利用数据驱动的原位对比度映射,通过原位 T1 心脏 MRI 对慢性心肌梗死进行可靠的视觉检测。

IF 3.8 Q1 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING Radiology. Cardiothoracic imaging Pub Date : 2024-08-01 DOI:10.1148/ryct.230338
Khalid Youssef, Xinheng Zhang, Ghazal Yoosefian, Yinyin Chen, Shing Fai Chan, Hsin-Jung Yang, Keyur Vora, Andrew Howarth, Andreas Kumar, Behzad Sharif, Rohan Dharmakumar
{"title":"利用数据驱动的原位对比度映射,通过原位 T1 心脏 MRI 对慢性心肌梗死进行可靠的视觉检测。","authors":"Khalid Youssef, Xinheng Zhang, Ghazal Yoosefian, Yinyin Chen, Shing Fai Chan, Hsin-Jung Yang, Keyur Vora, Andrew Howarth, Andreas Kumar, Behzad Sharif, Rohan Dharmakumar","doi":"10.1148/ryct.230338","DOIUrl":null,"url":null,"abstract":"<p><p>Purpose To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and <i>t</i>-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as <i>data-driven native mapping</i> (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; <i>P</i> < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; <i>P</i> = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (<i>R</i><sup>2</sup> = 0.71 for native T1 maps vs LGE; <i>R</i><sup>2</sup> = 0.85 for DNM vs LGE; <i>P</i> < .001). Conclusion Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories. <b>Keywords:</b> Chronic Myocardial Infarction, Cardiac MRI, Data-Driven Native Contrast Mapping <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":"6 4","pages":"e230338"},"PeriodicalIF":3.8000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11369652/pdf/","citationCount":"0","resultStr":"{\"title\":\"Enabling Reliable Visual Detection of Chronic Myocardial Infarction with Native T1 Cardiac MRI Using Data-Driven Native Contrast Mapping.\",\"authors\":\"Khalid Youssef, Xinheng Zhang, Ghazal Yoosefian, Yinyin Chen, Shing Fai Chan, Hsin-Jung Yang, Keyur Vora, Andrew Howarth, Andreas Kumar, Behzad Sharif, Rohan Dharmakumar\",\"doi\":\"10.1148/ryct.230338\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Purpose To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and <i>t</i>-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as <i>data-driven native mapping</i> (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; <i>P</i> < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; <i>P</i> = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (<i>R</i><sup>2</sup> = 0.71 for native T1 maps vs LGE; <i>R</i><sup>2</sup> = 0.85 for DNM vs LGE; <i>P</i> < .001). Conclusion Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories. <b>Keywords:</b> Chronic Myocardial Infarction, Cardiac MRI, Data-Driven Native Contrast Mapping <i>Supplemental material is available for this article.</i> © RSNA, 2024.</p>\",\"PeriodicalId\":21168,\"journal\":{\"name\":\"Radiology. Cardiothoracic imaging\",\"volume\":\"6 4\",\"pages\":\"e230338\"},\"PeriodicalIF\":3.8000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11369652/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Radiology. Cardiothoracic imaging\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1148/ryct.230338\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology. Cardiothoracic imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/ryct.230338","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

