tetano
Editor, Senior Moderator
Diagnostics (Basel)
. 2020 Dec 30;11(1):E41.
doi: 10.3390/diagnostics11010041.
Development and Validation of an Automated Radiomic CT Signature for Detecting COVID-19
Julien Guiot[SUP] 1 [/SUP], Akshayaa Vaidyanathan[SUP] 2 3 [/SUP], Louis Deprez[SUP] 4 [/SUP], Fadila Zerka[SUP] 2 3 [/SUP], Denis Danthine[SUP] 4 [/SUP], Anne-No?lle Frix[SUP] 1 [/SUP], Marie Thys[SUP] 5 [/SUP], Monique Henket[SUP] 1 [/SUP], Gregory Canivet[SUP] 6 [/SUP], Stephane Mathieu[SUP] 6 [/SUP], Evanthia Eftaxia[SUP] 4 [/SUP], Philippe Lambin[SUP] 3 [/SUP], Nathan Tsoutzidis[SUP] 2 [/SUP], Benjamin Miraglio[SUP] 2 [/SUP], Sean Walsh[SUP] 2 [/SUP], Michel Moutschen[SUP] 7 [/SUP], Renaud Louis[SUP] 1 [/SUP], Paul Meunier[SUP] 4 [/SUP], Wim Vos[SUP] 2 [/SUP], Ralph T H Leijenaar[SUP] 2 [/SUP], Pierre Lovinfosse[SUP] 8 [/SUP]
Affiliations
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.
Keywords: COVID-19; artificial intelligence; computed tomography; machine learning; radiomics.
. 2020 Dec 30;11(1):E41.
doi: 10.3390/diagnostics11010041.
Development and Validation of an Automated Radiomic CT Signature for Detecting COVID-19
Julien Guiot[SUP] 1 [/SUP], Akshayaa Vaidyanathan[SUP] 2 3 [/SUP], Louis Deprez[SUP] 4 [/SUP], Fadila Zerka[SUP] 2 3 [/SUP], Denis Danthine[SUP] 4 [/SUP], Anne-No?lle Frix[SUP] 1 [/SUP], Marie Thys[SUP] 5 [/SUP], Monique Henket[SUP] 1 [/SUP], Gregory Canivet[SUP] 6 [/SUP], Stephane Mathieu[SUP] 6 [/SUP], Evanthia Eftaxia[SUP] 4 [/SUP], Philippe Lambin[SUP] 3 [/SUP], Nathan Tsoutzidis[SUP] 2 [/SUP], Benjamin Miraglio[SUP] 2 [/SUP], Sean Walsh[SUP] 2 [/SUP], Michel Moutschen[SUP] 7 [/SUP], Renaud Louis[SUP] 1 [/SUP], Paul Meunier[SUP] 4 [/SUP], Wim Vos[SUP] 2 [/SUP], Ralph T H Leijenaar[SUP] 2 [/SUP], Pierre Lovinfosse[SUP] 8 [/SUP]
Affiliations
- PMID: 33396587
- DOI: 10.3390/diagnostics11010041
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.
Keywords: COVID-19; artificial intelligence; computed tomography; machine learning; radiomics.