False-Negative Results of Real-Time Reverse-Transcriptase Polymerase Chain Reaction for Severe Acute Respiratory Syndrome Coronavirus 2: Role of Deep-Learning-Based CT Diagnosis and Insights from Two Cases

Abstract

The epidemic of 2019 novel coronavirus, later named as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is still gradually spreading worldwide. The nucleic acid test or genetic sequencing serves as the gold standard method for confirmation of infection, yet several recent studies have reported false-negative results of real-time reverse-transcriptase polymerase chain reaction (rRT-PCR). Here, we report two representative false-negative cases and discuss the supplementary role of clinical data with rRT-PCR, including laboratory examination results and computed tomography features. Coinfection with SARS-COV-2 and other viruses has been discussed as well.

Keywords: COVID-19; Computed tomography; False-negative results; Laboratory examination; SARS-COV-2; rRT-PCR.

Fig. 1. Chest CT scans for 10-month-old patient in Case 1.

A. Thin-slice CT scan that shows glimpse of lesions (breathing-induced motion artifacts are heavy for patient). CT shows diffuse ill-defined ground-glass opacities in both upper lung lobes. B. Representative of DL-based segmentation of lesions in left lung that shows overview of automatically calculated abnormality proportions. Artificial intelligence alarms suspected pneumonia based on relatively large proportion of abnormalities in lung. Detailed abnormality proportions in whole lungs, right upper lobe, right middle lobe, right lower lobe, left upper lobe, and left lower lobe were calculated and listed. CT = computed tomography, DL = deep learning

Fig. 2. Chest CT scans for patient in Case 2.

A. Thin-slice CT scan that shows glimpse of lesions. CT shows diffuse ground-glass opacities in dependent area of right lower lobe. B. Representative of DL-based segmentation of lesions in lower lobe of right lung that shows overview of automatically calculated ratios. Artificial intelligence alarms suspected pneumonia based on relatively large proportion of abnormalities in lung. Detailed abnormality proportions in whole lungs, right upper lobe, right middle lobe, right lower lobe, left upper lobe, and left lower lobe were calculated and listed.