COVID-19 on Chest Radiographs: A Multireader Evaluation of an Artificial Intelligence System.

Background Chest radiography may play an important role in triage for coronavirus disease 2019 (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. Materials and Methods An AI system (CAD4COVID-XRay) was trained on 24 678 chest radiographs, including 1540 used only for validation while training. The test set consisted of a set of continuously acquired chest radiographs (n = 454) obtained in patients suspected of having COVID-19 pneumonia between March 4 and April 6, 2020, at one center (223 patients with positive reverse transcription polymerase chain reaction [RT-PCR] results, 231 with negative RT-PCR results). Radiographs were independently analyzed by six readers and by the AI system. Diagnostic performance was analyzed with the receiver operating characteristic curve. Results For the test set, the mean age of patients was 67 years ± 14.4 (standard deviation) (56% male). With RT-PCR test results as the reference standard, the AI system correctly classified chest radiographs as COVID-19 pneumonia with an area under the receiver operating characteristic curve of 0.81. The system significantly outperformed each reader (P < .001 using the McNemar test) at their highest possible sensitivities. At their lowest sensitivities, only one reader significantly outperformed the AI system (P = .04). Conclusion The performance of an artificial intelligence system in the detection of coronavirus disease 2019 on chest radiographs was comparable with that of six independent readers. © RSNA, 2020.

Accuracy of computed tomographic angiography and magnetic resonance angiography for diagnosing renal artery stenosis.

BACKGROUND: Timely, accurate detection of renal artery stenosis is important because this disorder may be a potentially curable cause of hypertension and renal impairment. OBJECTIVE: To determine the validity of computed tomographic angiography (CTA) and magnetic resonance angiography (MRA) compared with digital subtraction angiography (DSA) for detection of renal artery stenosis. DESIGN: Prospective multicenter comparative study conducted from 1998 to 2001. Two panels of 3 observers judged CTA and MRA image data and were blinded to all other results. Digital subtraction angiography images were evaluated by consensus. SETTING: 3 large teaching hospitals and 3 university hospitals in the Netherlands. PATIENTS: 402 hypertensive patients with suspected renal artery stenosis were included. A group of 356 patients who underwent all 3 diagnostic tests was used for analysis. MEASUREMENTS: Reproducibility was assessed by calculating interobserver agreement. Diagnostic performance was evaluated in terms of sensitivity, specificity, and other diagnostic variables. Atherosclerotic stenoses of 50% or greater and fibromuscular dysplasia were considered clinically relevant. RESULTS: Twenty percent of patients who underwent all 3 tests had clinically relevant renal artery stenosis. Moderate interobserver agreement was found, with kappa values ranging from 0.59 to 0.64 for CTA and 0.40 to 0.51 for MRA. The combined sensitivity and specificity were 64% (95% CI, 55% to 73%) and 92% (CI, 90% to 95%) for CTA and 62% (CI, 54% to 71%) and 84% (CI, 81% to 87%) for MRA. LIMITATIONS: Eighteen percent of the patients were included nonconsecutively. Digital subtraction angiography may be an imperfect reference test. CONCLUSION: Computed tomographic angiography and MRA are not reproducible or sensitive enough to rule out renal artery stenosis in hypertensive patients. Therefore, DSA remains the diagnostic method of choice. *For a list of the other investigators and research coordinators who participated in RADISH, see the Appendix.