Development and Validation of an Automated Radiomic CT Signature for Detecting COVID-19.
Julien GuiotAkshayaa VaidyanathanLouis DeprezFadila ZerkaDenis DanthineAnne-Noëlle FrixMarie ThysMonique HenketGregory CanivetStephane MathieuEvanthia EftaxiaPhilippe LambinNathan TsoutzidisBenjamin MiraglioSean WalshMichel MoutschenRenaud LouisPaul MeunierWim VosRalph T H LeijenaarPierre LovinfossePublished in: Diagnostics (Basel, Switzerland) (2020)
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.
Keyphrases
- coronavirus disease
- healthcare
- sars cov
- end stage renal disease
- ejection fraction
- newly diagnosed
- prognostic factors
- randomized controlled trial
- primary care
- peritoneal dialysis
- magnetic resonance imaging
- machine learning
- high resolution
- patient reported outcomes
- mental health
- deep learning
- artificial intelligence
- high throughput
- mass spectrometry
- decision making
- quantum dots
- anti inflammatory
- lymph node metastasis
- real time pcr
- image quality