Deep Learning for Prediction of Obstructive Disease from Fast Myocardial Perfusion SPECT: A Multicenter Study

By J. Betancur, F. Commandeur, M. Motlagh, T. Sharir, A. Einstein, S. Bokhari, M. Fish, T. Ruddy, P. Kaufmann, A. Sinusas and 10 more. JACC Cardiovascular Imaging, 2018

303 citations recorded by the source corpus.

Objectives We evaluated the automatic prediction of obstructive disease from myocardial perfusion imaging (MPI) by deep learning as compared to total perfusion deficit (TPD). Background Deep convolutional neural networks trained with large multi-center population may provide improved prediction of per-patient and per-vessel coronary artery disease (CAD) from SPECT MPI. Methods 1638 patients (67% males) without known CAD, 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). Left ventricular (LV) myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. Stress TPD was computed using gender- 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 1018 (62%) patients and 1797 out of 4914 (37%) arteries had obstructive disease. Area under the receiver operating characteristics curve (AUC) 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 to current clinical methods.

Subfields: Cardiology and Cardiovascular Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/4795ae67713de1ed0f890d17105687fa10e518cf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cardiology and Cardiovascular Medicine

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2021, background): “vided state-of-the-art performance for various healthcare tasks including medical image reconstruction [1], management of electronic health records [2], cancer segmentation [3], disease prediction [4], clinical imaging [5], image retrieval [6], and computational biology [7].”
Deep learning for cardiovascular medicine: a practical primer. (2019, methodology): “56 applied DL to single-photon emission computed tomography myocardial perfusion imaging in 2619 consecutive patients at exercise (38”
Artificial intelligence in medical education (2019, background): “Already, computers can perform prediction and diagnosis better than humans (Bogu (cid:1) sevi (cid:1) cius et al. 2002; Esteva et al. 2017; Litjens et al. 2017; Mobadersany et al. 2017; Betancur et al. 2018; De Fauw et al. 2018; Haenssle et al. 2018).”
Artificial Intelligence in Cardiovascular Imaging (2019, methodology): “Betancur et al. (82) used 1,638 SPECT MPIs from the REFINE SPECT registry, and obtained by the latest-generation SPECT cameras, in patients with suspected coronary artery disease (82) to train and validate a DL system for automatic detection of angiographically significant disease from SPECT MPI.”
Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging. (2018, methodology): “In further efforts to improve fully automatic image analysis, deep learning has been applied directly to nuclear cardiology polar map images in a large multi-centre multi-national study (1638 patients) by Betancur et al. 65 They demonstrated that deep learning could outperform current clinical stand”