Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia
We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 9...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/11/3/530 |
| _version_ | 1797541194192912384 |
|---|---|
| author | Christian Salvatore Matteo Interlenghi Caterina B. Monti Davide Ippolito Davide Capra Andrea Cozzi Simone Schiaffino Annalisa Polidori Davide Gandola Marco Alì Isabella Castiglioni Cristina Messa Francesco Sardanelli |
| author_facet | Christian Salvatore Matteo Interlenghi Caterina B. Monti Davide Ippolito Davide Capra Andrea Cozzi Simone Schiaffino Annalisa Polidori Davide Gandola Marco Alì Isabella Castiglioni Cristina Messa Francesco Sardanelli |
| author_sort | Christian Salvatore |
| collection | DOAJ |
| description | We assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia. |
| first_indexed | 2024-03-10T13:11:47Z |
| format | Article |
| id | doaj.art-94cb65d7a72742eeb33dada141570107 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T13:11:47Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-94cb65d7a72742eeb33dada1415701072023-11-21T10:42:36ZengMDPI AGDiagnostics2075-44182021-03-0111353010.3390/diagnostics11030530Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 PneumoniaChristian Salvatore0Matteo Interlenghi1Caterina B. Monti2Davide Ippolito3Davide Capra4Andrea Cozzi5Simone Schiaffino6Annalisa Polidori7Davide Gandola8Marco Alì9Isabella Castiglioni10Cristina Messa11Francesco Sardanelli12Department of Science, Technology, and Society, Scuola Universitaria IUSS, Istituto Universitario di Studi Superiori, Piazza della Vittoria 15, 27100 Pavia, ItalyDeepTrace Technologies S.R.L., via Conservatorio 17, 20122 Milano, ItalyDepartment of Biomedical Sciences for Health, Università degli Studi di Milano, Via Mangiagalli 31, 20133 Milano, ItalyDepartment of Radiology, ASST Monza—Ospedale San Gerardo, Via Pergolesi 33, 20900 Monza, ItalyDepartment of Biomedical Sciences for Health, Università degli Studi di Milano, Via Mangiagalli 31, 20133 Milano, ItalyDepartment of Biomedical Sciences for Health, Università degli Studi di Milano, Via Mangiagalli 31, 20133 Milano, ItalyUnit of Radiology, IRCCS Policlinico San Donato, Via Morandi 30, 20097 San Donato Milanese, ItalyDeepTrace Technologies S.R.L., via Conservatorio 17, 20122 Milano, ItalyDepartment of Radiology, ASST Monza—Ospedale San Gerardo, Via Pergolesi 33, 20900 Monza, ItalyDepartment of Diagnostic Imaging and Stereotactic Radiosurgery, C.D.I. Centro Diagnostico Italiano S.p.A., Via Saint Bon 20, 20147 Milano, ItalyDepartment of Physics, Università degli Studi di Milano-Bicocca, Piazza della Scienza 3, 20126 Milano, ItalySchool of Medicine and Surgery, Università degli Studi di Milano-Bicocca, Piazza dell’Ateneo Nuovo 1, 20126 Milano, ItalyDepartment of Biomedical Sciences for Health, Università degli Studi di Milano, Via Mangiagalli 31, 20133 Milano, ItalyWe assessed the role of artificial intelligence applied to chest X-rays (CXRs) in supporting the diagnosis of COVID-19. We trained and cross-validated a model with an ensemble of 10 convolutional neural networks with CXRs of 98 COVID-19 patients, 88 community-acquired pneumonia (CAP) patients, and 98 subjects without either COVID-19 or CAP, collected in two Italian hospitals. The system was tested on two independent cohorts, namely, 148 patients (COVID-19, CAP, or negative) collected by one of the two hospitals (independent testing I) and 820 COVID-19 patients collected by a multicenter study (independent testing II). On the training and cross-validation dataset, sensitivity, specificity, and area under the curve (AUC) were 0.91, 0.87, and 0.93 for COVID-19 versus negative subjects, 0.85, 0.82, and 0.94 for COVID-19 versus CAP. On the independent testing I, sensitivity, specificity, and AUC were 0.98, 0.88, and 0.98 for COVID-19 versus negative subjects, 0.97, 0.96, and 0.98 for COVID-19 versus CAP. On the independent testing II, the system correctly diagnosed 652 COVID-19 patients versus negative subjects (0.80 sensitivity) and correctly differentiated 674 COVID-19 versus CAP patients (0.82 sensitivity). This system appears promising for the diagnosis and differential diagnosis of COVID-19, showing its potential as a second opinion tool in conditions of the variable prevalence of different types of infectious pneumonia.https://www.mdpi.com/2075-4418/11/3/530artificial intelligenceneural networksSARS-CoV-2COVID-19community-acquired pneumoniachest X-ray |
| spellingShingle | Christian Salvatore Matteo Interlenghi Caterina B. Monti Davide Ippolito Davide Capra Andrea Cozzi Simone Schiaffino Annalisa Polidori Davide Gandola Marco Alì Isabella Castiglioni Cristina Messa Francesco Sardanelli Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia Diagnostics artificial intelligence neural networks SARS-CoV-2 COVID-19 community-acquired pneumonia chest X-ray |
| title | Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia |
| title_full | Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia |
| title_fullStr | Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia |
| title_full_unstemmed | Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia |
| title_short | Artificial Intelligence Applied to Chest X-ray for Differential Diagnosis of COVID-19 Pneumonia |
| title_sort | artificial intelligence applied to chest x ray for differential diagnosis of covid 19 pneumonia |
| topic | artificial intelligence neural networks SARS-CoV-2 COVID-19 community-acquired pneumonia chest X-ray |
| url | https://www.mdpi.com/2075-4418/11/3/530 |
| work_keys_str_mv | AT christiansalvatore artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT matteointerlenghi artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT caterinabmonti artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT davideippolito artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT davidecapra artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT andreacozzi artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT simoneschiaffino artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT annalisapolidori artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT davidegandola artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT marcoali artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT isabellacastiglioni artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT cristinamessa artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia AT francescosardanelli artificialintelligenceappliedtochestxrayfordifferentialdiagnosisofcovid19pneumonia |