Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography.

Deep learning predicts cardiovascular disease risks from lung cancer screening low dose computed tomography.
复制标题

DOI:
10.1038/s41467-021-23235-4
复制
发表时间:
2021-05-20
影响因子:
16.6
通讯作者:
Yan P
Yan P
中科院分区:
综合性期刊1区
文献类型:
--
作者:
Chao H;Shan H;Homayounieh F;Singh R;Khera RD;Guo H;Su T;Wang G;Kalra MK;Yan P

文献摘要

参考文献

被引文献

相似文献

与普通人群相比,癌症患者心血管疾病(CVD)死亡率更高。用于肺癌筛查的低剂量计算机断层扫描(LDCT)为高危患者提供了同时评估心血管疾病风险的机会。我们的深度学习心血管疾病风险预测模型,使用来自国家肺癌筛查试验的30,286个LDCT进行训练,在2,085名受试者的单独测试集上实现了0.871的曲线下面积(AuC),并识别出具有高心血管死亡风险的患者(AuC值为0.768)。我们根据基于心电门控心脏CT的标记物来验证我们的模型,包括冠状动脉钙化(CAC)评分、CAD-RADS评分和来自335名受试者的独立数据集的MESA 10年风险评分。我们的工作表明,在高危患者中,深度学习可以将用于肺癌筛查的LDCT转换为用于CVD风险评估的双重筛查定量工具。用于肺癌筛查的低剂量计算机断层扫描(LDCT)为高危患者提供了同时评估心血管疾病风险的机会。在这里,作者开发了一个深度学习模型来执行这项任务,显示出人类水平的表现。
Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for simultaneous CVD risk estimation in at-risk patients. Here, the authors develop a deep learning model to perform this task, showing human-level performance.
DOI: 10.1002/mp.13464
发表时间: 2019-05-01
期刊: MEDICAL PHYSICS
影响因子: 3.8
作者:
Freiman, Moti;Manjeshwar, Ravindra;Goshen, Liran
通讯作者: Goshen, Liran
DOI: 10.1186/s12933-019-0917-y
发表时间: 2019-08-30
影响因子: 9.3
作者:
Christensen, Regitse H.;von Scholten, Bernt Johan;Jorgensen, Peter G.
通讯作者: Jorgensen, Peter G.
DOI: 10.1016/0735-1097(90)90282-t
发表时间: 1990-03-15
影响因子: 24
作者:
AGATSTON, AS;JANOWITZ, WR;DETRANO, R
通讯作者: DETRANO, R
DOI: 10.1001/jama.2012.5521
发表时间: 2012-06-13
影响因子: 120.7
作者:
Bach, Peter B.;Mirkin, Joshua N.;Oliver, Thomas K.;Azzoli, Christopher G.;Berry, Donald A.;Brawley, Otis W.;Byers, Tim;Colditz, Graham A.;Gould, Michael K.;Jett, James R.;Sabichi, Anita L.;Smith-Bindman, Rebecca;Wood, Douglas E.;Qaseem, Amir;Detterbeck, Frank C.
通讯作者: Detterbeck, Frank C.
DOI: 10.1148/radiol.15142062
发表时间: 2015-07
期刊: Radiology
影响因子: 19.7
作者:
Chiles C;Duan F;Gladish GW;Ravenel JG;Baginski SG;Snyder BS;DeMello S;Desjardins SS;Munden RF;NLST Study Team
通讯作者: NLST Study Team