OBJECTIVE: We aimed to improve the diagnostic accuracy of myocardial perfusion SPECT (MPS) by integrating clinical data and quantitative image features with machine learning (ML) algorithms. METHODS: 1,181 rest (201)Tl/stress (99m)Tc-sestamibi dual-isotope MPS studies [713 consecutive cases with correlating invasive coronary angiography (ICA) and suspected coronary artery disease (CAD) and 468 with low likelihood (LLk) of CAD <5%] were considered. Cases with stenosis <70% by ICA and LLk of CAD were considered normal. Total stress perfusion deficit (TPD) for supine/prone data, stress/rest perfusion change, and transient ischemic dilatation were derived by automated perfusion quantification software and were combined with age, sex, and post-electrocardiogram CAD probability by a boosted ensemble ML algorithm (LogitBoost). The diagnostic accuracy of the model for prediction of obstructive CAD ≥70% was compared to standard prone/supine quantification and to visual analysis by two experienced readers utilizing all imaging, quantitative, and clinical data. Tenfold stratified cross-validation was performed. RESULTS: The diagnostic accuracy of ML (87.3% ± 2.1%) was similar to Expert 1 (86.0% ± 2.1%), but superior to combined supine/prone TPD (82.8% ± 2.2%) and Expert 2 (82.1% ± 2.2%) (P < .01). The receiver operator characteristic areas under curve for ML algorithm (0.94 ± 0.01) were higher than those for TPD and both visual readers (P < .001). The sensitivity of ML algorithm (78.9% ± 4.2%) was similar to TPD (75.6% ± 4.4%) and Expert 1 (76.3% ± 4.3%), but higher than that of Expert 2 (71.1% ± 4.6%), (P < .01). The specificity of ML algorithm (92.1% ± 2.2%) was similar to Expert 1 (91.4% ± 2.2%) and Expert 2 (88.3% ± 2.5%), but higher than TPD (86.8% ± 2.6%), (P < .01). CONCLUSION: ML significantly improves diagnostic performance of MPS by computational integration of quantitative perfusion and clinical data to the level rivaling expert analysis.
OBJECTIVE: We aimed to improve the diagnostic accuracy of myocardial perfusion SPECT (MPS) by integrating clinical data and quantitative image features with machine learning (ML) algorithms. METHODS: 1,181 rest (201)Tl/stress (99m)Tc-sestamibi dual-isotope MPS studies [713 consecutive cases with correlating invasive coronary angiography (ICA) and suspected coronary artery disease (CAD) and 468 with low likelihood (LLk) of CAD <5%] were considered. Cases with stenosis <70% by ICA and LLk of CAD were considered normal. Total stress perfusion deficit (TPD) for supine/prone data, stress/rest perfusion change, and transient ischemic dilatation were derived by automated perfusion quantification software and were combined with age, sex, and post-electrocardiogram CAD probability by a boosted ensemble ML algorithm (LogitBoost). The diagnostic accuracy of the model for prediction of obstructive CAD ≥70% was compared to standard prone/supine quantification and to visual analysis by two experienced readers utilizing all imaging, quantitative, and clinical data. Tenfold stratified cross-validation was performed. RESULTS: The diagnostic accuracy of ML (87.3% ± 2.1%) was similar to Expert 1 (86.0% ± 2.1%), but superior to combined supine/prone TPD (82.8% ± 2.2%) and Expert 2 (82.1% ± 2.2%) (P < .01). The receiver operator characteristic areas under curve for ML algorithm (0.94 ± 0.01) were higher than those for TPD and both visual readers (P < .001). The sensitivity of ML algorithm (78.9% ± 4.2%) was similar to TPD (75.6% ± 4.4%) and Expert 1 (76.3% ± 4.3%), but higher than that of Expert 2 (71.1% ± 4.6%), (P < .01). The specificity of ML algorithm (92.1% ± 2.2%) was similar to Expert 1 (91.4% ± 2.2%) and Expert 2 (88.3% ± 2.5%), but higher than TPD (86.8% ± 2.6%), (P < .01). CONCLUSION: ML significantly improves diagnostic performance of MPS by computational integration of quantitative perfusion and clinical data to the level rivaling expert analysis.
