Yuka Otaki1, Ananya Singh1, Paul Kavanagh1, Robert J H Miller2, Tejas Parekh1, Balaji K Tamarappoo1, Tali Sharir3, Andrew J Einstein4, Mathews B Fish5, Terrence D Ruddy6, Philipp A Kaufmann7, Albert J Sinusas8, Edward J Miller8, Timothy M Bateman9, Sharmila Dorbala10, Marcelo Di Carli10, Sebastien Cadet1, Joanna X Liang1, Damini Dey1, Daniel S Berman1, Piotr J Slomka11. 1. Department of Imaging (Division of Nuclear Medicine), Medicine (Division of Artificial Intelligence in Medicine), and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USA. 2. Department of Imaging (Division of Nuclear Medicine), Medicine (Division of Artificial Intelligence in Medicine), and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USA; Department of Cardiac Sciences, University of Calgary, Calgary, Alberta, Canada. 3. Department of Nuclear Cardiology, Assuta Medical Centers, Tel Aviv, Israel, and Ben Gurion University of the Negev, Beer Sheba, Israel. 4. Division of Cardiology, Departments of Medicine and Radiology, Columbia University Irving Medical Center and New York-Presbyterian Hospital, New York, New York, USA. 5. Oregon Heart and Vascular Institute, Sacred Heart Medical Center, Springfield, Oregon, USA. 6. Division of Cardiology, University of Ottawa Heart Institute, Ottawa, Ontario, Canada. 7. Department of Nuclear Medicine, Cardiac Imaging, University Hospital Zurich, Zurich, Switzerland. 8. Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, Connecticut, USA. 9. Cardiovascular Imaging Technologies, LLC, Kansas City, Missouri, USA. 10. Department of Radiology, Division of Nuclear Medicine and Molecular Imaging, Brigham and Women's Hospital, Boston, Massachusetts, USA. 11. Department of Imaging (Division of Nuclear Medicine), Medicine (Division of Artificial Intelligence in Medicine), and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California, USA. Electronic address: Piotr.Slomka@cshs.org.
Abstract
BACKGROUND: Explainable artificial intelligence (AI) can be integrated within standard clinical software to facilitate the acceptance of the diagnostic findings during clinical interpretation. OBJECTIVES: This study sought to develop and evaluate a novel, general purpose, explainable deep learning model (coronary artery disease-deep learning [CAD-DL]) for the detection of obstructive CAD following single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). METHODS: A total of 3,578 patients with suspected CAD undergoing SPECT MPI and invasive coronary angiography within a 6-month interval from 9 centers were studied. CAD-DL computes the probability of obstructive CAD from stress myocardial perfusion, wall motion, and wall thickening maps, as well as left ventricular volumes, age, and sex. Myocardial regions contributing to the CAD-DL prediction are highlighted to explain the findings to the physician. A clinical prototype was integrated using a standard clinical workstation. Diagnostic performance by CAD-DL was compared to automated quantitative total perfusion deficit (TPD) and reader diagnosis. RESULTS: In total, 2,247 patients (63%) had obstructive CAD. In 10-fold repeated testing, the area under the receiver-operating characteristic curve (AUC) (95% CI) was higher according to CAD-DL (AUC: 0.83 [95% CI: 0.82-0.85]) than stress TPD (AUC: 0.78 [95% CI: 0.77-0.80]) or reader diagnosis (AUC: 0.71 [95% CI: 0.69-0.72]; P < 0.0001 for both). In external testing, the AUC in 555 patients was higher according to CAD-DL (AUC: 0.80 [95% CI: 0.76-0.84]) than stress TPD (AUC: 0.73 [95% CI: 0.69-0.77]) or reader diagnosis (AUC: 0.65 [95% CI: 0.61-0.69]; P < 0.001 for all). The present model can be integrated within standard clinical software and generates results rapidly (<12 seconds on a standard clinical workstation) and therefore could readily be incorporated into a typical clinical workflow. CONCLUSIONS: The deep-learning model significantly surpasses the diagnostic accuracy of standard quantitative analysis and clinical visual reading for MPI. Explainable artificial intelligence can be integrated within standard clinical software to facilitate acceptance of artificial intelligence diagnosis of CAD following MPI.
