 (2020).
2. Kundu, S. , Elhalawani, H. , Gichoya, J. W. & Kahn Jr, C. E. How might AI and chest imaging help unravel COVID-19’s mysteries? Radiology. Artificial Intelligence 2 (2020).
3. Ghoshal, B. & Tucker, A. Estimating uncertainty and interpretability in deep learning for coronavirus (COVID-19) detection. arXiv:2003.10769 (2020).
4. Wang, L. & Wong, A. COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images. arXiv:2003.09871 (2020).
5. Hemdan, E. E.-D. , Shouman, M. A. & Karar, M. E. COVIDX-Net: A framework of deep learning classifiers to diagnose COVID-19 in X-ray images. arXiv:2003.11055 (2020).
Cited by
69 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