A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis
BackgroundIn ST-segment elevation myocardial infarction (STEMI) with the restoration of TIMI 3 flow by percutaneous coronary intervention (PCI), visually defined microvascular obstruction (MVO) was shown to be the predictor of poor prognosis, but not an ideal risk stratification method. We intend to...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1140025/full |
| _version_ | 1797838650082328576 |
|---|---|
| author | Mingqi Li Dewen Zeng Yanxiang Zhou Jinling Chen Sheng Cao Hongning Song Bo Hu Wenyue Yuan Jing Chen Yuanting Yang Hao Wang Hongwen Fei Yiyu Shi Qing Zhou |
| author_facet | Mingqi Li Dewen Zeng Yanxiang Zhou Jinling Chen Sheng Cao Hongning Song Bo Hu Wenyue Yuan Jing Chen Yuanting Yang Hao Wang Hongwen Fei Yiyu Shi Qing Zhou |
| author_sort | Mingqi Li |
| collection | DOAJ |
| description | BackgroundIn ST-segment elevation myocardial infarction (STEMI) with the restoration of TIMI 3 flow by percutaneous coronary intervention (PCI), visually defined microvascular obstruction (MVO) was shown to be the predictor of poor prognosis, but not an ideal risk stratification method. We intend to introduce deep neural network (DNN) assisted myocardial contrast echocardiography (MCE) quantitative analysis and propose a better risk stratification model.Methods194 STEMI patients with successful primary PCI with at least 6 months follow-up were included. MCE was performed within 48 h after PCI. The major adverse cardiovascular events (MACE) were defined as cardiac death, congestive heart failure, reinfarction, stroke, and recurrent angina. The perfusion parameters were derived from a DNN-based myocardial segmentation framework. Three patterns of visual microvascular perfusion (MVP) qualitative analysis: normal, delay, and MVO. Clinical markers and imaging features, including global longitudinal strain (GLS) were analyzed. A calculator for risk was constructed and validated with bootstrap resampling.ResultsThe time-cost for processing 7,403 MCE frames is 773 s. The correlation coefficients of microvascular blood flow (MBF) were 0.99 to 0.97 for intra-observer and inter-observer variability. 38 patients met MACE in 6-month follow-up. We proposed A risk prediction model based on MBF [HR: 0.93 (0.91–0.95)] in culprit lesion areas and GLS [HR: 0.80 (0.73–0.88)]. At the best risk threshold of 40%, the AUC was 0.95 (sensitivity: 0.84, specificity: 0.94), better than visual MVP method (AUC: 0.70, Sensitivity: 0.89, Specificity: 0.40, IDI: −0.49). The Kaplan-Meier curves showed that the proposed risk prediction model allowed for better risk stratification.ConclusionThe MBF + GLS model allowed more accurate risk stratification of STEMI after PCI than visual qualitative analysis. The DNN-assisted MCE quantitative analysis is an objective, efficient and reproducible method to evaluate microvascular perfusion. |
| first_indexed | 2024-04-09T15:44:16Z |
| format | Article |
| id | doaj.art-7f0293710c3347ce9769458f97733d93 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-04-09T15:44:16Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-7f0293710c3347ce9769458f97733d932023-04-27T04:50:54ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2023-04-011010.3389/fcvm.2023.11400251140025A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysisMingqi Li0Dewen Zeng1Yanxiang Zhou2Jinling Chen3Sheng Cao4Hongning Song5Bo Hu6Wenyue Yuan7Jing Chen8Yuanting Yang9Hao Wang10Hongwen Fei11Yiyu Shi12Qing Zhou13Department of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Computer Science and Engineering, University of Notre Dame, South Bend, IN, United StatesDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Cardiology, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaDepartment of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, ChinaDepartment of Computer Science and Engineering, University of Notre Dame, South Bend, IN, United StatesDepartment of Ultrasound Imaging, Renmin Hospital of Wuhan University, Wuhan, ChinaBackgroundIn ST-segment elevation myocardial infarction (STEMI) with the restoration of TIMI 3 flow by percutaneous coronary intervention (PCI), visually defined microvascular obstruction (MVO) was shown to be the predictor of poor prognosis, but not an ideal risk stratification method. We intend to introduce deep neural network (DNN) assisted myocardial contrast echocardiography (MCE) quantitative analysis and propose a better risk stratification model.Methods194 STEMI patients with successful primary PCI with at least 6 months follow-up were included. MCE was performed within 48 h after PCI. The major adverse cardiovascular events (MACE) were defined as cardiac death, congestive heart failure, reinfarction, stroke, and recurrent angina. The perfusion parameters were derived from a DNN-based myocardial segmentation framework. Three patterns of visual microvascular perfusion (MVP) qualitative analysis: normal, delay, and MVO. Clinical markers and imaging features, including global longitudinal strain (GLS) were analyzed. A calculator for risk was constructed and validated with bootstrap resampling.ResultsThe time-cost for processing 7,403 MCE frames is 773 s. The correlation coefficients of microvascular blood flow (MBF) were 0.99 to 0.97 for intra-observer and inter-observer variability. 