Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images

doi:10.1007/s00330-020-07454-9

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中国科学院分子影像重点实验室

	Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images
	Zhou, Hongyu 2,5,6; Li, Lu 1; Liu, Zhenyu 2,5; Zhao, Kankan 6; Chen, Xiuyu 1; Lu, Minjie 1; Yin, Gang 1; Song, Lei 7; Zhao, Shihua 1; Zheng, Hairong 6
刊名	EUROPEAN RADIOLOGY
	2020-11-25
页码	10
关键词	Cardiomyopathy hypertrophic Genotype Deep learning Magnetic resonance imaging
ISSN号	0938-7994
DOI	10.1007/s00330-020-07454-9
通讯作者	Zhao, Shihua(cjrzhaoshihua2009@163.com) ; Tian, Jie(jie.tian@ia.ac.cn)
英文摘要	Objectives The high variability of hypertrophic cardiomyopathy (HCM) genetic phenotypes has prompted the establishment of risk-stratification systems that predict the risk of a positive genetic mutation based on clinical and echocardiographic profiles. This study aims to improve mutation-risk prediction by extracting cardiovascular magnetic resonance (CMR) morphological features using a deep learning algorithm. Methods We recruited 198 HCM patients (48% men, aged 47 +/- 13 years) and divided them into training (147 cases) and test (51 cases) sets based on different genetic testing institutions and CMR scan dates (2012, 2013, respectively). All patients underwent CMR examinations, HCM genetic testing, and an assessment of established genotype scores (Mayo Clinic score I, Mayo Clinic score II, and Toronto score). A deep learning (DL) model was developed to classify the HCM genotypes, based on a nonenhanced four-chamber view of cine images. Results The areas under the curve (AUCs) for the test set were Mayo Clinic score I (AUC: 0.64, sensitivity: 64.29%, specificity: 47.83%), Mayo Clinic score II (AUC: 0.70, sensitivity: 64.29%, specificity: 65.22%), Toronto score (AUC: 0.74, sensitivity: 75.00%, specificity: 56.52%), and DL model (AUC: 0.80, sensitivity: 85.71%, specificity: 69.57%). The combination of the DL and the Toronto score resulted in a significantly higher predictive performance (AUC = 0.84, sensitivity: 83.33%, specificity: 78.26%), compared with Mayo I (p = 006), Mayo II (p = 022), and Toronto score (p = 0.029). Conclusions The combination of the DL model, based on nonenhanced cine CMR images and the Toronto score yielded significantly higher diagnostic performance in detecting HCM mutations.
资助项目	National Natural Science Foundation of China[81922040] ; National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81527805] ; National Natural Science Foundation of China[81772012] ; major international (regional) joint research project of National Science Foundation of China[81620108015] ; Beijing Natural Science Foundation[7182109] ; National Key Research and Development Plan of China[2017YFA0205200] ; National Key Research and Development Plan of China[2016YFA0100900] ; National Key Research and Development Plan of China[2016YFA0100902] ; Youth Innovation Promotion Association CAS[2019136]
WOS关键词	GENOTYPE-PHENOTYPE ASSOCIATIONS ; LOWER-GRADE GLIOMAS ; FEATURES PREDICT ; MRI FEATURES ; GENETICS ; GENES ; YIELD ; SCORE
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000592579000009
资助机构	National Natural Science Foundation of China ; major international (regional) joint research project of National Science Foundation of China ; Beijing Natural Science Foundation ; National Key Research and Development Plan of China ; Youth Innovation Promotion Association CAS
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/41663]
专题	自动化研究所_中国科学院分子影像重点实验室
通讯作者	Zhao, Shihua; Tian, Jie
作者单位	1.Chinese Acad Med Sci & Peking Union Med Coll, Dept Magnet Resonance Imaging, Fuwai Hosp, Natl Ctr Cardiovasc Dis China,State Key Lab Cardi, Beijing 100037, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100080, Peoples R China 3.Beihang Univ, Sch Med, Beijing Adv Innovat Ctr Big Data Based Precis Med, Beijing 100191, Peoples R China 4.Xidian Univ, Engn Res Ctr Mol & Neuro Imaging, Minist Educ, Sch Life Sci & Technol, Xian 710126, Peoples R China 5.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China 6.Chinese Acad Sci, Shenzhen Inst Adv Technol, Paul C Lauterbur Res Ctr Biomed Imaging, Shenzhen 518055, Peoples R China 7.Chinese Acad Med Sci, Dept Cardiol, Fuwai Hosp, Natl Ctr Cardiovasc Dis China, Beijing 100037, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Hongyu,Li, Lu,Liu, Zhenyu,et al. Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images[J]. EUROPEAN RADIOLOGY,2020:10.
APA	Zhou, Hongyu.,Li, Lu.,Liu, Zhenyu.,Zhao, Kankan.,Chen, Xiuyu.,...&Tian, Jie.(2020).Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images.EUROPEAN RADIOLOGY,10.
MLA	Zhou, Hongyu,et al."Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images".EUROPEAN RADIOLOGY (2020):10.