Authors: Hidetaka Nishina; Piotr J Slomka; Aiden Abidov; Shunichi Yoda; Cigdem Akincioglu; Xingping Kang; Ishac Cohen; Sean W Hayes; John D Friedman; Guido Germano; Daniel S Berman Journal: J Nucl Med Date: 2006-01 Impact factor: 10.057
Authors: Piotr J Slomka; Hidetaka Nishina; Aiden Abidov; Sean W Hayes; John D Friedman; Daniel S Berman; Guido Germano Journal: J Nucl Cardiol Date: 2007-01 Impact factor: 5.952
Authors: R J Golub; A W Ahlberg; J R McClellan; S D Herman; M I Travin; J F Mather; P W Aitken; J I Baron; G V Heller Journal: J Nucl Cardiol Date: 1999 May-Jun Impact factor: 5.952
Authors: E V Garcia; C D Cooke; R D Folks; C A Santana; E G Krawczynska; L De Braal; N F Ezquerra Journal: J Nucl Med Date: 2001-08 Impact factor: 10.057
Authors: Reza Arsanjani; Yuan Xu; Sean W Hayes; Mathews Fish; Mark Lemley; James Gerlach; Sharmila Dorbala; Daniel S Berman; Guido Germano; Piotr Slomka Journal: J Nucl Med Date: 2013-01-11 Impact factor: 10.057
Authors: Yuan Xu; Paul Kavanagh; Mathews Fish; James Gerlach; Amit Ramesh; Mark Lemley; Sean Hayes; Daniel S Berman; Guido Germano; Piotr J Slomka Journal: J Nucl Med Date: 2009-08-18 Impact factor: 10.057
Authors: D S Berman; X Kang; K F Van Train; H C Lewin; I Cohen; J Areeda; J D Friedman; G Germano; L J Shaw; R Hachamovitch Journal: J Am Coll Cardiol Date: 1998-12 Impact factor: 24.094
Authors: S R Underwood; C Anagnostopoulos; M Cerqueira; P J Ell; E J Flint; M Harbinson; A D Kelion; A Al-Mohammad; E M Prvulovich; L J Shaw; A C Tweddel Journal: Eur J Nucl Med Mol Imaging Date: 2004-02 Impact factor: 9.236
Authors: Luis Eduardo Juarez-Orozco; Remco J J Knol; Carlos A Sanchez-Catasus; Octavio Martinez-Manzanera; Friso M van der Zant; Juhani Knuuti Journal: J Nucl Cardiol Date: 2018-05-22 Impact factor: 5.952
Authors: Damini Dey; Piotr J Slomka; Paul Leeson; Dorin Comaniciu; Sirish Shrestha; Partho P Sengupta; Thomas H Marwick Journal: J Am Coll Cardiol Date: 2019-03-26 Impact factor: 24.094
Authors: Rine Nakanishi; Heidi Gransar; Piotr Slomka; Reza Arsanjani; Aryeh Shalev; Yuka Otaki; John D Friedman; Sean W Hayes; Louise E B Thomson; Mathews Fish; Guido Germano; Aiden Abidov; Leslee Shaw; Alan Rozanski; Daniel S Berman Journal: J Nucl Cardiol Date: 2015-05-14 Impact factor: 5.952
Authors: Julian Betancur; Lien-Hsin Hu; Frederic Commandeur; 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 Di Carli; Guido Germano; Yuka Otaki; Joanna X Liang; Balaji K Tamarappoo; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: J Nucl Med Date: 2018-09-27 Impact factor: 10.057
Authors: Julian Betancur; Frederic Commandeur; Mahsaw Motlagh; Tali Sharir; Andrew J Einstein; Sabahat Bokhari; Mathews B Fish; Terrence D Ruddy; Philipp Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Sharmila Dorbala; Marcelo Di Carli; Guido Germano; Yuka Otaki; Balaji K Tamarappoo; Damini Dey; Daniel S Berman; Piotr J Slomka Journal: JACC Cardiovasc Imaging Date: 2018-03-14
Authors: Reza Arsanjani; Sean W Hayes; Mathews Fish; Aryeh Shalev; Rine Nakanishi; Louise E J Thomson; John D Friedman; Guido Germano; Daniel S Berman; Piotr Slomka Journal: J Nucl Cardiol Date: 2014-05-08 Impact factor: 5.952