38 patients met MACE in 6-month follow-up. We proposed A risk prediction model based on MBF [HR: 0.93 (0.91–0.95)] in culprit lesion areas and GLS [HR: 0.80 (0.73–0.88)]. At the best risk threshold of 40%, the AUC was 0.95 (sensitivity: 0.84, specificity: 0.94), better than visual MVP method (AUC: 0.70, Sensitivity: 0.89, Specificity: 0.40, IDI: −0.49). The Kaplan-Meier curves showed that the proposed risk prediction model allowed for better risk stratification.ConclusionThe MBF + GLS model allowed more accurate risk stratification of STEMI after PCI than visual qualitative analysis. The DNN-assisted MCE quantitative analysis is an objective, efficient and reproducible method to evaluate microvascular perfusion.https://www.frontiersin.org/articles/10.3389/fcvm.2023.1140025/fullST-segment elevation myocardial infarctiondeep neural networkmyocardial contrast echocardiographymicrovascular perfusionprognosis |
| spellingShingle | Mingqi Li Dewen Zeng Yanxiang Zhou Jinling Chen Sheng Cao Hongning Song Bo Hu Wenyue Yuan Jing Chen Yuanting Yang Hao Wang Hongwen Fei Yiyu Shi Qing Zhou A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis Frontiers in Cardiovascular Medicine ST-segment elevation myocardial infarction deep neural network myocardial contrast echocardiography microvascular perfusion prognosis |
| title | A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis |
| title_full | A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis |
| title_fullStr | A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis |
| title_full_unstemmed | A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis |
| title_short | A novel risk stratification model for STEMI after primary PCI: global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis |
| title_sort | novel risk stratification model for stemi after primary pci global longitudinal strain and deep neural network assisted myocardial contrast echocardiography quantitative analysis |
| topic | ST-segment elevation myocardial infarction deep neural network myocardial contrast echocardiography microvascular perfusion prognosis |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2023.1140025/full |
| work_keys_str_mv | AT mingqili anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT dewenzeng anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT yanxiangzhou anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT jinlingchen anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT shengcao anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT hongningsong anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT bohu anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT wenyueyuan anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT jingchen anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT yuantingyang anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT haowang anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT hongwenfei anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT yiyushi anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT qingzhou anovelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT mingqili novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT dewenzeng novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT yanxiangzhou novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT jinlingchen novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT shengcao novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT hongningsong novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT bohu novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT wenyueyuan novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT jingchen novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT yuantingyang novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT haowang novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT hongwenfei novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT yiyushi novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis AT qingzhou novelriskstratificationmodelforstemiafterprimarypcigloballongitudinalstrainanddeepneuralnetworkassistedmyocardialcontrastechocardiographyquantitativeanalysis |