Journal article
Deep Learning for Prediction of Obstructive Disease From Fast Myocardial Perfusion SPECT: A Multicenter Study.
- Betancur J Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Commandeur F Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Motlagh M Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Sharir T Department of Nuclear Cardiology, Assuta Medical Centers, Tel Aviv, Israel; Ben Gurion University of the Negev, Beer Sheba, Israel.
- Einstein AJ Division of Cardiology, Department of Medicine, Columbia University Medical Center and New York-Presbyterian Hospital, New York, New York; Department of Radiology, Columbia University Medical Center and New York-Presbyterian Hospital, New York, New York.
- Bokhari S Division of Cardiology, Department of Medicine, Columbia University Medical Center and New York-Presbyterian Hospital, New York, New York.
- Fish MB Oregon Heart and Vascular Institute, Sacred Heart Medical Center, Springfield, Oregon.
- Ruddy TD Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Canada.
- Kaufmann P Department of Nuclear Medicine, Cardiac Imaging, University Hospital Zurich, Zurich, Switzerland.
- Sinusas AJ Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, Connecticut.
- Miller EJ Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, Connecticut.
- Bateman TM Cardiovascular Imaging Technologies LLC, Kansas City, Missouri.
- Dorbala S Department of Radiology, Division of Nuclear Medicine and Molecular Imaging, Brigham and Women's Hospital, Boston, Massachusetts.
- Di Carli M Department of Radiology, Division of Nuclear Medicine and Molecular Imaging, Brigham and Women's Hospital, Boston, Massachusetts.
- Germano G Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Otaki Y Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Tamarappoo BK Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Dey D Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Berman DS Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
- Slomka PJ Department of Imaging (Division of Nuclear Medicine), Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California. Electronic address: piotr.slomka@cshs.org.
- 2018-03-19
Published in:
- JACC. Cardiovascular imaging. - 2018
SPECT myocardial perfusion imaging
convolutional neural network
deep learning
obstructive coronary artery disease
Aged
Aged, 80 and over
Coronary Circulation
Coronary Stenosis
Deep Learning
Female
Humans
Image Interpretation, Computer-Assisted
Male
Middle Aged
Myocardial Perfusion Imaging
Organophosphorus Compounds
Organotechnetium Compounds
Predictive Value of Tests
Radiopharmaceuticals
Registries
Technetium Tc 99m Sestamibi
Tomography, Emission-Computed, Single-Photon
English
OBJECTIVES
The study evaluated the automatic prediction of obstructive disease from myocardial perfusion imaging (MPI) by deep learning as compared with total perfusion deficit (TPD).
BACKGROUND
Deep convolutional neural networks trained with a large multicenter population may provide improved prediction of per-patient and per-vessel coronary artery disease from single-photon emission computed tomography MPI.
METHODS
A total of 1,638 patients (67% men) without known coronary artery disease, undergoing stress 99mTc-sestamibi or tetrofosmin MPI with new generation solid-state scanners in 9 different sites, with invasive coronary angiography performed within 6 months of MPI, were studied. Obstructive disease was defined as ≥70% narrowing of coronary arteries (≥50% for left main artery). Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. Stress TPD was computed using sex- and camera-specific normal limits. Deep learning was trained using raw and quantitative polar maps and evaluated for prediction of obstructive stenosis in a stratified 10-fold cross-validation procedure.
RESULTS
A total of 1,018 (62%) patients and 1,797 of 4,914 (37%) arteries had obstructive disease. Area under the receiver-operating characteristic curve for disease prediction by deep learning was higher than for TPD (per patient: 0.80 vs. 0.78; per vessel: 0.76 vs. 0.73: p < 0.01). With deep learning threshold set to the same specificity as TPD, per-patient sensitivity improved from 79.8% (TPD) to 82.3% (deep learning) (p < 0.05), and per-vessel sensitivity improved from 64.4% (TPD) to 69.8% (deep learning) (p < 0.01).
CONCLUSIONS
Deep learning has the potential to improve automatic interpretation of MPI as compared with current clinical methods.
The study evaluated the automatic prediction of obstructive disease from myocardial perfusion imaging (MPI) by deep learning as compared with total perfusion deficit (TPD).
BACKGROUND
Deep convolutional neural networks trained with a large multicenter population may provide improved prediction of per-patient and per-vessel coronary artery disease from single-photon emission computed tomography MPI.
METHODS
A total of 1,638 patients (67% men) without known coronary artery disease, undergoing stress 99mTc-sestamibi or tetrofosmin MPI with new generation solid-state scanners in 9 different sites, with invasive coronary angiography performed within 6 months of MPI, were studied. Obstructive disease was defined as ≥70% narrowing of coronary arteries (≥50% for left main artery). Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. Stress TPD was computed using sex- and camera-specific normal limits. Deep learning was trained using raw and quantitative polar maps and evaluated for prediction of obstructive stenosis in a stratified 10-fold cross-validation procedure.
RESULTS
A total of 1,018 (62%) patients and 1,797 of 4,914 (37%) arteries had obstructive disease. Area under the receiver-operating characteristic curve for disease prediction by deep learning was higher than for TPD (per patient: 0.80 vs. 0.78; per vessel: 0.76 vs. 0.73: p < 0.01). With deep learning threshold set to the same specificity as TPD, per-patient sensitivity improved from 79.8% (TPD) to 82.3% (deep learning) (p < 0.05), and per-vessel sensitivity improved from 64.4% (TPD) to 69.8% (deep learning) (p < 0.01).
CONCLUSIONS
Deep learning has the potential to improve automatic interpretation of MPI as compared with current clinical methods.
- Language
-
- English
- Open access status
- bronze
- Identifiers
-
- DOI 10.1016/j.jcmg.2018.01.020
- PMID 29550305
- Persistent URL
- https://sonar.ch/global/documents/47489
Export to…
Statistics
Document views: 130
File downloads: