A machine learning cardiac magnetic resonance approach to extract disease features and automate pulmonary arterial hypertension diagnosis.
A machine learning cardiac magnetic resonance approach to extract disease features and automate pulmonary arterial hypertension diagnosis.
复制标题
DOI：
10.1093/ehjci/jeaa001
复制
发表时间：
2021-01-22
期刊：
影响因子：
--
通讯作者：
Kiely DG
中科院分区：
文献类型：
--
作者：
Swift AJ;Lu H;Uthoff J;Garg P;Cogliano M;Taylor J;Metherall P;Zhou S;Johns CS;Alabed S;Condliffe RA;Lawrie A;Wild JM;Kiely DG
肺动脉高压(PAH)是一种进行性疾病，病死率高。肺动脉高压的定量心血管磁共振(CMR)成像指标针对单个心脏结构，具有诊断和预后价值，但获得这些指标具有挑战性。这项研究的主要目的是开发和测试一种基于张量的机器学习方法，以使用CMR整体识别PAH的诊断特征，其次，可视化和解释与PAH相关的关键区分特征。来自ASPIRE登记的持续治疗的有肺动脉高压或无肺动脉高压(PH)证据的患者，在48 小时内接受了CMR和右心导管术。提出了一种基于张量的机器学习方法--多线性子空间学习方法，并将该方法的诊断精度与标准CMR测量结果进行了比较。共有220名患者入选，其中150人患有肺动脉高压，70人没有肺动脉高压。根据受试者操作特征分析(P <； 0.001)的曲线下面积评估，该方法的诊断准确率很高：肺动脉高压：0.92，略高于标准的CMR指标。此外，使用该方法建立诊断花费的时间较少，在10 S内即可实现。学习的特征被可视化地显示在特征图上，与心脏时相对应，确认已知的特征，并识别潜在的新的诊断特征。提出了一种基于张量的机器学习方法，并将其应用于CMR。PAH的诊断准确率很高，新的学习特征被可视化，具有诊断潜力。
Pulmonary arterial hypertension (PAH) is a progressive condition with high mortality. Quantitative cardiovascular magnetic resonance (CMR) imaging metrics in PAH target individual cardiac structures and have diagnostic and prognostic utility but are challenging to acquire. The primary aim of this study was to develop and test a tensor-based machine learning approach to holistically identify diagnostic features in PAH using CMR, and secondarily, visualize and interpret key discriminative features associated with PAH. Consecutive treatment naive patients with PAH or no evidence of pulmonary hypertension (PH), undergoing CMR and right heart catheterization within 48 h, were identified from the ASPIRE registry. A tensor-based machine learning approach, multilinear subspace learning, was developed and the diagnostic accuracy of this approach was compared with standard CMR measurements. Two hundred and twenty patients were identified: 150 with PAH and 70 with no PH. The diagnostic accuracy of the approach was high as assessed by area under the curve at receiver operating characteristic analysis (P < 0.001): 0.92 for PAH, slightly higher than standard CMR metrics. Moreover, establishing the diagnosis using the approach was less time-consuming, being achieved within 10 s. Learnt features were visualized in feature maps with correspondence to cardiac phases, confirming known and also identifying potentially new diagnostic features in PAH. A tensor-based machine learning approach has been developed and applied to CMR. High diagnostic accuracy has been shown for PAH diagnosis and new learnt features were visualized with diagnostic potential.
登录
查看更多内容
影响因子：
19.7
作者：
Johns CS;Kiely DG;Rajaram S;Hill C;Thomas S;Karunasaagarar K;Garg P;Hamilton N;Solanki R;Capener DA;Elliot C;Sabroe I;Charalamopopoulos A;Condliffe R;Wild JM;Swift AJ
通讯作者：
Swift AJ
影响因子：
2.6
作者：
Bergemann R;Allsopp J;Jenner H;Daniels FA;Drage E;Samyshkin Y;Schmitt C;Wood S;Kiely DG;Lawrie A;SPHInX Project team
通讯作者：
SPHInX Project team
DOI：
10.1164/rccm.201909-1771oc
发表时间：
2020-02-15
影响因子：
24.7
作者：
Lewis, Robert A.;Johns, Christopher S.;Kiely, David G.
通讯作者：
Kiely, David G.
DOI：
10.1016/0735-1097(93)90327-w
发表时间：
1993-05-01
影响因子：
24
作者：
KATZ, J;WHANG, J;BARST, RJ
通讯作者：
BARST, RJ
影响因子：
7.5
作者：
Gall, Henning;Hoeper, Marius M.;Richter, Manuel J.;Cacheris, William;Hinzmann, Barbara;Mayer, Eckhard
通讯作者：
Mayer, Eckhard