A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography
Abstract Since its first outbreak, Coronavirus Disease 2019 (COVID-19) has been rapidly spreading worldwide and caused a global pandemic. Rapid and early detection is essential to contain COVID-19. Here, we first developed a deep learning (DL) integrated radiomics model for end-to-end identification...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/2bba194f8c524411b02bf0aa9361d075 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:2bba194f8c524411b02bf0aa9361d075 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:2bba194f8c524411b02bf0aa9361d0752021-12-02T14:21:50ZA deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography10.1038/s41598-021-83237-62045-2322https://doaj.org/article/2bba194f8c524411b02bf0aa9361d0752021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83237-6https://doaj.org/toc/2045-2322Abstract Since its first outbreak, Coronavirus Disease 2019 (COVID-19) has been rapidly spreading worldwide and caused a global pandemic. Rapid and early detection is essential to contain COVID-19. Here, we first developed a deep learning (DL) integrated radiomics model for end-to-end identification of COVID-19 using CT scans and then validated its clinical feasibility. We retrospectively collected CT images of 386 patients (129 with COVID-19 and 257 with other community-acquired pneumonia) from three medical centers to train and externally validate the developed models. A pre-trained DL algorithm was utilized to automatically segment infected lesions (ROIs) on CT images which were used for feature extraction. Five feature selection methods and four machine learning algorithms were utilized to develop radiomics models. Trained with features selected by L1 regularized logistic regression, classifier multi-layer perceptron (MLP) demonstrated the optimal performance with AUC of 0.922 (95% CI 0.856–0.988) and 0.959 (95% CI 0.910–1.000), the same sensitivity of 0.879, and specificity of 0.900 and 0.887 on internal and external testing datasets, which was equivalent to the senior radiologist in a reader study. Additionally, diagnostic time of DL-MLP was more efficient than radiologists (38 s vs 5.15 min). With an adequate performance for identifying COVID-19, DL-MLP may help in screening of suspected cases.Xiaoguo ZhangDawei WangJiang ShaoSong TianWeixiong TanYan MaQingnan XuXiaoman MaDasheng LiJun ChaiDingjun WangWenwen LiuLingbo LinJiangfen WuChen XiaZhongfa ZhangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Xiaoguo Zhang Dawei Wang Jiang Shao Song Tian Weixiong Tan Yan Ma Qingnan Xu Xiaoman Ma Dasheng Li Jun Chai Dingjun Wang Wenwen Liu Lingbo Lin Jiangfen Wu Chen Xia Zhongfa Zhang A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography |
| description |
Abstract Since its first outbreak, Coronavirus Disease 2019 (COVID-19) has been rapidly spreading worldwide and caused a global pandemic. Rapid and early detection is essential to contain COVID-19. Here, we first developed a deep learning (DL) integrated radiomics model for end-to-end identification of COVID-19 using CT scans and then validated its clinical feasibility. We retrospectively collected CT images of 386 patients (129 with COVID-19 and 257 with other community-acquired pneumonia) from three medical centers to train and externally validate the developed models. A pre-trained DL algorithm was utilized to automatically segment infected lesions (ROIs) on CT images which were used for feature extraction. Five feature selection methods and four machine learning algorithms were utilized to develop radiomics models. Trained with features selected by L1 regularized logistic regression, classifier multi-layer perceptron (MLP) demonstrated the optimal performance with AUC of 0.922 (95% CI 0.856–0.988) and 0.959 (95% CI 0.910–1.000), the same sensitivity of 0.879, and specificity of 0.900 and 0.887 on internal and external testing datasets, which was equivalent to the senior radiologist in a reader study. Additionally, diagnostic time of DL-MLP was more efficient than radiologists (38 s vs 5.15 min). With an adequate performance for identifying COVID-19, DL-MLP may help in screening of suspected cases. |
| format |
article |
| author |
Xiaoguo Zhang Dawei Wang Jiang Shao Song Tian Weixiong Tan Yan Ma Qingnan Xu Xiaoman Ma Dasheng Li Jun Chai Dingjun Wang Wenwen Liu Lingbo Lin Jiangfen Wu Chen Xia Zhongfa Zhang |
| author_facet |
Xiaoguo Zhang Dawei Wang Jiang Shao Song Tian Weixiong Tan Yan Ma Qingnan Xu Xiaoman Ma Dasheng Li Jun Chai Dingjun Wang Wenwen Liu Lingbo Lin Jiangfen Wu Chen Xia Zhongfa Zhang |
| author_sort |
Xiaoguo Zhang |
| title |
A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography |
| title_short |
A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography |
| title_full |
A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography |
| title_fullStr |
A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography |
| title_full_unstemmed |
A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography |
| title_sort |
deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/2bba194f8c524411b02bf0aa9361d075 |
| work_keys_str_mv |
AT xiaoguozhang adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT daweiwang adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT jiangshao adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT songtian adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT weixiongtan adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT yanma adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT qingnanxu adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT xiaomanma adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT dashengli adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT junchai adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT dingjunwang adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT wenwenliu adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT lingbolin adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT jiangfenwu adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT chenxia adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT zhongfazhang adeeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT xiaoguozhang deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT daweiwang deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT jiangshao deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT songtian deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT weixiongtan deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT yanma deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT qingnanxu deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT xiaomanma deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT dashengli deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT junchai deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT dingjunwang deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT wenwenliu deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT lingbolin deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT jiangfenwu deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT chenxia deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography AT zhongfazhang deeplearningintegratedradiomicsmodelforidentificationofcoronavirusdisease2019usingcomputedtomography |
| _version_ |
1718391475784384512 |