Video-based AI for beat-to-beat assessment of cardiac function.
Video-based AI for beat-to-beat assessment of cardiac function.
复制标题
DOI：
10.1038/s41586-020-2145-8
复制
发表时间：
2020-04
期刊：
影响因子：
64.8
通讯作者：
Zou JY
中科院分区：
文献类型：
--
作者：
Ouyang D;He B;Ghorbani A;Yuan N;Ebinger J;Langlotz CP;Heidenreich PA;Harrington RA;Liang DH;Ashley EA;Zou JY
心功能的准确评估对于心血管疾病的诊断、心脏毒性的筛查以及危重病患者的临床治疗至关重要。然而，心脏功能的人类评估集中在心动周期的有限采样上，尽管经过多年的训练，但观察者之间存在显着的差异。为了克服这一挑战，我们提出了第一个基于视频的深度学习算法EchoNet-Dynamic，该算法在分割左心室、估计射血分数和评估心肌病等关键任务中超越了人类专家的表现。在超声心动图视频上训练，我们的模型准确地分割了左心室，Dice相似系数为0.92，预测射血分数的平均绝对误差为4.1%，并可靠地对射血分数降低的心力衰竭进行了分类（AUC为0.97）。在另一个医疗保健系统的外部数据集中，EchoNet-Dynamic预测射血分数的平均绝对误差为6.0%，并将射血分数降低的心力衰竭分类为AUC为0.96。重复人类测量的前瞻性评估证实，该模型具有与人类专家相当或更少的方差。通过利用多个心动周期的信息，我们的模型可以快速识别射血分数的细微变化，比人类评估更具可重复性，并为实时精确诊断心血管疾病奠定了基础。作为促进进一步创新的新资源，我们还公开了10，030个带注释的超声心动图视频的最大医学视频数据集。
Accurate assessment of cardiac function is crucial for diagnosing cardiovascular disease, screening for cardiotoxicity, and deciding clinical management in patients with critical illness. However human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has significant inter-observer variability despite years of training. To overcome this challenge, we present the first video-based deep learning algorithm, EchoNet-Dynamic, that surpasses human expert performance in the critical tasks of segmenting the left ventricle, estimating ejection fraction, and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice Similarity Coefficient of 0.92, predicts ejection fraction with mean absolute error of 4.1%, and reliably classifies heart failure with reduced ejection fraction (AUC of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts ejection fraction with mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an AUC of 0.96. Prospective evaluation with repeated human measurements confirms that the model has comparable or less variance than human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation, and lays the foundation for precise diagnosis of cardiovascular disease in real-time. As a new resource to promote further innovation, we also make publicly available the largest medical video dataset of 10,030 annotated echocardiogram videos.
登录
查看更多内容
影响因子：
49.6
作者：
Bui, Anh L.;Horwich, Tamara B.;Fonarow, Gregg C.
通讯作者：
Fonarow, Gregg C.
幸存的败血症运动：严重败血症和化粪池冲击管理的国际指南，2012年。
影响因子：
38.9
作者：
Dellinger RP;Levy MM;Rhodes A;Annane D;Gerlach H;Opal SM;Sevransky JE;Sprung CL;Douglas IS;Jaeschke R;Osborn TM;Nunnally ME;Townsend SR;Reinhart K;Kleinpell RM;Angus DC;Deutschman CS;Machado FR;Rubenfeld GD;Webb S;Beale RJ;Vincent JL;Moreno R;Surviving Sepsis Campaign Guidelines Committee including The Pediatric Subgroup
通讯作者：
Surviving Sepsis Campaign Guidelines Committee including The Pediatric Subgroup
影响因子：
37.8
作者：
Zhang J;Gajjala S;Agrawal P;Tison GH;Hallock LA;Beussink-Nelson L;Lassen MH;Fan E;Aras MA;Jordan C;Fleischmann KE;Melisko M;Qasim A;Shah SJ;Bajcsy R;Deo RC
通讯作者：
Deo RC
影响因子：
2.1
作者：
Cole, Graham D.;Dhutia, Niti M.;Francis, Darrel P.
通讯作者：
Francis, Darrel P.
影响因子：
6.2
作者：
Lang, Roberto M.;Badano, Luigi P.;Voigt, Jens-Uwe
通讯作者：
Voigt, Jens-Uwe