BACKGROUND: Explainable artificial intelligence (AI) can be integrated within standard clinical software to facilitate the acceptance of the diagnostic findings during clinical interpretation. OBJECTIVES: This study sought to develop and evaluate a novel, general purpose, explainable deep learning model (coronary artery disease-deep learning [CAD-DL]) for the detection of obstructive CAD following single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). METHODS: A total of 3,578 patients with suspected CAD undergoing SPECT MPI and invasive coronary angiography within a 6-month interval from 9 centers were studied. CAD-DL computes the probability of obstructive CAD from stress myocardial perfusion, wall motion, and wall thickening maps, as well as left ventricular volumes, age, and sex. Myocardial regions contributing to the CAD-DL prediction are highlighted to explain the findings to the physician. A clinical prototype was integrated using a standard clinical workstation. Diagnostic performance by CAD-DL was compared to automated quantitative total perfusion deficit (TPD) and reader diagnosis. RESULTS: In total, 2,247 patients (63%) had obstructive CAD. In 10-fold repeated testing, the area under the receiver-operating characteristic curve (AUC) (95% CI) was higher according to CAD-DL (AUC: 0.83 [95% CI: 0.82-0.85]) than stress TPD (AUC: 0.78 [95% CI: 0.77-0.80]) or reader diagnosis (AUC: 0.71 [95% CI: 0.69-0.72]; P < 0.0001 for both). In external testing, the AUC in 555 patients was higher according to CAD-DL (AUC: 0.80 [95% CI: 0.76-0.84]) than stress TPD (AUC: 0.73 [95% CI: 0.69-0.77]) or reader diagnosis (AUC: 0.65 [95% CI: 0.61-0.69]; P < 0.001 for all). The present model can be integrated within standard clinical software and generates results rapidly (<12 seconds on a standard clinical workstation) and therefore could readily be incorporated into a typical clinical workflow. CONCLUSIONS: The deep-learning model significantly surpasses the diagnostic accuracy of standard quantitative analysis and clinical visual reading for MPI. Explainable artificial intelligence can be integrated within standard clinical software to facilitate acceptance of artificial intelligence diagnosis of CAD following MPI.
Authors: Piotr J Slomka; Hidetaka Nishina; Daniel S Berman; Cigdem Akincioglu; Aiden Abidov; John D Friedman; Sean W Hayes; Guido Germano Journal: J Nucl Cardiol Date: 2005 Jan-Feb Impact factor: 5.952
Authors: Sharmila Dorbala; Karthik Ananthasubramaniam; Ian S Armstrong; Panithaya Chareonthaitawee; E Gordon DePuey; Andrew J Einstein; Robert J Gropler; Thomas A Holly; John J Mahmarian; Mi-Ae Park; Donna M Polk; Raymond Russell; Piotr J Slomka; Randall C Thompson; R Glenn Wells Journal: J Nucl Cardiol Date: 2018-10 Impact factor: 5.952
Authors: Yuka Otaki; Julian Betancur; Tali Sharir; Lien-Hsin Hu; Heidi Gransar; Joanna X Liang; Peyman N Azadani; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo Di Carli; Balaji K Tamarappoo; Guido Germano; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: JACC Cardiovasc Imaging Date: 2019-06-12
Authors: Piotr J Slomka; Julian Betancur; Joanna X Liang; Yuka Otaki; Lien-Hsin Hu; Tali Sharir; Sharmila Dorbala; Marcelo Di Carli; Mathews B Fish; Terrence D Ruddy; Timothy M Bateman; Andrew J Einstein; Philipp A Kaufmann; Edward J Miller; Albert J Sinusas; Peyman N Azadani; Heidi Gransar; Balaji K Tamarappoo; Damini Dey; Daniel S Berman; Guido Germano Journal: J Nucl Cardiol Date: 2018-06-19 Impact factor: 5.952
Authors: Lien-Hsin Hu; Robert J H Miller; Tali Sharir; Frederic Commandeur; Richard Rios; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo Di Carli; Joanna X Liang; Evann Eisenberg; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: Eur Heart J Cardiovasc Imaging Date: 2021-05-10 Impact factor: 6.875
Authors: Christopher J Kelly; Alan Karthikesalingam; Mustafa Suleyman; Greg Corrado; Dominic King Journal: BMC Med Date: 2019-10-29 Impact factor: 8.775
Authors: Robert J H Miller; Ananya Singh; Yuka Otaki; Balaji K Tamarappoo; Paul Kavanagh; Tejas Parekh; Lien-Hsin Hu; Heidi Gransar; Tali Sharir; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo F Di Carli; Joanna X Liang; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: Eur J Nucl Med Mol Imaging Date: 2022-10-04 Impact factor: 10.057