Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks
Abstract Myocardial perfusion imaging (MPI) is a clinical tool which can assess the heart's perfusion status, thereby revealing impairments in patients' cardiac function. Within the MPI modality, the acquired three-dimensional signals are typically represented as a sequence of two-dimensio...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-54139-0 |
| _version_ | 1797274632788639744 |
|---|---|
| author | Yi-Lian Li Hsin-Bang Leu Chien-Hsin Ting Su-Shen Lim Tsung-Ying Tsai Cheng-Hsueh Wu I-Fang Chung Kung-Hao Liang |
| author_facet | Yi-Lian Li Hsin-Bang Leu Chien-Hsin Ting Su-Shen Lim Tsung-Ying Tsai Cheng-Hsueh Wu I-Fang Chung Kung-Hao Liang |
| author_sort | Yi-Lian Li |
| collection | DOAJ |
| description | Abstract Myocardial perfusion imaging (MPI) is a clinical tool which can assess the heart's perfusion status, thereby revealing impairments in patients' cardiac function. Within the MPI modality, the acquired three-dimensional signals are typically represented as a sequence of two-dimensional grayscale tomographic images. Here, we proposed an end-to-end survival training approach for processing gray-scale MPI tomograms to generate a risk score which reflects subsequent time to cardiovascular incidents, including cardiovascular death, non-fatal myocardial infarction, and non-fatal ischemic stroke (collectively known as Major Adverse Cardiovascular Events; MACE) as well as Congestive Heart Failure (CHF). We recruited a total of 1928 patients who had undergone MPI followed by coronary interventions. Among them, 80% (n = 1540) were randomly reserved for the training and 5- fold cross-validation stage, while 20% (n = 388) were set aside for the testing stage. The end-to-end survival training can converge well in generating effective AI models via the fivefold cross-validation approach with 1540 patients. When a candidate model is evaluated using independent images, the model can stratify patients into below-median-risk (n = 194) and above-median-risk (n = 194) groups, the corresponding survival curves of the two groups have significant difference (P < 0.0001). We further stratify the above-median-risk group to the quartile 3 and 4 group (n = 97 each), and the three patient strata, referred to as the high, intermediate and low risk groups respectively, manifest statistically significant difference. Notably, the 5-year cardiovascular incident rate is less than 5% in the low-risk group (accounting for 50% of all patients), while the rate is nearly 40% in the high-risk group (accounting for 25% of all patients). Evaluation of patient subgroups revealed stronger effect size in patients with three blocked arteries (Hazard ratio [HR]: 18.377, 95% CI 3.719–90.801, p < 0.001), followed by those with two blocked vessels at HR 7.484 (95% CI 1.858–30.150; p = 0.005). Regarding stent placement, patients with a single stent displayed a HR of 4.410 (95% CI 1.399–13.904; p = 0.011). Patients with two stents show a HR of 10.699 (95% CI 2.262–50.601; p = 0.003), escalating notably to a HR of 57.446 (95% CI 1.922–1717.207; p = 0.019) for patients with three or more stents, indicating a substantial relationship between the disease severity and the predictive capability of the AI for subsequent cardiovascular inciidents. The success of the MPI AI model in stratifying patients into subgroups with distinct time-to-cardiovascular incidents demonstrated the feasibility of proposed end-to-end survival training approach. |
| first_indexed | 2024-03-07T15:01:06Z |
| format | Article |
| id | doaj.art-219f4d85ce164488b056e1e513b6dab2 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-07T15:01:06Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-219f4d85ce164488b056e1e513b6dab22024-03-05T19:07:50ZengNature PortfolioScientific Reports2045-23222024-02-0114111210.1038/s41598-024-54139-0Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networksYi-Lian Li0Hsin-Bang Leu1Chien-Hsin Ting2Su-Shen Lim3Tsung-Ying Tsai4Cheng-Hsueh Wu5I-Fang Chung6Kung-Hao Liang7Institute of Biomedical Informatics, National Yang Ming Chiao Tung UniversityDepartment of Medicine, Taipei Veterans General HospitalDepartment of Nuclear Medicine, Taipei Veterans General HospitalDepartment of Medicine, Taipei Veterans General HospitalDepartment of Medicine, Taipei Veterans General HospitalDepartment of Medicine, Taipei Veterans General HospitalInstitute of Biomedical Informatics, National Yang Ming Chiao Tung UniversityDepartment of Medical