In the journal Radiology RIHS researcher Keelin Murphy described the evaluation of a newly developed artificial intelligence (AI) system, CAD4COVID-XRay, for the detection of COVID-19 characteristics on chest X-ray (CXR).
The system is developed by Thirona and is available cost-free to any institution upon request. The system was trained on 24,678 CXR images and tested on a set of 454 images from an independent center (223 patients tested positive for COVID-19, the remaining 231 tested negative). The CXR images were also examined and scored by 6 radiologists independently. Analysis was performed by calculation of the receiver operating characteristic curve (ROC). In the task of identifying COVID-19 positive patients the AI system performed at a level comparable to all six radiologists and had an area under the ROC of 0.81. The system may be useful as part of a triage process for symptomatic subjects, particularly in low-resource settings where radiological expertise is not available.
Background Chest radiography (CXR) may play an important role in triage for COVID-19, particularly in low-resource settings. Purpose To evaluate the performance of an artificial intelligence (AI) system for detection of COVID-19 pneumonia on chest radiographs. Methods An AI system (CAD4COVID-Xray) was trained on 24,678 CXR images including 1,540 used only for validation while training. The test set consisted of a set of continuously acquired CXR images (n=454) obtained in patients suspected for COVID-19 pneumonia between March 4th and April 6th 2020 in a single center (223 RT-PCR positive subjects, 231 RT-PCR negative subjects). The radiographs were independently analyzed by six readers and by the AI system. Diagnostic performance was performed by receiver operating characteristic curve analysis. Results For the test set, the mean age of the patients was 67.3 (+/-14.4) years (56% male). Using RT-PCR test results as the reference standard, the AI system correctly classified CXR images as COVID-19 pneumonia with an AUC of 0.81. The system significantly outperforms each reader (p < 0.001 using McNemar test) at their highest possible sensitivities. At their lowest sensitivities, only one reader can significantly outperform the AI system (p=0.04). Conclusions An AI system for detection of COVID-19 on chest radiographs was comparable to six independent readers.
COVID-19 on the Chest Radiograph: A Multi-Reader Evaluation of an AI System.
Murphy K, Smits H, Knoops AJG, Korst MBJM, Samson T, Scholten ET, Schalekamp S, Schaefer-Prokop CM, Philipsen RHHM, Meijers A, Melendez J, van Ginneken B, Rutten M.
Related news items
First clinical trial with genetically modified malaria vaccine completed22 May 2020
In an innovative study, Radboudumc and LUMC jointly tested a candidate vaccine based on a genetically weakened malaria parasite. The results of this clinical trial, published in Science Translational Medicine, show that the vaccine is safe and elicits a defense response against a malaria infection.read more
New step in the development of a vaccine against malaria22 May 2020
A new vaccine based on rodent malaria parasites achieved a 95% reduction in infection of the liver in humans. An international consortium publishes the results in Science Translational Medicine.read more
Intra-articular corticosteroid injections increase the risk of requiring knee arthroplasty14 May 2020
In The Bone & Joint Journal, RIHS researcher Stan Wijn et al. showed that corticosteroid injections in the knee joint are associated with an increased risk of knee arthroplasty in patients with, or at risk of developing, symptomatic osteoarthritis of the knee.read more
Comenius Senior Fellowship for Jos Kole12 May 2020
Assistant professor in Healthcare Ethics, Jos Kole received a Comenius Senior Fellowship, a prestigious educational scholarship for his plan ‘Physicians with character’. Aim of this scholarship is to innovate the Master of Medicine program.read more