Development and Validation of an Automated Radiomic CT Signature for Detecting COVID-19

Abstract

The coronavirus disease 2019 (COVID-19) outbreak has reached pandemic status. Drastic measures of social distancing are enforced in society and healthcare systems are being pushed to and beyond their limits. To help in the fight against this threat on human health, a fully automated AI framework was developed to extract radiomics features from volumetric chest computed tomography (CT) exams. The detection model was developed on a dataset of 1381 patients (181 COVID-19 patients plus 1200 non COVID control patients). A second, independent dataset of 197 RT-PCR confirmed COVID-19 patients and 500 control patients was used to assess the performance of the model. Diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC). The model had an AUC of 0.882 (95% CI: 0.851–0.913) in the independent test dataset (641 patients). The optimal decision threshold, considering the cost of false negatives twice as high as the cost of false positives, resulted in an accuracy of 85.18%, a sensitivity of 69.52%, a specificity of 91.63%, a negative predictive value (NPV) of 94.46% and a positive predictive value (PPV) of 59.44%. Benchmarked against RT-PCR confirmed cases of COVID-19, our AI framework can accurately differentiate COVID-19 from routine clinical conditions in a fully automated fashion. Thus, providing rapid accurate diagnosis in patients suspected of COVID-19 infection, facilitating the timely implementation of isolation procedures and early intervention.

Long-term clinical follow-up of patients suffering from moderate-to-severe COVID-19 infection: a monocentric prospective observational cohort study

“…We prospectively recruited patients admitted at the University hospital of Liège for moderate to severe confirmed COVID-19, who were discharged between March 2 and October 1, 2020. Inclusion criteria were: ( 1 ) age ≥16, ( 2 ) confirmed SARS-CoV-2 infection and ( 3 ) hospitalization at the University hospital of Liège, Belgium. Recruitment was performed on voluntary basis.…”

“…In December 2019, a novel coronavirus (severe acute respiratory syndrome coronavirus 2; SARS-CoV-2) was detected in Wuhan, China, and identified as the etiological agent of coronavirus disease 2019 (COVID-19). Clinical manifestations range from the absence of symptoms to acute respiratory distress syndrome (ARDS) and sometimes multi-organ failure ( 1 , 2 , 3 , 4 ). For most patients, the infection is mild with low-grade fever and cough, but 15% of patients experience respiratory impairment, combined with diffuse alveolar damage (DAD), pulmonary (hyper)inflammatory infiltrates and microvascular thrombosis associated to elevated levels of inflammatory markers, and require hospital care ( 3 , 5 ).…”

What is Artificial Intelligence Surgery?

“…Researchers from Switzerland were even able to use radiomics, a form of computer vision, to develop methods to instantaneously diagnose COVID-19 patients using CT imaging alone, this finding which was published in December of 2020 less than 12 months after the start of the pandemic, elucidates the fundamental role that AI can hold in healthcare and public health in the future [16] . Radiomics uses imaging and algorithms to enhance diagnostic accuracy via interpretation of vast amounts of imaging data.…”

An Interpretation Architecture for Deep Learning Models with the Application of COVID-19 Diagnosis

“…Based on the detection results, they further achieved the diagnosis result for the COVID-19 patients, and the highest diagnostic accuracy was 90.6%. Guiot et al [31] proposed an automated detection framework, which extracted radiomics features from volumetric chest CT exams and then conducted detection of COVID-19 based on these features. Alom et al [32] proposed a COVID_MTNet to identify COVID-19 patients with multi-task deep learning methods, in which both X-ray and CT scan images were considered.…”