Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography Images
Catheter ablation therapy, which is a treatment for atrial fibrillation (AF), has a higher recurrence rate as AF duration increases. Compared to paroxysmal AF (PAF), sustained AF is known to cause progressive anatomic remodeling of the left atrium, resulting in enlargement and shape changes. In this...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/13/12/309 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846105232354836480 |
|---|---|
| author | Hina Kotani Atsushi Teramoto Tomoyuki Ohno Yoshihiro Sobue Eiichi Watanabe Hiroshi Fujita |
| author_facet | Hina Kotani Atsushi Teramoto Tomoyuki Ohno Yoshihiro Sobue Eiichi Watanabe Hiroshi Fujita |
| author_sort | Hina Kotani |
| collection | DOAJ |
| description | Catheter ablation therapy, which is a treatment for atrial fibrillation (AF), has a higher recurrence rate as AF duration increases. Compared to paroxysmal AF (PAF), sustained AF is known to cause progressive anatomic remodeling of the left atrium, resulting in enlargement and shape changes. In this study, we used contrast-enhanced computed tomography (CT) to classify atrial fibrillation (AF) into paroxysmal atrial fibrillation (PAF) and long-term persistent atrial fibrillation (LSAF), which have particularly different recurrence rates after catheter ablation. Contrast-enhanced CT images of 30 patients with PAF and 30 patients with LSAF were input into six pretrained convolutional neural networks (CNNs) for the binary classification of PAF and LSAF. In this study, we propose a method that can recognize information regarding the body axis direction of the left atrium by inputting five slices near the left atrium. The classification was visualized by obtaining a saliency map based on score-class activation mapping (CAM). Furthermore, we surveyed cardiologists regarding the classification of AF types, and the results of the CNN classification were compared with the results of physicians’ clinical judgment. The proposed method achieved the highest correct classification rate (81.7%). In particular, models with shallow layers, such as VGGNet and ResNet, are able to capture the overall characteristics of the image and therefore are likely to be suitable for focusing on the left atrium. In many cases, patients with an enlarged left atrium tended to have long-lasting AF, confirming the validity of the proposed method. The results of the saliency map and survey of physicians’ basis for judgment showed that many patients tended to focus on the shape of the left atrium in both classifications, suggesting that this method can classify atrial fibrillation more accurately than physicians, similar to the judgment criteria of physicians. |
| format | Article |
| id | doaj-art-c5441b515cb24e709e809db12ed7dca5 |
| institution | Kabale University |
| issn | 2073-431X |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj-art-c5441b515cb24e709e809db12ed7dca52024-12-27T14:18:59ZengMDPI AGComputers2073-431X2024-11-01131230910.3390/computers13120309Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography ImagesHina Kotani0Atsushi Teramoto1Tomoyuki Ohno2Yoshihiro Sobue3Eiichi Watanabe4Hiroshi Fujita5Graduate School of Health Sciences, Fujita Health University, Toyoake 470-1192, JapanFaculty of Information Engineering, Meijo University, Nagoya 468-8502, JapanDepartment of Radiation, Fujita Health University Bantane Hospital, Nagoya 454-8509, JapanDepartment of Internal Medicine, Fujita Health University Bantane Hospital, Nagoya 454-8509, JapanDepartment of Internal Medicine, Fujita Health University Bantane Hospital, Nagoya 454-8509, JapanFaculty of Engineering, Gifu University, Gifu 501-1193, JapanCatheter ablation therapy, which is a treatment for atrial fibrillation (AF), has a higher recurrence rate as AF duration increases. Compared to paroxysmal AF (PAF), sustained AF is known to cause progressive anatomic remodeling of the left atrium, resulting in enlargement and shape changes. In this study, we used contrast-enhanced computed tomography (CT) to classify atrial fibrillation (AF) into paroxysmal atrial fibrillation (PAF) and long-term persistent atrial fibrillation (LSAF), which have particularly different recurrence rates after catheter ablation. Contrast-enhanced CT images of 30 patients with PAF and 30 patients with LSAF were input into six pretrained convolutional neural networks (CNNs) for the binary classification of PAF and LSAF. In this study, we propose a method that can recognize information regarding the body axis direction of the left atrium by inputting five slices near the left atrium. The classification was visualized by obtaining a saliency map based on score-class activation mapping (CAM). Furthermore, we surveyed cardiologists regarding the classification of AF types, and the results of the CNN classification were compared with the results of physicians’ clinical judgment. The proposed method achieved the highest correct classification rate (81.7%). In particular, models with shallow layers, such as VGGNet and ResNet, are able to capture the overall characteristics of the image and therefore are likely to be suitable for focusing on the left atrium. In many cases, patients with an enlarged left atrium tended to have long-lasting AF, confirming the validity of the proposed method. The results of the saliency map and survey of physicians’ basis for judgment showed that many patients tended to focus on the shape of the left atrium in both classifications, suggesting that this method can classify atrial fibrillation more accurately than physicians, similar to the judgment criteria of physicians.https://www.mdpi.com/2073-431X/13/12/309atrial fibrillationcatheter ablationclassificationconvolutional neural networkcontrast-enhanced computed tomographydeep learning |
| spellingShingle | Hina Kotani Atsushi Teramoto Tomoyuki Ohno Yoshihiro Sobue Eiichi Watanabe Hiroshi Fujita Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography Images Computers atrial fibrillation catheter ablation classification convolutional neural network contrast-enhanced computed tomography deep learning |
| title | Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography Images |
| title_full | Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography Images |
| title_fullStr | Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography Images |
| title_full_unstemmed | Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography Images |
| title_short | Atrial Fibrillation Type Classification by a Convolutional Neural Network Using Contrast-Enhanced Computed Tomography Images |
| title_sort | atrial fibrillation type classification by a convolutional neural network using contrast enhanced computed tomography images |
| topic | atrial fibrillation catheter ablation classification convolutional neural network contrast-enhanced computed tomography deep learning |
| url | https://www.mdpi.com/2073-431X/13/12/309 |
| work_keys_str_mv | AT hinakotani atrialfibrillationtypeclassificationbyaconvolutionalneuralnetworkusingcontrastenhancedcomputedtomographyimages AT atsushiteramoto atrialfibrillationtypeclassificationbyaconvolutionalneuralnetworkusingcontrastenhancedcomputedtomographyimages AT tomoyukiohno atrialfibrillationtypeclassificationbyaconvolutionalneuralnetworkusingcontrastenhancedcomputedtomographyimages AT yoshihirosobue atrialfibrillationtypeclassificationbyaconvolutionalneuralnetworkusingcontrastenhancedcomputedtomographyimages AT eiichiwatanabe atrialfibrillationtypeclassificationbyaconvolutionalneuralnetworkusingcontrastenhancedcomputedtomographyimages AT hiroshifujita atrialfibrillationtypeclassificationbyaconvolutionalneuralnetworkusingcontrastenhancedcomputedtomographyimages |