Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT
Abstract The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neur...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-01-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-020-00369-1 |
| _version_ | 1797427972019322880 |
|---|---|
| author | Edward H. Lee Jimmy Zheng Errol Colak Maryam Mohammadzadeh Golnaz Houshmand Nicholas Bevins Felipe Kitamura Emre Altinmakas Eduardo Pontes Reis Jae-Kwang Kim Chad Klochko Michelle Han Sadegh Moradian Ali Mohammadzadeh Hashem Sharifian Hassan Hashemi Kavous Firouznia Hossien Ghanaati Masoumeh Gity Hakan Doğan Hojjat Salehinejad Henrique Alves Jayne Seekins Nitamar Abdala Çetin Atasoy Hamidreza Pouraliakbar Majid Maleki S. Simon Wong Kristen W. Yeom |
| author_facet | Edward H. Lee Jimmy Zheng Errol Colak Maryam Mohammadzadeh Golnaz Houshmand Nicholas Bevins Felipe Kitamura Emre Altinmakas Eduardo Pontes Reis Jae-Kwang Kim Chad Klochko Michelle Han Sadegh Moradian Ali Mohammadzadeh Hashem Sharifian Hassan Hashemi Kavous Firouznia Hossien Ghanaati Masoumeh Gity Hakan Doğan Hojjat Salehinejad Henrique Alves Jayne Seekins Nitamar Abdala Çetin Atasoy Hamidreza Pouraliakbar Majid Maleki S. Simon Wong Kristen W. Yeom |
| author_sort | Edward H. Lee |
| collection | DOAJ |
| description | Abstract The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neural network (CNN) that uses the entire chest CT volume to automatically predict COVID-19 (COVID+) from non-COVID-19 (COVID−) pneumonia and normal controls. We discuss training strategies and differences in performance across 13 international institutions and 8 countries. The inclusion of non-China sites in training significantly improved classification performance with area under the curve (AUCs) and accuracies above 0.8 on most test sites. Furthermore, using available follow-up scans, we investigate methods to track patient disease course and predict prognosis. |
| first_indexed | 2024-03-09T08:52:25Z |
| format | Article |
| id | doaj.art-b8cdd6ddc1174a5a86416c48a44db3cc |
| institution | Directory Open Access Journal |
| issn | 2398-6352 |
| language | English |
| last_indexed | 2024-03-09T08:52:25Z |
| publishDate | 2021-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj.art-b8cdd6ddc1174a5a86416c48a44db3cc2023-12-02T14:04:35ZengNature Portfolionpj Digital Medicine2398-63522021-01-014111110.1038/s41746-020-00369-1Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CTEdward H. Lee0Jimmy Zheng1Errol Colak2Maryam Mohammadzadeh3Golnaz Houshmand4Nicholas Bevins5Felipe Kitamura6Emre Altinmakas7Eduardo Pontes Reis8Jae-Kwang Kim9Chad Klochko10Michelle Han11Sadegh Moradian12Ali Mohammadzadeh13Hashem Sharifian14Hassan Hashemi15Kavous Firouznia16Hossien Ghanaati17Masoumeh Gity18Hakan Doğan19Hojjat Salehinejad20Henrique Alves21Jayne Seekins22Nitamar Abdala23Çetin Atasoy24Hamidreza Pouraliakbar25Majid Maleki26S. Simon Wong27Kristen W. Yeom28Department of Radiology, School of Medicine, Stanford UniversityDepartment of Radiology, School of Medicine, Stanford UniversityUnity Health Toronto, University of TorontoDivision of Radiology, Amir Alam Hospital, Tehran University of Medical SciencesRajaie Cardiovascular Medical and Research Center, Iran University of Medical SciencesHenry Ford Health SystemUniversidade Federal de São Paulo (UNIFESP)Department of Radiology, Koç University School of MedicineHospital Israelita Albert EinsteinDepartment of Radiology, School of Medicine, Kyungpook National UniversityRajaie Cardiovascular Medical and Research Center, Iran University of Medical SciencesDepartment of Radiology, School of Medicine, Stanford UniversitySchool of Medicine, Tehran University of Medical SciencesRajaie Cardiovascular Medical and Research Center, Iran University of Medical SciencesDivision of Radiology, Amir Alam Hospital, Tehran University of Medical SciencesAdvanced Diagnostic and Interventional Radiology Research Center(ADIR), Medical Imaging Center, Imam Khomeini Hospital Complex, Tehran University of Medical SciencesAdvanced Diagnostic and Interventional Radiology Research Center(ADIR), Medical Imaging Center, Imam Khomeini Hospital Complex, Tehran University of Medical SciencesAdvanced Diagnostic and Interventional Radiology Research Center(ADIR), Medical Imaging Center, Imam Khomeini Hospital Complex, Tehran University of Medical SciencesAdvanced Diagnostic and Interventional Radiology Research Center(ADIR), Medical Imaging Center, Imam Khomeini Hospital Complex, Tehran University