Stefano Buoso, Christian T Stoeck, Sebastian Kozerke
{"title":"利用合成数据训练的神经网络自动分析三维心脏标记磁共振图像。","authors":"Stefano Buoso, Christian T Stoeck, Sebastian Kozerke","doi":"10.1016/j.jocmr.2025.101869","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Three-dimensional (3D) tagged magnetic resonance (MR) imaging enables in vivo quantification of cardiac motion. While deep learning methods have been developed to analyze these images, they have been restricted to two-dimensional datasets. We present a deep learning approach specifically designed for displacement analysis of 3D cardiac tagged MR images.</p><p><strong>Methods: </strong>We developed two neural networks to predict left-ventricular motion throughout the cardiac cycle. Networks were trained using synthetic 3D tagged MR images, generated by combining a biophysical left-ventricular model with an analytical MR signal model. Network performance was initially validated on synthetic data, including assessment of signal-to-noise ratio (SNR) sensitivity. The networks were then retrospectively evaluated on an in vivo external validation human datasets and a in vivo porcine study.</p><p><strong>Results: </strong>For the external validation dataset, predicted displacements deviated from manual tracking by median(IQR) values of 0.72(1.51), 0.81(1.64) and 1.12(4.17) mm in x, y and z directions, respectively. In the porcine dataset, strain measurements showed median(IQR) differences from manual annotations of 0.01(0.04), 0.01(0.06) and - 0.01(0.18) for circumferential, longitudinal, and radial components. These strain values are within physiological ranges and demonstrate superior performance of the network approach compared to existing 3D tagged image analysis methods.</p><p><strong>Conclusions: </strong>The method enables rapid analysis times of approximately 10 seconds per cardiac phase, making it suitable for large cohort investigations.</p>","PeriodicalId":15221,"journal":{"name":"Journal of Cardiovascular Magnetic Resonance","volume":" ","pages":"101869"},"PeriodicalIF":4.2000,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automatic analysis of 3D cardiac tagged magnetic resonance images using neural networks trained on synthetic data.\",\"authors\":\"Stefano Buoso, Christian T Stoeck, Sebastian Kozerke\",\"doi\":\"10.1016/j.jocmr.2025.101869\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Three-dimensional (3D) tagged magnetic resonance (MR) imaging enables in vivo quantification of cardiac motion. While deep learning methods have been developed to analyze these images, they have been restricted to two-dimensional datasets. We present a deep learning approach specifically designed for displacement analysis of 3D cardiac tagged MR images.</p><p><strong>Methods: </strong>We developed two neural networks to predict left-ventricular motion throughout the cardiac cycle. Networks were trained using synthetic 3D tagged MR images, generated by combining a biophysical left-ventricular model with an analytical MR signal model. Network performance was initially validated on synthetic data, including assessment of signal-to-noise ratio (SNR) sensitivity. The networks were then retrospectively evaluated on an in vivo external validation human datasets and a in vivo porcine study.</p><p><strong>Results: </strong>For the external validation dataset, predicted displacements deviated from manual tracking by median(IQR) values of 0.72(1.51), 0.81(1.64) and 1.12(4.17) mm in x, y and z directions, respectively. In the porcine dataset, strain measurements showed median(IQR) differences from manual annotations of 0.01(0.04), 0.01(0.06) and - 0.01(0.18) for circumferential, longitudinal, and radial components. These strain values are within physiological ranges and demonstrate superior performance of the network approach compared to existing 3D tagged image analysis methods.</p><p><strong>Conclusions: </strong>The method enables rapid analysis times of approximately 10 seconds per cardiac phase, making it suitable for large cohort investigations.</p>\",\"PeriodicalId\":15221,\"journal\":{\"name\":\"Journal of Cardiovascular Magnetic Resonance\",\"volume\":\" \",\"pages\":\"101869\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2025-02-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Cardiovascular Magnetic Resonance\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1016/j.jocmr.2025.101869\",\"RegionNum\":1,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cardiovascular Magnetic Resonance","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.jocmr.2025.101869","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
Automatic analysis of 3D cardiac tagged magnetic resonance images using neural networks trained on synthetic data.
Background: Three-dimensional (3D) tagged magnetic resonance (MR) imaging enables in vivo quantification of cardiac motion. While deep learning methods have been developed to analyze these images, they have been restricted to two-dimensional datasets. We present a deep learning approach specifically designed for displacement analysis of 3D cardiac tagged MR images.
Methods: We developed two neural networks to predict left-ventricular motion throughout the cardiac cycle. Networks were trained using synthetic 3D tagged MR images, generated by combining a biophysical left-ventricular model with an analytical MR signal model. Network performance was initially validated on synthetic data, including assessment of signal-to-noise ratio (SNR) sensitivity. The networks were then retrospectively evaluated on an in vivo external validation human datasets and a in vivo porcine study.
Results: For the external validation dataset, predicted displacements deviated from manual tracking by median(IQR) values of 0.72(1.51), 0.81(1.64) and 1.12(4.17) mm in x, y and z directions, respectively. In the porcine dataset, strain measurements showed median(IQR) differences from manual annotations of 0.01(0.04), 0.01(0.06) and - 0.01(0.18) for circumferential, longitudinal, and radial components. These strain values are within physiological ranges and demonstrate superior performance of the network approach compared to existing 3D tagged image analysis methods.
Conclusions: The method enables rapid analysis times of approximately 10 seconds per cardiac phase, making it suitable for large cohort investigations.
期刊介绍:
Journal of Cardiovascular Magnetic Resonance (JCMR) publishes high-quality articles on all aspects of basic, translational and clinical research on the design, development, manufacture, and evaluation of cardiovascular magnetic resonance (CMR) methods applied to the cardiovascular system. Topical areas include, but are not limited to:
New applications of magnetic resonance to improve the diagnostic strategies, risk stratification, characterization and management of diseases affecting the cardiovascular system.
New methods to enhance or accelerate image acquisition and data analysis.
Results of multicenter, or larger single-center studies that provide insight into the utility of CMR.
Basic biological perceptions derived by CMR methods.