A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects
Abstract Chronic obstructive pulmonary disease (COPD) is a respiratory disorder involving abnormalities of lung parenchymal morphology with different severities. COPD is assessed by pulmonary-function tests and computed tomography-based approaches. We introduce a new classification method for COPD g...
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/624cbda4a11c46aa82869410744f1496 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:624cbda4a11c46aa82869410744f1496 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:624cbda4a11c46aa82869410744f14962021-12-02T15:12:55ZA 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects10.1038/s41598-020-79336-52045-2322https://doaj.org/article/624cbda4a11c46aa82869410744f14962021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-79336-5https://doaj.org/toc/2045-2322Abstract Chronic obstructive pulmonary disease (COPD) is a respiratory disorder involving abnormalities of lung parenchymal morphology with different severities. COPD is assessed by pulmonary-function tests and computed tomography-based approaches. We introduce a new classification method for COPD grouping based on deep learning and a parametric-response mapping (PRM) method. We extracted parenchymal functional variables of functional small airway disease percentage (fSAD%) and emphysema percentage (Emph%) with an image registration technique, being provided as input parameters of 3D convolutional neural network (CNN). The integrated 3D-CNN and PRM (3D-cPRM) achieved a classification accuracy of 89.3% and a sensitivity of 88.3% in five-fold cross-validation. The prediction accuracy of the proposed 3D-cPRM exceeded those of the 2D model and traditional 3D CNNs with the same neural network, and was comparable to that of 2D pretrained PRM models. We then applied a gradient-weighted class activation mapping (Grad-CAM) that highlights the key features in the CNN learning process. Most of the class-discriminative regions appeared in the upper and middle lobes of the lung, consistent with the regions of elevated fSAD% and Emph% in COPD subjects. The 3D-cPRM successfully represented the parenchymal abnormalities in COPD and matched the CT-based diagnosis of COPD.Thao Thi HoTaewoo KimWoo Jin KimChang Hyun LeeKum Ju ChaeSo Hyeon BakSung Ok KwonGong Yong JinEun-Kee ParkSanghun ChoiNature 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 Thao Thi Ho Taewoo Kim Woo Jin Kim Chang Hyun Lee Kum Ju Chae So Hyeon Bak Sung Ok Kwon Gong Yong Jin Eun-Kee Park Sanghun Choi A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects |
| description |
Abstract Chronic obstructive pulmonary disease (COPD) is a respiratory disorder involving abnormalities of lung parenchymal morphology with different severities. COPD is assessed by pulmonary-function tests and computed tomography-based approaches. We introduce a new classification method for COPD grouping based on deep learning and a parametric-response mapping (PRM) method. We extracted parenchymal functional variables of functional small airway disease percentage (fSAD%) and emphysema percentage (Emph%) with an image registration technique, being provided as input parameters of 3D convolutional neural network (CNN). The integrated 3D-CNN and PRM (3D-cPRM) achieved a classification accuracy of 89.3% and a sensitivity of 88.3% in five-fold cross-validation. The prediction accuracy of the proposed 3D-cPRM exceeded those of the 2D model and traditional 3D CNNs with the same neural network, and was comparable to that of 2D pretrained PRM models. We then applied a gradient-weighted class activation mapping (Grad-CAM) that highlights the key features in the CNN learning process. Most of the class-discriminative regions appeared in the upper and middle lobes of the lung, consistent with the regions of elevated fSAD% and Emph% in COPD subjects. The 3D-cPRM successfully represented the parenchymal abnormalities in COPD and matched the CT-based diagnosis of COPD. |
| format |
article |
| author |
Thao Thi Ho Taewoo Kim Woo Jin Kim Chang Hyun Lee Kum Ju Chae So Hyeon Bak Sung Ok Kwon Gong Yong Jin Eun-Kee Park Sanghun Choi |
| author_facet |
Thao Thi Ho Taewoo Kim Woo Jin Kim Chang Hyun Lee Kum Ju Chae So Hyeon Bak Sung Ok Kwon Gong Yong Jin Eun-Kee Park Sanghun Choi |
| author_sort |
Thao Thi Ho |
| title |
A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects |
| title_short |
A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects |
| title_full |
A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects |
| title_fullStr |
A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects |
| title_full_unstemmed |
A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects |
| title_sort |
3d-cnn model with ct-based parametric response mapping for classifying copd subjects |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/624cbda4a11c46aa82869410744f1496 |
| work_keys_str_mv |
AT thaothiho a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT taewookim a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT woojinkim a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT changhyunlee a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT kumjuchae a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT sohyeonbak a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT sungokkwon a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT gongyongjin a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT eunkeepark a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT sanghunchoi a3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT thaothiho 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT taewookim 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT woojinkim 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT changhyunlee 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT kumjuchae 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT sohyeonbak 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT sungokkwon 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT gongyongjin 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT eunkeepark 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects AT sanghunchoi 3dcnnmodelwithctbasedparametricresponsemappingforclassifyingcopdsubjects |
| _version_ |
1718387632502734848 |