Literature DB >> 36194270

Mitigating bias in deep learning for diagnosis of coronary artery disease from myocardial perfusion SPECT images.

Robert J H Miller1,2, Ananya Singh1, Yuka Otaki1, Balaji K Tamarappoo1, Paul Kavanagh1, Tejas Parekh1, Lien-Hsin Hu1,3, Heidi Gransar1, Tali Sharir4, Andrew J Einstein5, Mathews B Fish6, Terrence D Ruddy7, Philipp A Kaufmann8, Albert J Sinusas9, Edward J Miller9, Timothy M Bateman10, Sharmila Dorbala11, Marcelo F Di Carli11, Joanna X Liang1, Damini Dey1, Daniel S Berman1, Piotr J Slomka12.   

Abstract

PURPOSE: Artificial intelligence (AI) has high diagnostic accuracy for coronary artery disease (CAD) from myocardial perfusion imaging (MPI). However, when trained using high-risk populations (such as patients with correlating invasive testing), the disease probability can be overestimated due to selection bias. We evaluated different strategies for training AI models to improve the calibration (accurate estimate of disease probability), using external testing.
METHODS: Deep learning was trained using 828 patients from 3 sites, with MPI and invasive angiography within 6 months. Perfusion was assessed using upright (U-TPD) and supine total perfusion deficit (S-TPD). AI training without data augmentation (model 1) was compared to training with augmentation (increased sampling) of patients without obstructive CAD (model 2), and patients without CAD and TPD < 2% (model 3). All models were tested in an external population of patients with invasive angiography within 6 months (n = 332) or low likelihood of CAD (n = 179).
RESULTS: Model 3 achieved the best calibration (Brier score 0.104 vs 0.121, p < 0.01). Improvement in calibration was particularly evident in women (Brier score 0.084 vs 0.124, p < 0.01). In external testing (n = 511), the area under the receiver operating characteristic curve (AUC) was higher for model 3 (0.930), compared to U-TPD (AUC 0.897) and S-TPD (AUC 0.900, p < 0.01 for both).
CONCLUSION: Training AI models with augmentation of low-risk patients can improve calibration of AI models developed to identify patients with CAD, allowing more accurate assignment of disease probability. This is particularly important in lower-risk populations and in women, where overestimation of disease probability could significantly influence down-stream patient management.
© 2022. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Entities:  

Keywords:  Calibration; Deep learning; Diagnostic accuracy; Model training; Sex-specific analysis

Year:  2022        PMID: 36194270     DOI: 10.1007/s00259-022-05972-w

Source DB:  PubMed          Journal:  Eur J Nucl Med Mol Imaging        ISSN: 1619-7070            Impact factor:   10.057


  15 in total

1.  Calibration of risk prediction models: impact on decision-analytic performance.

Authors:  Ben Van Calster; Andrew J Vickers
Journal:  Med Decis Making       Date:  2014-08-25       Impact factor: 2.583

2.  Automated quantification of myocardial perfusion SPECT using simplified normal limits.

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

3.  A novel high-sensitivity rapid-acquisition single-photon cardiac imaging camera.

Authors:  Sanjiv S Gambhir; Daniel S Berman; Jack Ziffer; Michael Nagler; Martin Sandler; Jim Patton; Brian Hutton; Tali Sharir; Shlomo Ben Haim; Simona Ben Haim
Journal:  J Nucl Med       Date:  2009-04       Impact factor: 10.057

Review 4.  Single Photon Emission Computed Tomography (SPECT) Myocardial Perfusion Imaging Guidelines: Instrumentation, Acquisition, Processing, and Interpretation.

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

5.  Deep Learning Analysis of Upright-Supine High-Efficiency SPECT Myocardial Perfusion Imaging for Prediction of Obstructive Coronary Artery Disease: A Multicenter Study.

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

6.  Cardiovascular disease in Europe: epidemiological update 2016.

Authors:  Nick Townsend; Lauren Wilson; Prachi Bhatnagar; Kremlin Wickramasinghe; Mike Rayner; Melanie Nichols
Journal:  Eur Heart J       Date:  2016-08-14       Impact factor: 29.983

7.  Upper reference limits of transient ischemic dilation ratio for different protocols on new-generation cadmium zinc telluride cameras: A report from REFINE SPECT registry.

Authors:  Lien-Hsin Hu; Tali Sharir; Robert J H Miller; Andrew J Einstein; Mathews B Fish; Terrence D Ruddy; Sharmila Dorbala; Marcelo Di Carli; Philipp A Kaufmann; Albert J Sinusas; Edward J Miller; Timothy M Bateman; Julian Betancur; Guido Germano; Joanna X Liang; Frederic Commandeur; Peyman N Azadani; Heidi Gransar; Yuka Otaki; Balaji K Tamarappoo; Damini Dey; Daniel S Berman; Piotr J Slomka
Journal:  J Nucl Cardiol       Date:  2019-05-13       Impact factor: 5.952

8.  Deep Learning for Prediction of Obstructive Disease From Fast Myocardial Perfusion SPECT: A Multicenter Study.

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

9.  Calibration: the Achilles heel of predictive analytics.

Authors:  Ben Van Calster; David J McLernon; Maarten van Smeden; Laure Wynants; Ewout W Steyerberg
Journal:  BMC Med       Date:  2019-12-16       Impact factor: 8.775

10.  Clinical Deployment of Explainable Artificial Intelligence of SPECT for Diagnosis of Coronary Artery Disease.

Authors:  Yuka Otaki; Ananya Singh; Paul Kavanagh; Robert J H Miller; Tejas Parekh; Balaji K Tamarappoo; 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; Sebastien Cadet; Joanna X Liang; Damini Dey; Daniel S Berman; Piotr J Slomka
Journal:  JACC Cardiovasc Imaging       Date:  2021-07-14
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.