论著摘要 |【AI-MR】三维右心室运动的机器学习使肺结核预测的肺动脉高压:心脏磁共振成像研究(双语版)

2018-02-23 10:55:43 admin 0
标签:   AI 机器学习 三维心脏收缩运动 生存预测 肺动脉高压 右心室衰竭 心脏

Machine Learning of Three-dimensional Right Ventricular Motion Enables Outcome Prediction in Pulmonary Hypertension: A Cardiac MR Imaging Study.

发表日期: 2017.05.01   来源:Radiology. 2017 May;283(2):381-390.

作者:

Dawes TJW1, de Marvao A1, Shi W1, Fletcher T1, Watson GMJ1, Wharton J1 , Rhodes CJ1, Howard LSGE1, Gibbs JSR1, Rueckert D1, Cook SA1, Wilkins MR1, O'Regan DP1.

作者介绍:

1. From the MRC Clinical Sciences Centre, Du Cane Rd, London W12 0NN, England (T.J.W.D., A.d.M., W.S., T.F., S.A.C., D.P.O.); Division of Experimental Medicine, Department of Medicine (T.J.W.D, T.F., G.M.J.W., J.W., C.J.R., M.R.W.), Department of Computing (W.S., D.R.), and National Heart and Lung Institute (J.S.R.G.), Imperial College London, London, England; National Heart Centre Singapore, Singapore and Duke-NUS Graduate Medical School, Singapore (S.A.C.); and Department of Cardiology, National Pulmonary Hypertension Service, Imperial College Healthcare NHS Trust, London, England (L.S.G.E.H., J.S.R.G.).

摘要

Abstact

目的

通过使用三维心脏收缩运动模式的监督机器学习来确定患者的生存期和肺动脉高压中右心室衰竭的机制是否可以预测。

Purpose

To determine if patient survival and mechanisms of right ventricular failure in pulmonary hypertension could be predicted by using supervised machine learning of three-dimensional patterns of systolic cardiac motion.

材料和方法

研究得到研究伦理委员会的批准,参与者书面知情同意。对新诊断的肺动脉高压的256名患者(143名女性;平均年龄±标准差,63岁±17)进行了心脏磁共振(MR)成像,右心导管检查和6分钟步行试验,随访4.0年。使用短轴电影图像的半自动分割来创建右心室运动的三维模型。使用监督主成分分析来识别最能强烈预测生存的收缩运动模式。通过使用生存时间中位数和曲线下面积的差异来评估存活预测,并使用时间依赖性接受者操作特征分析1年存活。

Materials and Methods

The study was approved by a research ethics committee, and participants gave written informed consent. Two hundred fifty-six patients (143 women; mean age ± standard deviation, 63 years ± 17) with newly diagnosed pulmonary hypertension underwent cardiac magnetic resonance (MR) imaging, right-sided heart catheterization, and 6-minute walk testing with a median follow-up of 4.0 years. Semiautomated segmentation of short-axis cine images was used to create a three-dimensional model of right ventricular motion. Supervised principal components analysis was used to identify patterns of systolic motion that were most strongly predictive of survival. Survival prediction was assessed by using difference in median survival time and area under the curve with time-dependent receiver operating characteristic analysis for 1-year survival.

结果

随访结束时,36%的患者(其中93人)死亡,1人接受肺移植。 由于隔膜和游离壁的有效收缩减少以及基底纵向运动减少,预测的结果不佳。当添加常规影像学和血流动力学的功能和临床指标时,三维心脏运动改善了生存预测(受试者工作特征曲线下面积分别为0.73和0.60,P < 0.001),并使得高风险组和低风险组之间的生存期中位数的差异增大(分别为13.8和10.7岁,P < 0.001)。

Results

At the end of follow-up, 36% of patients (93 of 256) died, and one underwent lung transplantation. Poor outcome was predicted by a loss of effective contraction in the septum and free wall, coupled with reduced basal longitudinal motion. When added to conventional imaging and hemodynamic, functional, and clinical markers, three-dimensional cardiac motion improved survival prediction (area under the receiver operating characteristic curve, 0.73 vs 0.60, respectively; P < .001) and provided greater differentiation according to difference in median survival time between high- and low-risk groups (13.8 vs 10.7 years, respectively; P < .001).

结论

机器学习生存模型,使用三维心脏运动预测新诊断肺动脉高压患者独立于传统危险因素的结果。在线补充材料可用于这篇文章。

Conclusions

A machine-learning survival model that uses three-dimensional cardiac motion predicts outcome independent of conventional risk factors in patients with newly diagnosed pulmonary hypertension. Online supplemental material is available for this article.

阅读原文:PMID: 28092203  PMCID: PMC5398374  DOI: 10.1148/radiol.2016161315


慧影医疗科技(北京)有限公司

地点:北京市海淀区中关村东升科技园B2-C103

电话:400-890-9020

邮箱:radcloud@huiyihuiying.com

关闭
图片
图片