Predicting Late Gadolinium Enhancement of Acute Myocardial Infarction in Contrast-Free Cardiac Cine MRI Using Deep Generative Learning.

IF 6.5 1区医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS

Circulation: Cardiovascular Imaging Pub Date : 2024-09-10 DOI:10.1161/circimaging.124.016786

Haikun Qi,Pengfang Qian,Langlang Tang,Binghua Chen,Dongaolei An,Lian-Ming Wu

{"title":"Predicting Late Gadolinium Enhancement of Acute Myocardial Infarction in Contrast-Free Cardiac Cine MRI Using Deep Generative Learning.","authors":"Haikun Qi,Pengfang Qian,Langlang Tang,Binghua Chen,Dongaolei An,Lian-Ming Wu","doi":"10.1161/circimaging.124.016786","DOIUrl":null,"url":null,"abstract":"BACKGROUND\r\nLate gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) is a standard technique for diagnosing myocardial infarction (MI), which, however, poses risks due to gadolinium contrast usage. Techniques enabling MI assessment based on contrast-free CMR are desirable to overcome the limitations associated with contrast enhancement.\r\n\r\nMETHODS\r\nWe introduce a novel deep generative learning method, termed cine-generated enhancement (CGE), which transforms standard contrast-free cine CMR into LGE-equivalent images for MI assessment. CGE features with multislice spatiotemporal feature extractor, enhancement contrast modulation, and sophisticated loss function. Data from 430 patients with acute MI from 3 centers were collected. After image quality control, 1525 pairs (289 patients) of center I were used for training, and 293 slices (52 patients) of the same center were reserved for internal testing. The 40 patients (401 slices) of the other 2 centers were used for external testing. The CGE robustness was further tested in 20 normal subjects in a public cine CMR data set. CGE images were compared with LGE for image quality assessment and MI quantification regarding scar size and transmurality.\r\n\r\nRESULTS\r\nThe CGE method produced images of superior quality to LGE in both internal and external data sets. There was a significant (P<0.001) correlation between CGE and LGE measurements of scar size (Pearson correlation, 0.79/0.80; intraclass correlation coefficient, 0.79/0.77) and transmurality (Pearson correlation, 0.76/0.64; intraclass correlation coefficient, 0.76/0.63) in internal/external data set. Considering all data sets, CGE demonstrated high sensitivity (91.27%) and specificity (95.83%) in detecting scars. Realistic enhancement images were obtained for the normal subjects in the public data set without false positive subjects.\r\n\r\nCONCLUSIONS\r\nCGE achieved superior image quality to LGE and accurate scar delineation in patients with acute MI of both internal and external data sets. CGE can significantly simplify the CMR examination, reducing scan times and risks associated with gadolinium-based contrasts, which are crucial for acute patients.","PeriodicalId":10202,"journal":{"name":"Circulation: Cardiovascular Imaging","volume":"308 1","pages":"e016786"},"PeriodicalIF":6.5000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Circulation: Cardiovascular Imaging","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1161/circimaging.124.016786","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

BACKGROUND Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) is a standard technique for diagnosing myocardial infarction (MI), which, however, poses risks due to gadolinium contrast usage. Techniques enabling MI assessment based on contrast-free CMR are desirable to overcome the limitations associated with contrast enhancement. METHODS We introduce a novel deep generative learning method, termed cine-generated enhancement (CGE), which transforms standard contrast-free cine CMR into LGE-equivalent images for MI assessment. CGE features with multislice spatiotemporal feature extractor, enhancement contrast modulation, and sophisticated loss function. Data from 430 patients with acute MI from 3 centers were collected. After image quality control, 1525 pairs (289 patients) of center I were used for training, and 293 slices (52 patients) of the same center were reserved for internal testing. The 40 patients (401 slices) of the other 2 centers were used for external testing. The CGE robustness was further tested in 20 normal subjects in a public cine CMR data set. CGE images were compared with LGE for image quality assessment and MI quantification regarding scar size and transmurality. RESULTS The CGE method produced images of superior quality to LGE in both internal and external data sets. There was a significant (P<0.001) correlation between CGE and LGE measurements of scar size (Pearson correlation, 0.79/0.80; intraclass correlation coefficient, 0.79/0.77) and transmurality (Pearson correlation, 0.76/0.64; intraclass correlation coefficient, 0.76/0.63) in internal/external data set. Considering all data sets, CGE demonstrated high sensitivity (91.27%) and specificity (95.83%) in detecting scars. Realistic enhancement images were obtained for the normal subjects in the public data set without false positive subjects. CONCLUSIONS CGE achieved superior image quality to LGE and accurate scar delineation in patients with acute MI of both internal and external data sets. CGE can significantly simplify the CMR examination, reducing scan times and risks associated with gadolinium-based contrasts, which are crucial for acute patients.

查看原文本刊更多论文

利用深度生成学习预测无对比度心脏 Cine MRI 中急性心肌梗死的晚期钆增强。

背景晚期钆增强（LGE）心脏磁共振（CMR）是诊断心肌梗死（MI）的标准技术，但由于钆对比剂的使用而存在风险。我们介绍了一种新颖的深度生成学习方法，称为 "电影生成增强"（CGE），它能将标准的无对比度电影 CMR 转变为 LGE 等效图像，用于 MI 评估。CGE 具有多切片时空特征提取器、增强对比度调制和复杂的损失函数。收集了来自 3 个中心的 430 名急性心肌梗死患者的数据。经过图像质量控制后，中心I的1525对切片（289名患者）被用于训练，同一中心的293张切片（52名患者）被用于内部测试。另外两个中心的 40 名患者（401 张切片）用于外部测试。在公共 cine CMR 数据集中，对 20 名正常受试者的 CGE 鲁棒性进行了进一步测试。结果在内部和外部数据集中，CGE 方法生成的图像质量优于 LGE。在内部/外部数据集中，CGE 和 LGE 测量的疤痕大小（Pearson 相关性，0.79/0.80；类内相关系数，0.79/0.77）和透亮度（Pearson 相关性，0.76/0.64；类内相关系数，0.76/0.63）之间存在明显的相关性（P<0.001）。考虑到所有数据集，CGE 在检测疤痕方面表现出较高的灵敏度（91.27%）和特异性（95.83%）。结论在内部和外部数据集中，CGE 的图像质量优于 LGE，并能准确划分急性心肌梗死患者的疤痕。CGE 可大大简化 CMR 检查，减少扫描时间，降低与钆对比剂相关的风险，这对急性心肌梗死患者至关重要。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Circulation: Cardiovascular Imaging 医学-核医学

CiteScore

6.30

自引率

2.70%

发文量

225

审稿时长

6-12 weeks

期刊介绍： Circulation: Cardiovascular Imaging, an American Heart Association journal, publishes high-quality, patient-centric articles focusing on observational studies, clinical trials, and advances in applied (translational) research. The journal features innovative, multimodality approaches to the diagnosis and risk stratification of cardiovascular disease. Modalities covered include echocardiography, cardiac computed tomography, cardiac magnetic resonance imaging and spectroscopy, magnetic resonance angiography, cardiac positron emission tomography, noninvasive assessment of vascular and endothelial function, radionuclide imaging, molecular imaging, and others. Article types considered by Circulation: Cardiovascular Imaging include Original Research, Research Letters, Advances in Cardiovascular Imaging, Clinical Implications of Molecular Imaging Research, How to Use Imaging, Translating Novel Imaging Technologies into Clinical Applications, and Cardiovascular Images.