摘要

目的 研究在犬模型的慢性再灌注心肌梗死中,用数据驱动的机器学习像素法取代用于获得原始 T1 图的通用拟合算法,是否能优化梗死与远端心肌的对比度。材料与方法 研究了一种慢性心肌梗死的对照大型动物模型(24 只犬科动物,雌雄各半),其组织学证据表明梗死组织的组成不均匀。使用自组织图和 t 分布随机邻域嵌入的无监督聚类技术来分析和可视化原生 T1 加权像素强度模式。对深度神经网络模型进行了训练,以便将原生 T1 加权图像系列中的像素强度模式映射到晚期钆增强(LGE)图像上的相应像素上,从而生成视觉增强的非对比度映射图,这一过程被称为数据驱动的原生映射(DNM)。采用皮尔逊相关系数和布兰-阿尔特曼分析法将 DNM 方法的结果与标准 T1 地图进行比较。结果 原位 T1 加权图像在梗死区和偏远区之间显示出不同的像素强度模式。颗粒模式可视化显示,与原始 T1 图相比,LGE 标记的梗死区与偏远区的分离度更高。DNM 的表观对比噪声比(平均值为 15.01 ± 2.88 [标度])与原始 T1 地图(5.64 ± 1.58;P < .001)有显著差异,但与 LGE 对比噪声比(15.51 ± 2.43;P = .40)相似。与原始 T1 地图相比,基于 LGE 的梗死区域与 DNM 的相关性更强(原始 T1 地图与 LGE 相比,R2 = 0.71;DNM 与 LGE 相比,R2 = 0.85;P < .001)。结论 原位 T1 加权像素所携带的信息可通过建议的 DNM 方法提取出来,从而最大限度地提高梗死区和远端区域的图像对比度,增强慢性梗死区的可视化。关键词慢性心肌梗死 心脏 MRI 数据驱动的原位对比度映射 本文有补充材料。© RSNA, 2024.
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Enabling Reliable Visual Detection of Chronic Myocardial Infarction with Native T1 Cardiac MRI Using Data-Driven Native Contrast Mapping.

Purpose To investigate whether infarct-to-remote myocardial contrast can be optimized by replacing generic fitting algorithms used to obtain native T1 maps with a data-driven machine learning pixel-wise approach in chronic reperfused infarct in a canine model. Materials and Methods A controlled large animal model (24 canines, equal male and female animals) of chronic myocardial infarction with histologic evidence of heterogeneous infarct tissue composition was studied. Unsupervised clustering techniques using self-organizing maps and t-distributed stochastic neighbor embedding were used to analyze and visualize native T1-weighted pixel-intensity patterns. Deep neural network models were trained to map pixel-intensity patterns from native T1-weighted image series to corresponding pixels on late gadolinium enhancement (LGE) images, yielding visually enhanced noncontrast maps, a process referred to as data-driven native mapping (DNM). Pearson correlation coefficients and Bland-Altman analyses were used to compare findings from the DNM approach against standard T1 maps. Results Native T1-weighted images exhibited distinct pixel-intensity patterns between infarcted and remote territories. Granular pattern visualization revealed higher infarct-to-remote cluster separability with LGE labeling as compared with native T1 maps. Apparent contrast-to-noise ratio from DNM (mean, 15.01 ± 2.88 [SD]) was significantly different from native T1 maps (5.64 ± 1.58; P < .001) but similar to LGE contrast-to-noise ratio (15.51 ± 2.43; P = .40). Infarcted areas based on LGE were more strongly correlated with DNM compared with native T1 maps (R2 = 0.71 for native T1 maps vs LGE; R2 = 0.85 for DNM vs LGE; P < .001). Conclusion Native T1-weighted pixels carry information that can be extracted with the proposed DNM approach to maximize image contrast between infarct and remote territories for enhanced visualization of chronic infarct territories. Keywords: Chronic Myocardial Infarction, Cardiac MRI, Data-Driven Native Contrast Mapping Supplemental material is available for this article. © RSNA, 2024.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
20.40
自引率
1.40%
发文量
0
期刊介绍:
期刊最新文献
Accelerated Cardiac MRI with Deep Learning-based Image Reconstruction for Cine Imaging. Diagnostic Performance of AI-enabled Plaque Quantification from Coronary CT Angiography Compared with Intravascular Ultrasound. Cardiac MRI Pectoralis Muscle Thickness as a Measure of Sarcopenia: Prognostic Significance, Interreader Agreement, and Physiologic Correlation. Association of Aortic Stiffness with Heart Failure with Preserved Ejection Fraction: New Insights into the Ventriculoarterial Connection. Severe Quadricuspid Pulmonary Valve Stenosis Presenting as Scrotal Edema.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1