EUVIMEDEUVIMED entdecken
Open Access

Deep Learning Coronary Artery Calcium Scores from SPECT/CT Attenuation Maps Improve Prediction of Major Adverse Cardiac Events

Robert J H Miller, Konrad Pieszko, Aakash Shanbhag, Attila Feher, Mark Lemley, Aditya Killekar, Paul B Kavanagh, Serge D Van Kriekinge, Joanna X Liang, Cathleen Huang, Edward J Miller, Timothy Bateman und 3 weitere

Journal of Nuclear Medicine · 2023-04 · 64 (4) · 652-658

DOI: 10.2967/jnumed.122.264423 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Nuclear Medicine, online erschienen am 07.10.2022. Verfasst von Robert J H Miller und 14 weiteren Autor:innen. Beteiligte Einrichtung: Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles…. Hauptthemen laut MEDLINE: Coronary Artery Disease, Deep Learning. Die Arbeit wurde bisher 65-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCATS NIH HHS, NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-dose ungated CT attenuation correction (CTAC) scans are commonly obtained with SPECT/CT myocardial perfusion imaging. Despite the characteristically low image quality of CTAC, deep learning (DL) can potentially quantify coronary artery calcium (CAC) from these scans in an automatic manner. We evaluated CAC quantification derived with a DL model, including correlation with expert annotations and associations with major adverse cardiovascular events (MACE).

Methods

We trained a convolutional long short-term memory DL model to automatically quantify CAC on CTAC scans using 6,608 studies (2 centers) and evaluated the model in an external cohort of patients without known coronary artery disease (n = 2,271) obtained in a separate center. We assessed agreement between DL and expert annotated CAC scores. We also assessed associations between MACE (death, revascularization, myocardial infarction, or unstable angina) and CAC categories (0, 1-100, 101-400, or >400) for scores manually derived by experienced readers and scores obtained fully automatically by DL using multivariable Cox models (adjusted for age, sex, past medical history, perfusion, and ejection fraction) and net reclassification index.

Results

In the external testing population, DL CAC was 0 in 908 patients (40.0%), 1-100 in 596 (26.2%), 100-400 in 354 (15.6%), and >400 in 413 (18.2%). Agreement in CAC category by DL CAC and expert annotation was excellent (linear weighted κ, 0.80), but DL CAC was obtained automatically in less than 2 s compared with about 2.5 min for expert CAC. DL CAC category was an independent risk factor for MACE with hazard ratios in comparison to a CAC of zero: CAC of 1-100 (2.20; 95% CI, 1.54-3.14; P < 0.001), CAC of 101-400 (4.58; 95% CI, 3.23-6.48; P < 0.001), and CAC of more than 400 (5.92; 95% CI, 4.27-8.22; P < 0.001). Overall, the net reclassification index was 0.494 for DL CAC, which was similar to expert annotated CAC (0.503).

Conclusion

DL CAC from SPECT/CT attenuation maps agrees well with expert CAC annotations and provides a similar risk stratification but can be obtained automatically. DL CAC scores improved classification of a significant proportion of patients as compared with SPECT myocardial perfusion alone.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Coronary Artery DiseaseDeep LearningHumansCalciumSingle Photon Emission Computed Tomography Computed TomographyTomography, Emission-Computed, Single-PhotonRisk FactorsCoronary Angiography

Stichwörter der Autor:innen

artificial intelligencecardiologycoronary artery calcificationdeep learningmyocardial perfusion imagingrisk stratification

Substanzen

Calcium

Autor:innen und Institutionen

  • Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California.
  • Department of Cardiac Sciences, University of Calgary, Calgary, Alberta, Canada.
  • Department of Interventional Cardiology and Cardiac Surgery, University of Zielona Góra, Zielona Góra, Poland.
  • Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, Connecticut; and.
  • Cardiovascular Imaging Technologies LLC, Kansas City, Missouri.
  • Departments of Medicine (Division of Artificial Intelligence in Medicine), Imaging, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, California; piotr.slomka@cshs.org.

Förderung

  • NCATS NIH HHS
  • NHLBI NIH HHS

Zitieren

APA

Miller, R. J. H., Pieszko, K., Shanbhag, A., Feher, A., Lemley, M., Killekar, A., Kavanagh, P. B., Van Kriekinge, S. D., Liang, J. X., Huang, C., Miller, E. J., Bateman, T., Berman, D. S., Dey, D., & Slomka, P. J. (2023). Deep Learning Coronary Artery Calcium Scores from SPECT/CT Attenuation Maps Improve Prediction of Major Adverse Cardiac Events. Journal of Nuclear Medicine, 64(4), 652-658. https://doi.org/10.2967/jnumed.122.264423

Vancouver

Miller RJH, Pieszko K, Shanbhag A, Feher A, Lemley M, Killekar A, et al. Deep Learning Coronary Artery Calcium Scores from SPECT/CT Attenuation Maps Improve Prediction of Major Adverse Cardiac Events. Journal of Nuclear Medicine. 2023;64(4):652-658. doi:10.2967/jnumed.122.264423

BibTeX
@article{Miller2023,
  author = {Miller, Robert J H and Pieszko, Konrad and Shanbhag, Aakash and Feher, Attila and Lemley, Mark and Killekar, Aditya and Kavanagh, Paul B and Van Kriekinge, Serge D and Liang, Joanna X and Huang, Cathleen and Miller, Edward J and Bateman, Timothy and Berman, Daniel S and Dey, Damini and Slomka, Piotr J},
  title = {Deep Learning Coronary Artery Calcium Scores from SPECT/CT Attenuation Maps Improve Prediction of Major Adverse Cardiac Events},
  journal = {Journal of Nuclear Medicine},
  year = {2023},
  volume = {64},
  number = {4},
  pages = {652--658},
  doi = {10.2967/jnumed.122.264423}
}
Kostenlos starten →