A Deep Learning Approach to Using Wearable Seismocardiography (SCG) for Diagnosing Aortic Valve Stenosis and Predicting Aortic Hemodynamics Obtained by 4D Flow MRI

被引:2
作者
Ebrahimkhani, Mahmoud [1 ]
Johnson, Ethan M. I. [1 ]
Sodhi, Aparna [2 ]
Robinson, Joshua D. [1 ,2 ,3 ]
Rigsby, Cynthia K. [1 ,2 ,3 ]
Allen, Bradly D. [1 ]
Markl, Michael [1 ,4 ]
机构
[1] Northwestern Univ, Feinberg Sch Med, Dept Radiol, Chicago, IL 60611 USA
[2] Ann & Robert H Lurie Childrens Hosp, Chicago, IL 60611 USA
[3] Northwestern Univ, Feinberg Sch Med, Dept Pediat, Chicago, IL 60611 USA
[4] Northwestern Univ, McCormick Sch Engn, Dept Biomed Engn, Evanston, IL 60208 USA
关键词
4D flow MRI; Cardiac MRI; Convolutional neural networks (CNN); Continuous wavelet transform (CWT); Deep learning; Seismocardiography (SCG); WALL SHEAR-STRESS; BLOOD-FLOW; CONTRAST; QUANTIFICATION; TIME; HEART; VELOCITY;
D O I
10.1007/s10439-023-03342-7
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
In this paper, we explored the use of deep learning for the prediction of aortic flow metrics obtained using 4-dimensional (4D) flow magnetic resonance imaging (MRI) using wearable seismocardiography (SCG) devices. 4D flow MRI provides a comprehensive assessment of cardiovascular hemodynamics, but it is costly and time-consuming. We hypothesized that deep learning could be used to identify pathological changes in blood flow, such as elevated peak systolic velocity ( V max) in patients with heart valve diseases, from SCG signals. We also investigated the ability of this deep learning technique to differentiate between patients diagnosed with aortic valve stenosis (AS), non-AS patients with a bicuspid aortic valve (BAV), non-AS patients with a mechanical aortic valve (MAV), and healthy subjects with a normal tricuspid aortic valve (TAV). In a study of 77 subjects who underwent same-day 4D flow MRI and SCG, we found that the V max values obtained using deep learning and SCGs were in good agreement with those obtained by 4D flow MRI. Additionally, subjects with non-AS TAV, non-AS BAV, non-AS MAV, and AS could be classified with ROC-AUC (area under the receiver operating characteristic curves) values of 92%, 95%, 81%, and 83%, respectively. This suggests that SCG obtained using low-cost wearable electronics may be used as a supplement to 4D flow MRI exams or as a screening tool for aortic valve disease.
引用
收藏
页码:2802 / 2811
页数:10
相关论文
共 63 条
[1]   Four-dimensional Flow MRI: Principles and Cardiovascular Applications [J].
Azarine, Arshid ;
Garcon, Philippe ;
Stansal, Audrey ;
Canepa, Nadia ;
Angelopoulos, Giorgios ;
Silvera, Stephane ;
Sidi, Daniel ;
Marteau, Veronique ;
Zins, Marc .
RADIOGRAPHICS, 2019, 39 (03) :632-+
[2]   Four-Dimensional Flow Assessment of Pulmonary Artery Flow and Wall Shear Stress in Adult Pulmonary Arterial Hypertension: Results from Two Institutions [J].
Barker, Alex J. ;
Roldan-Alzate, Alejandro ;
Entezari, Pegah ;
Shah, Sanjiv J. ;
Chesler, Naomi C. ;
Wieben, Oliver ;
Markl, Michael ;
Francois, Christopher J. .
MAGNETIC RESONANCE IN MEDICINE, 2015, 73 (05) :1904-1913
[3]  
Becker M, 2014, HERZ, V39, P586, DOI 10.1007/s00059-013-3851-x
[4]   Fully automated 3D aortic segmentation of 4D flow MRI for hemodynamic analysis using deep learning [J].
Berhane, Haben ;
Scott, Michael ;
Elbaz, Mohammed ;
Jarvis, Kelly ;
McCarthy, Patrick ;
Carr, James ;
Malaisrie, Chris ;
Avery, Ryan ;
Barker, Alex J. ;
Robinson, Joshua D. ;
Rigsby, Cynthia K. ;
Markl, Michael .
MAGNETIC RESONANCE IN MEDICINE, 2020, 84 (04) :2204-2218
[5]   Wearable seismocardiography [J].
Castiglioni, Paolo ;
Faini, Andrea ;
Parati, Gianfranco ;
Di Rienzo, Marco .
2007 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-16, 2007, :3954-3957
[6]   Respiratory Rate Estimation Using U-Net-Based Cascaded Framework From Electrocardiogram and Seismocardiogram Signals [J].
Chan, Michael ;
Ganti, Venu G. ;
Inan, Omer T. .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2022, 26 (06) :2481-2492
[7]   Automatic Detection of Aortic Valve Opening Using Seismocardiography in Healthy Individuals [J].
Choudhary, Tilendra ;
Sharma, L. N. ;
Bhuyan, M. K. .
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2019, 23 (03) :1032-1040
[8]   A new imaging method for assessment of aortic dissection using four-dimensional phase contrast magnetic resonance imaging [J].
Clough, Rachel E. ;
Waltham, Matthew ;
Giese, Daniel ;
Taylor, Peter R. ;
Schaeffter, Tobias .
JOURNAL OF VASCULAR SURGERY, 2012, 55 (04) :914-923
[9]   Wearable seismocardiography: Towards a beat-by-beat assessment of cardiac mechanics in ambulant subjects [J].
Di Rienzo, M. ;
Vaini, E. ;
Castiglioni, P. ;
Merati, G. ;
Meriggi, P. ;
Parati, G. ;
Faini, A. ;
Rizzo, F. .
AUTONOMIC NEUROSCIENCE-BASIC & CLINICAL, 2013, 178 (1-2) :50-59
[10]   4D flow cardiovascular magnetic resonance consensus statement [J].
Dyverfeldt, Petter ;
Bissell, Malenka ;
Barker, Alex J. ;
Bolger, Ann F. ;
Carlhall, Carl-Johan ;
Ebbers, Tino ;
Francios, Christopher J. ;
Frydrychowicz, Alex ;
Geiger, Julia ;
Giese, Daniel ;
Hope, Michael D. ;
Kilner, Philip J. ;
Kozerke, Sebastian ;
Myerson, Saul ;
Neubauer, Stefan ;
Wieben, Oliver ;
Markl, Michael .
JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE, 2015, 17