The use of artificial intelligence (AI) has been rapidly progressing in medicine, particularly in radiology. AI has also been the source of great innovation and a prominent topic of discussion within radiology societies and ground-breaking research in recent years. Despite the risks and quality assurance issues involved in AI, it offers tremendous opportunities for changing how radiological services are delivered. Moreover, it is conceivable that AI could become a reliable, hard-working friend to the radiologist rather than a foe, in addition to being a useful training tool for radiologist trainees.
11 December 2002 in Journal of Clinical Ultrasound
Clinically suspicious novel coronavirus (COVID-19) lung pneumonia can be observed typically on computed tomography (CT) chest scans even in patients with a negative real-time polymerase chain reaction (RT-PCR) test. The purpose of the study was to describe the CT imaging findings of five patients with negative RT-PCR results on initial and repeated testing but a high radiological suspicion of COVID-19 pneumonia. Out of 19 clinically and/or radiologically diagnosed COVID-19 patients from our institution, five patients were selected for our study who had typical findings of COVID-19 on CT scan despite two negative RT-PCR results. Two district general hospital radiologists reviewed the chest CT images without prior knowledge of the RT-PCR test results. Scans were analyzed for the density of opacification and the distribution of disease. Out of 19 patients, five (26%) had initial negative RT-PCR test findings but positive CT chest features consistent with COVID-19. All patients had typical CT imaging findings of COVID-19. These included one patient with purely ground-glass opacities (GGO) and four patients with mixed GGO and consolidation. The typical distribution of parenchymal involvement was bilateral, posterior, and peripheral. Of the five patients with negative RT-PCR and positive CT findings, the range of CT severity score was 5 to 14. The median score, seen in three patients, was a score of 5, which corresponded to mild disease. One patient had a score of 8, corresponding to moderate disease, and one patient had severe disease with a score of 14. Lung parenchymal changes related to COVID-19 can be seen on chest CT clearly despite repeated RT-PCR negative results.