A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning
The detection of coronary artery stenosis is one of the most important indicators for the diagnosis of coronary artery disease. However, stenosis in branch vessels is often difficult to detect using computer-aided systems and even radiologists because of several factors, such as imaging angle and co...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4893/17/3/119 |
| _version_ | 1797242358205513728 |
|---|---|
| author | Yanjun Li Takaaki Yoshimura Yuto Horima Hiroyuki Sugimori |
| author_facet | Yanjun Li Takaaki Yoshimura Yuto Horima Hiroyuki Sugimori |
| author_sort | Yanjun Li |
| collection | DOAJ |
| description | The detection of coronary artery stenosis is one of the most important indicators for the diagnosis of coronary artery disease. However, stenosis in branch vessels is often difficult to detect using computer-aided systems and even radiologists because of several factors, such as imaging angle and contrast agent inhomogeneity. Traditional coronary artery stenosis localization algorithms often only detect aortic stenosis and ignore branch vessels that may also cause major health threats. Therefore, improving the localization of branch vessel stenosis in coronary angiographic images is a potential development property. In this study, we propose a preprocessing approach that combines vessel enhancement and image fusion as a prerequisite for deep learning. The sensitivity of the neural network to stenosis features is improved by enhancing the blurry features in coronary angiographic images. By validating five neural networks, such as YOLOv4 and R-FCN-Inceptionresnetv2, our proposed method can improve the performance of deep learning network applications on the images from six common imaging angles. The results showed that the proposed method is suitable as a preprocessing method for coronary angiographic image processing based on deep learning and can be used to amend the recognition ability of the deep model for fine vessel stenosis. |
| first_indexed | 2024-04-24T18:37:57Z |
| format | Article |
| id | doaj.art-a7e5b28ab5124d139d37f237196a2cc9 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-04-24T18:37:57Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-a7e5b28ab5124d139d37f237196a2cc92024-03-27T13:17:26ZengMDPI AGAlgorithms1999-48932024-03-0117311910.3390/a17030119A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep LearningYanjun Li0Takaaki Yoshimura1Yuto Horima2Hiroyuki Sugimori3Graduate School of Health Sciences, Hokkaido University, Sapporo 060-0812, JapanDepartment of Health Sciences and Technology, Faculty of Health Sciences, Hokkaido University, Sapporo 060-0812, JapanDepartment of Central Radiology, JR Sapporo Hospital, Sapporo 060-0033, JapanGlobal Center for Biomedical Science and Engineering, Faculty of Medicine, Hokkaido University, Sapporo 060-8648, JapanThe detection of coronary artery stenosis is one of the most important indicators for the diagnosis of coronary artery disease. However, stenosis in branch vessels is often difficult to detect using computer-aided systems and even radiologists because of several factors, such as imaging angle and contrast agent inhomogeneity. Traditional coronary artery stenosis localization algorithms often only detect aortic stenosis and ignore branch vessels that may also cause major health threats. Therefore, improving the localization of branch vessel stenosis in coronary angiographic images is a potential development property. In this study, we propose a preprocessing approach that combines vessel enhancement and image fusion as a prerequisite for deep learning. The sensitivity of the neural network to stenosis features is improved by enhancing the blurry features in coronary angiographic images. By validating five neural networks, such as YOLOv4 and R-FCN-Inceptionresnetv2, our proposed method can improve the performance of deep learning network applications on the images from six common imaging angles. The results showed that the proposed method is suitable as a preprocessing method for coronary angiographic image processing based on deep learning and can be used to amend the recognition ability of the deep model for fine vessel stenosis.https://www.mdpi.com/1999-4893/17/3/119coronary angiographydeep learningimage enhancementimage fusion |
| spellingShingle | Yanjun Li Takaaki Yoshimura Yuto Horima Hiroyuki Sugimori A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning Algorithms coronary angiography deep learning image enhancement image fusion |
| title | A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning |
| title_full | A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning |
| title_fullStr | A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning |
| title_full_unstemmed | A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning |
| title_short | A Preprocessing Method for Coronary Artery Stenosis Detection Based on Deep Learning |
| title_sort | preprocessing method for coronary artery stenosis detection based on deep learning |
| topic | coronary angiography deep learning image enhancement image fusion |
| url | https://www.mdpi.com/1999-4893/17/3/119 |
| work_keys_str_mv | AT yanjunli apreprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning AT takaakiyoshimura apreprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning AT yutohorima apreprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning AT hiroyukisugimori apreprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning AT yanjunli preprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning AT takaakiyoshimura preprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning AT yutohorima preprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning AT hiroyukisugimori preprocessingmethodforcoronaryarterystenosisdetectionbasedondeeplearning |