Research, Taipei Veterans General HospitalAbstract Myocardial perfusion imaging (MPI) is a clinical tool which can assess the heart's perfusion status, thereby revealing impairments in patients' cardiac function. Within the MPI modality, the acquired three-dimensional signals are typically represented as a sequence of two-dimensional grayscale tomographic images. Here, we proposed an end-to-end survival training approach for processing gray-scale MPI tomograms to generate a risk score which reflects subsequent time to cardiovascular incidents, including cardiovascular death, non-fatal myocardial infarction, and non-fatal ischemic stroke (collectively known as Major Adverse Cardiovascular Events; MACE) as well as Congestive Heart Failure (CHF). We recruited a total of 1928 patients who had undergone MPI followed by coronary interventions. Among them, 80% (n = 1540) were randomly reserved for the training and 5- fold cross-validation stage, while 20% (n = 388) were set aside for the testing stage. The end-to-end survival training can converge well in generating effective AI models via the fivefold cross-validation approach with 1540 patients. When a candidate model is evaluated using independent images, the model can stratify patients into below-median-risk (n = 194) and above-median-risk (n = 194) groups, the corresponding survival curves of the two groups have significant difference (P < 0.0001). We further stratify the above-median-risk group to the quartile 3 and 4 group (n = 97 each), and the three patient strata, referred to as the high, intermediate and low risk groups respectively, manifest statistically significant difference. Notably, the 5-year cardiovascular incident rate is less than 5% in the low-risk group (accounting for 50% of all patients), while the rate is nearly 40% in the high-risk group (accounting for 25% of all patients). Evaluation of patient subgroups revealed stronger effect size in patients with three blocked arteries (Hazard ratio [HR]: 18.377, 95% CI 3.719–90.801, p < 0.001), followed by those with two blocked vessels at HR 7.484 (95% CI 1.858–30.150; p = 0.005). Regarding stent placement, patients with a single stent displayed a HR of 4.410 (95% CI 1.399–13.904; p = 0.011). Patients with two stents show a HR of 10.699 (95% CI 2.262–50.601; p = 0.003), escalating notably to a HR of 57.446 (95% CI 1.922–1717.207; p = 0.019) for patients with three or more stents, indicating a substantial relationship between the disease severity and the predictive capability of the AI for subsequent cardiovascular inciidents. The success of the MPI AI model in stratifying patients into subgroups with distinct time-to-cardiovascular incidents demonstrated the feasibility of proposed end-to-end survival training approach.https://doi.org/10.1038/s41598-024-54139-0End-to-end survival trainingSurvival analysisRisk scoreMultiresolution |
| spellingShingle | Yi-Lian Li Hsin-Bang Leu Chien-Hsin Ting Su-Shen Lim Tsung-Ying Tsai Cheng-Hsueh Wu I-Fang Chung Kung-Hao Liang Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks Scientific Reports End-to-end survival training Survival analysis Risk score Multiresolution |
| title | Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks |
| title_full | Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks |
| title_fullStr | Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks |
| title_full_unstemmed | Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks |
| title_short | Predicting long-term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks |
| title_sort | predicting long term time to cardiovascular incidents using myocardial perfusion imaging and deep convolutional neural networks |
| topic | End-to-end survival training Survival analysis Risk score Multiresolution |
| url | https://doi.org/10.1038/s41598-024-54139-0 |
| work_keys_str_mv | AT yilianli predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks AT hsinbangleu predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks AT chienhsinting predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks AT sushenlim predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks AT tsungyingtsai predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks AT chenghsuehwu predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks AT ifangchung predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks AT kunghaoliang predictinglongtermtimetocardiovascularincidentsusingmyocardialperfusionimaginganddeepconvolutionalneuralnetworks |