RESUMO
PURPOSE: To investigate the diagnostic performance of an Artificial Intelligence (AI) system for detection of COVID-19 in chest radiographs (CXR), and compare results to those of physicians working alone, or with AI support. MATERIALS AND METHODS: An AI system was fine-tuned to discriminate confirmed COVID-19 pneumonia, from other viral and bacterial pneumonia and non-pneumonia patients and used to review 302 CXR images from adult patients retrospectively sourced from nine different databases. Fifty-four physicians blind to diagnosis, were invited to interpret images under identical conditions in a test set, and randomly assigned either to receive or not receive support from the AI system. Comparisons were then made between diagnostic performance of physicians working with and without AI support. AI system performance was evaluated using the area under the receiver operating characteristic (AUROC), and sensitivity and specificity of physician performance compared to that of the AI system. RESULTS: Discrimination by the AI system of COVID-19 pneumonia showed an AUROC curve of 0.96 in the validation and 0.83 in the external test set, respectively. The AI system outperformed physicians in the AUROC overall (70% increase in sensitivity and 1% increase in specificity, pâ¯<â¯0.0001). When working with AI support, physicians increased their diagnostic sensitivity from 47% to 61% (pâ¯<â¯0.001), although specificity decreased from 79% to 75% (pâ¯=â¯0.007). CONCLUSIONS: Our results suggest interpreting chest radiographs (CXR) supported by AI, increases physician diagnostic sensitivity for COVID-19 detection. This approach involving a human-machine partnership may help expedite triaging efforts and improve resource allocation in the current crisis.
RESUMO
BACKGROUND AND PURPOSE: Multinodular and Vacuolating Neuronal Tumor of the cerebrum (MVNT) is a benign -seizure associated- lesion affecting mostly adults. This new entity has been included in the 2016 World Health Organization classification of tumors of the central nervous system. Its pathologic hallmark consist of a subcortical cluster of nodular lesions located on the subcortical white matter. We aim to report a series of cases of presumed MVNT observed in our institution and review the literature. MATERIALS AND METHODS: In this retrospective study, a search was performed on our hospital information system. Sixteen cases were included. Demographic, clinical and radiological features were detailed in a table. All patients had an MRI acquired either on a 1.5 or a 3 Tesla scanner. Sequences performed included T1, T2, GRE/SWI, T2 FLAIR and DWI. Gadolinium enhanced T1-WI wer available in 11 patients and follow-up MRI were available in 7 patients. RESULTS: Patient ages ranged from 16 to 77 years (mean 42 years). Seizure and non-focal headache were by far the most common neurological complaints for which MRI was requested. All lesions consisted of clusters of multiple, discrete, round or ovoid, intra-axial, FLAIR and T2-WI hyperintense nodules. Follow-up MRI scans showed no changes between studies. CONCLUSIONS: MVNT is a benign, stable lesion that exhibits a typical radiological pattern that most of the times sufficed to arrive to a diagnosis, without the need of pathological confirmation. We confirm that our demographic, clinical and radiological findings are in accordance with those published in international literature.