Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net
Abstract Background Intravascular ultrasound (IVUS) is the golden standard in accessing the coronary lesions, stenosis, and atherosclerosis plaques. In this paper, a fully automatic approach by an 8-layer U-Net is developed to segment the coronary artery lumen and the area bounded by external elasti...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-02-01
|
| Series: | BioMedical Engineering OnLine |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12938-021-00852-0 |
| _version_ | 1818569720859721728 |
|---|---|
| author | Liang Dong Wenbing Jiang Wei Lu Jun Jiang Ya Zhao Xiangfen Song Xiaochang Leng Hang Zhao Jian’an Wang Changling Li Jianping Xiang |
| author_facet | Liang Dong Wenbing Jiang Wei Lu Jun Jiang Ya Zhao Xiangfen Song Xiaochang Leng Hang Zhao Jian’an Wang Changling Li Jianping Xiang |
| author_sort | Liang Dong |
| collection | DOAJ |
| description | Abstract Background Intravascular ultrasound (IVUS) is the golden standard in accessing the coronary lesions, stenosis, and atherosclerosis plaques. In this paper, a fully automatic approach by an 8-layer U-Net is developed to segment the coronary artery lumen and the area bounded by external elastic membrane (EEM), i.e., cross-sectional area (EEM-CSA). The database comprises single-vendor and single-frequency IVUS data. Particularly, the proposed data augmentation of MeshGrid combined with flip and rotation operations is implemented, improving the model performance without pre- or post-processing of the raw IVUS images. Results The mean intersection of union (MIoU) of 0.937 and 0.804 for the lumen and EEM-CSA, respectively, were achieved, which exceeded the manual labeling accuracy of the clinician. Conclusion The accuracy shown by the proposed method is sufficient for subsequent reconstruction of 3D-IVUS images, which is essential for doctors’ diagnosis in the tissue characterization of coronary artery walls and plaque compositions, qualitatively and quantitatively. |
| first_indexed | 2024-12-14T06:51:28Z |
| format | Article |
| id | doaj.art-578185a1eaca4f0c916084052b08d853 |
| institution | Directory Open Access Journal |
| issn | 1475-925X |
| language | English |
| last_indexed | 2024-12-14T06:51:28Z |
| publishDate | 2021-02-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj.art-578185a1eaca4f0c916084052b08d8532022-12-21T23:12:52ZengBMCBioMedical Engineering OnLine1475-925X2021-02-012011910.1186/s12938-021-00852-0Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-NetLiang Dong0Wenbing Jiang1Wei Lu2Jun Jiang3Ya Zhao4Xiangfen Song5Xiaochang Leng6Hang Zhao7Jian’an Wang8Changling Li9Jianping Xiang10The Department of Cardiology, The Second Affiliated Hospital of Zhejiang University School of MedicineThe Department of Cardiology, Wenzhou People HospitalArteryFlow Technology Co., Ltd.The Department of Cardiology, The Second Affiliated Hospital of Zhejiang University School of MedicineArteryFlow Technology Co., Ltd.ArteryFlow Technology Co., Ltd.ArteryFlow Technology Co., Ltd.ArteryFlow Technology Co., Ltd.The Department of Cardiology, The Second Affiliated Hospital of Zhejiang University School of MedicineThe Department of Cardiology, The Second Affiliated Hospital of Zhejiang University School of MedicineArteryFlow Technology Co., Ltd.Abstract Background Intravascular ultrasound (IVUS) is the golden standard in accessing the coronary lesions, stenosis, and atherosclerosis plaques. In this paper, a fully automatic approach by an 8-layer U-Net is developed to segment the coronary artery lumen and the area bounded by external elastic membrane (EEM), i.e., cross-sectional area (EEM-CSA). The database comprises single-vendor and single-frequency IVUS data. Particularly, the proposed data augmentation of MeshGrid combined with flip and rotation operations is implemented, improving the model performance without pre- or post-processing of the raw IVUS images. Results The mean intersection of union (MIoU) of 0.937 and 0.804 for the lumen and EEM-CSA, respectively, were achieved, which exceeded the manual labeling accuracy of the clinician. Conclusion The accuracy shown by the proposed method is sufficient for subsequent reconstruction of 3D-IVUS images, which is essential for doctors’ diagnosis in the tissue characterization of coronary artery walls and plaque compositions, qualitatively and quantitatively.https://doi.org/10.1186/s12938-021-00852-0IVUSCoronarySegmentationLumenEEMMeshGrid |
| spellingShingle | Liang Dong Wenbing Jiang Wei Lu Jun Jiang Ya Zhao Xiangfen Song Xiaochang Leng Hang Zhao Jian’an Wang Changling Li Jianping Xiang Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net BioMedical Engineering OnLine IVUS Coronary Segmentation Lumen EEM MeshGrid |
| title | Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net |
| title_full | Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net |
| title_fullStr | Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net |
| title_full_unstemmed | Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net |
| title_short | Automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8-layer U-Net |
| title_sort | automatic segmentation of coronary lumen and external elastic membrane in intravascular ultrasound images using 8 layer u net |
| topic | IVUS Coronary Segmentation Lumen EEM MeshGrid |
| url | https://doi.org/10.1186/s12938-021-00852-0 |
| work_keys_str_mv | AT liangdong automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT wenbingjiang automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT weilu automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT junjiang automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT yazhao automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT xiangfensong automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT xiaochangleng automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT hangzhao automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT jiananwang automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT changlingli automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet AT jianpingxiang automaticsegmentationofcoronarylumenandexternalelasticmembraneinintravascularultrasoundimagesusing8layerunet |