of Medical SciencesDepartment of Radiology, Koç University School of MedicineUnity Health Toronto, University of TorontoUniversidade Federal de São Paulo (UNIFESP)Department of Radiology, School of Medicine, Stanford UniversityUniversidade Federal de São Paulo (UNIFESP)Department of Radiology, Koç University School of MedicineRajaie Cardiovascular Medical and Research Center, Iran University of Medical SciencesRajaie Cardiovascular Medical and Research Center, Iran University of Medical SciencesDepartment of Electrical Engineering, Stanford UniversityDepartment of Radiology, School of Medicine, Stanford UniversityAbstract The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neural network (CNN) that uses the entire chest CT volume to automatically predict COVID-19 (COVID+) from non-COVID-19 (COVID−) pneumonia and normal controls. We discuss training strategies and differences in performance across 13 international institutions and 8 countries. The inclusion of non-China sites in training significantly improved classification performance with area under the curve (AUCs) and accuracies above 0.8 on most test sites. Furthermore, using available follow-up scans, we investigate methods to track patient disease course and predict prognosis.https://doi.org/10.1038/s41746-020-00369-1 |
| spellingShingle | Edward H. Lee Jimmy Zheng Errol Colak Maryam Mohammadzadeh Golnaz Houshmand Nicholas Bevins Felipe Kitamura Emre Altinmakas Eduardo Pontes Reis Jae-Kwang Kim Chad Klochko Michelle Han Sadegh Moradian Ali Mohammadzadeh Hashem Sharifian Hassan Hashemi Kavous Firouznia Hossien Ghanaati Masoumeh Gity Hakan Doğan Hojjat Salehinejad Henrique Alves Jayne Seekins Nitamar Abdala Çetin Atasoy Hamidreza Pouraliakbar Majid Maleki S. Simon Wong Kristen W. Yeom Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT npj Digital Medicine |
| title | Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT |
| title_full | Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT |
| title_fullStr | Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT |
| title_full_unstemmed | Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT |
| title_short | Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT |
| title_sort | deep covid detect an international experience on covid 19 lung detection and prognosis using chest ct |
| url | https://doi.org/10.1038/s41746-020-00369-1 |
| work_keys_str_mv | AT edwardhlee deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT jimmyzheng deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT errolcolak deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT maryammohammadzadeh deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT golnazhoushmand deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT nicholasbevins deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT felipekitamura deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT emrealtinmakas deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT eduardopontesreis deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT jaekwangkim deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT chadklochko deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT michellehan deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT sadeghmoradian deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT alimohammadzadeh deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT hashemsharifian deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT hassanhashemi deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT kavousfirouznia deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT hossienghanaati deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT masoumehgity deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT hakandogan deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT hojjatsalehinejad deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT henriquealves deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT jayneseekins deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT nitamarabdala deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT cetinatasoy deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT hamidrezapouraliakbar deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT majidmaleki deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT ssimonwong deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct AT kristenwyeom deepcoviddetectaninternationalexperienceoncovid19lungdetectionandprognosisusingchestct |