A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection
Abstract Myocardial infarction (MI) remains a significant contributor to global mortality and morbidity, necessitating accurate and timely diagnosis. Current diagnostic methods encounter challenges in capturing intricate patterns, urging the need for advanced automated approaches to enhance MI detec...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-54846-8 |
| _version_ | 1797274869089435648 |
|---|---|
| author | Junaid Abdul Wahid Xu Mingliang Muhammad Ayoub Shabir Husssain Lifeng Li Lei Shi |
| author_facet | Junaid Abdul Wahid Xu Mingliang Muhammad Ayoub Shabir Husssain Lifeng Li Lei Shi |
| author_sort | Junaid Abdul Wahid |
| collection | DOAJ |
| description | Abstract Myocardial infarction (MI) remains a significant contributor to global mortality and morbidity, necessitating accurate and timely diagnosis. Current diagnostic methods encounter challenges in capturing intricate patterns, urging the need for advanced automated approaches to enhance MI detection. In this study, we strive to advance MI detection by proposing a hybrid approach that combines the strengths of ResNet and Vision Transformer (ViT) models, leveraging global and local features for improved accuracy. We introduce a slim-model ViT design with multibranch networks and channel attention mechanisms to enhance patch embedding extraction, addressing ViT’s limitations. By training data through both ResNet and modified ViT models, we incorporate a dual-pathway feature extraction strategy. The fusion of global and local features addresses the challenge of robust feature vector creation. Our approach showcases enhanced learning capabilities through modified ViT architecture and ResNet architecture. The dual-pathway training enriches feature extraction, culminating in a comprehensive feature vector. Preliminary results demonstrate significant potential for accurate detection of MI. Our study introduces a hybrid ResNet-ViT model for advanced MI detection, highlighting the synergy between global and local feature extraction. This approach holds promise for elevating MI classification accuracy, with implications for improved patient care. Further validation and clinical applicability exploration are warranted. |
| first_indexed | 2024-03-07T15:04:19Z |
| format | Article |
| id | doaj.art-6f4bf6fd30534b35af5974d80ee12263 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-07T15:04:19Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-6f4bf6fd30534b35af5974d80ee122632024-03-05T18:57:33ZengNature PortfolioScientific Reports2045-23222024-02-0114111710.1038/s41598-024-54846-8A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detectionJunaid Abdul Wahid0Xu Mingliang1Muhammad Ayoub2Shabir Husssain3Lifeng Li4Lei Shi5School of Computer and Artificial Intelligence, Zhengzhou UniversitySchool of Computer and Artificial Intelligence, Zhengzhou UniversitySchool of Computer Science and Engineering, Central South UniversitySchool of Architecture, Harbin Institute of TechnologyDepartment of Radiology, The Affiliated Changsha Central Hospital, Hengyang Medical school, University of South ChinaSchool of Cyberspace and Security, Zhengzhou UniversityAbstract Myocardial infarction (MI) remains a significant contributor to global mortality and morbidity, necessitating accurate and timely diagnosis. Current diagnostic methods encounter challenges in capturing intricate patterns, urging the need for advanced automated approaches to enhance MI detection. In this study, we strive to advance MI detection by proposing a hybrid approach that combines the strengths of ResNet and Vision Transformer (ViT) models, leveraging global and local features for improved accuracy. We introduce a slim-model ViT design with multibranch networks and channel attention mechanisms to enhance patch embedding extraction, addressing ViT’s limitations. By training data through both ResNet and modified ViT models, we incorporate a dual-pathway feature extraction strategy. The fusion of global and local features addresses the challenge of robust feature vector creation. Our approach showcases enhanced learning capabilities through modified ViT architecture and ResNet architecture. The dual-pathway training enriches feature extraction, culminating in a comprehensive feature vector. Preliminary results demonstrate significant potential for accurate detection of MI. Our study introduces a hybrid ResNet-ViT model for advanced MI detection, highlighting the synergy between global and local feature extraction. This approach holds promise for elevating MI classification accuracy, with implications for improved patient care. Further validation and clinical applicability exploration are warranted.https://doi.org/10.1038/s41598-024-54846-8 |
| spellingShingle | Junaid Abdul Wahid Xu Mingliang Muhammad Ayoub Shabir Husssain Lifeng Li Lei Shi A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection Scientific Reports |
| title | A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection |
| title_full | A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection |
| title_fullStr | A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection |
| title_full_unstemmed | A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection |
| title_short | A hybrid ResNet-ViT approach to bridge the global and local features for myocardial infarction detection |
| title_sort | hybrid resnet vit approach to bridge the global and local features for myocardial infarction detection |
| url | https://doi.org/10.1038/s41598-024-54846-8 |
| work_keys_str_mv | AT junaidabdulwahid ahybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT xumingliang ahybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT muhammadayoub ahybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT shabirhusssain ahybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT lifengli ahybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT leishi ahybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT junaidabdulwahid hybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT xumingliang hybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT muhammadayoub hybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT shabirhusssain hybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT lifengli hybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection AT leishi hybridresnetvitapproachtobridgetheglobalandlocalfeaturesformyocardialinfarctiondetection |