Coronary artery disease (CAD) continues to be a major public health problem. It is the single greatest cause of death for men and women in the US, accounting for 20% of all deaths. While there are effective medical and invasive therapies for CAD, their appropriate use is dependent on accurate detection of the disease and evaluation of cardiac risk in individual patients. Gated myocardial perfusion SPECT (MRS) has played a critical role in this process, providing key information about myocardial perfusion and ventricular function. Over 8 million patients underwent MRS in the US in 2005. Currently, the standard method for MRS interpretation is subjective visual scoring of regional myocardial uptake of perfusion at stress and rest. This visual approach is time-consuming, suffers from inter-observer variability, and is potentially sub-optimal in the detection of abnormalities and estimation of their magnitude.
We aim to develop a fully automated computer system for MRS that will surpass the performance of experienced human readers in diagnosing CAD and in predicting cardiac events. This high level of performance will be accomplished by the application of new image processing techniques, improvement of image quality, and automatic regional integration of all available image data. Specifically, we aim to: 1) develop enhanced techniques for perfusion quantification, 2) develop new techniques for quantification of attenuation corrected MRS, and 3) validate performance of the final integrated system diagnostically by comparison to the visual evaluation by multiple experts in a large multi-center study and prognostically by retrospective analysis of a large outcome database. The new system will have the ability to distinguish true abnormalities from imaging artifacts and will detect subtle defects. We hypothesize that the new system will be able to detect CAD and predict outcomes such as cardiac death better than the best attainable visual analysis. Such development will have far-reaching and immediate consequences since this new level of accuracy and automation for MRS can be widely reproduced nationally and internationally. This work will result in increased efficiency of MRS testing and large cost savings due to more accurate diagnosis of CAD and better selection of appropriate treatment. Imaging of myocardial perfusion (heart muscle blood flow) at rest and stress allows physicians to detect disease and predict risk in millions of patients in the US each year, but it is currently limited by the need of visual interpretation, which is dependent on doctor's experience. The investigators propose to develop and validate an automated, highly-accurate and objective computer system which will outperform even experienced physicians in interpreting these images and consequently allow a greater number of lives saved by better selection of patients needing treatment and also resulting in time- and cost-savings. ? ? ?

National Institute of Health (NIH)
National Heart, Lung, and Blood Institute (NHLBI)
Research Project (R01)
Project #
Application #
Study Section
Biomedical Imaging Technology Study Section (BMIT)
Program Officer
Buxton, Denis B
Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
Cedars-Sinai Medical Center
Los Angeles
United States
Zip Code
Betancur, Julian A; Hu, Lien-Hsin; Commandeur, Frederic et al. (2018) Deep Learning Analysis of Upright-Supine High-Efficiency SPECT Myocardial Perfusion Imaging for Prediction of Obstructive Coronary Artery Disease: A Multicenter Study. J Nucl Med :
Haro Alonso, David; Wernick, Miles N; Yang, Yongyi et al. (2018) Prediction of cardiac death after adenosine myocardial perfusion SPECT based on machine learning. J Nucl Cardiol :
Slomka, Piotr J; Betancur, Julian; Liang, Joanna X et al. (2018) Rationale and design of the REgistry of Fast Myocardial Perfusion Imaging with NExt generation SPECT (REFINE SPECT). J Nucl Cardiol :
Sharif, Behzad; Motwani, Manish; Arsanjani, Reza et al. (2018) Impact of incomplete ventricular coverage on diagnostic performance of myocardial perfusion imaging. Int J Cardiovasc Imaging 34:661-669
Betancur, Julian; Otaki, Yuka; Motwani, Manish et al. (2018) Prognostic Value of Combined Clinical and Myocardial Perfusion Imaging Data Using Machine Learning. JACC Cardiovasc Imaging 11:1000-1009
Motwani, Manish; Leslie, William D; Goertzen, Andrew L et al. (2018) Fully automated analysis of attenuation-corrected SPECT for the long-term prediction of acute myocardial infarction. J Nucl Cardiol 25:1353-1360
Gomez, Javier; Doukky, Rami; Germano, Guido et al. (2018) New Trends in Quantitative Nuclear Cardiology Methods. Curr Cardiovasc Imaging Rep 11:
Betancur, Julian; Commandeur, Frederic; Motlagh, Mahsaw et al. (2018) Deep Learning for Prediction of Obstructive Disease From Fast Myocardial Perfusion SPECT: A Multicenter Study. JACC Cardiovasc Imaging 11:1654-1663
Išgum, Ivana; de Vos, Bob D; Wolterink, Jelmer M et al. (2018) Automatic determination of cardiovascular risk by CT attenuation correction maps in Rb-82 PET/CT. J Nucl Cardiol 25:2133-2142
Chaudhry, Waseem; Hussain, Nasir; Ahlberg, Alan W et al. (2017) Multicenter evaluation of stress-first myocardial perfusion image triage by nuclear technologists and automated quantification. J Nucl Cardiol 24:809-820

Showing the most recent 10 out of 67 publications