EUVIMEDEUVIMED entdecken
Open Access

Deep Learning–Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT

Aakash D Shanbhag, Robert J H Miller, Konrad Pieszko, Mark Lemley, Paul Kavanagh, Attila Feher, Edward J Miller, Albert J Sinusas, Philipp A Kaufmann, Donghee Han, Cathleen Huang, Joanna X Liang und 3 weitere

Journal of Nuclear Medicine · 2023-03 · 64 (3) · 472-478

DOI: 10.2967/jnumed.122.264429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Nuclear Medicine, online erschienen am 22.09.2022. Verfasst von Aakash D Shanbhag 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: Deep Learning, Coronary Artery Disease, Myocardial Perfusion Imaging. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NHLBI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To improve diagnostic accuracy, myocardial perfusion imaging (MPI) SPECT studies can use CT-based attenuation correction (AC). However, CT-based AC is not available for most SPECT systems in clinical use, increases radiation exposure, and is impacted by misregistration. We developed and externally validated a deep-learning model to generate simulated AC images directly from non-AC (NC) SPECT, without the need for CT.

Methods

SPECT myocardial perfusion imaging was performed using 99mTc-sestamibi or 99mTc-tetrofosmin on contemporary scanners with solid-state detectors. We developed a conditional generative adversarial neural network that applies a deep learning model (DeepAC) to generate simulated AC SPECT images. The model was trained with short-axis NC and AC images performed at 1 site (n = 4,886) and was tested on patients from 2 separate external sites (n = 604). We assessed the diagnostic accuracy of the stress total perfusion deficit (TPD) obtained from NC, AC, and DeepAC images for obstructive coronary artery disease (CAD) with area under the receiver-operating-characteristic curve. We also quantified the direct count change among AC, NC, and DeepAC images on a per-voxel basis.

Results

DeepAC could be obtained in less than 1 s from NC images; area under the receiver-operating-characteristic curve for obstructive CAD was higher for DeepAC TPD (0.79; 95% CI, 0.72-0.85) than for NC TPD (0.70; 95% CI, 0.63-0.78; P < 0.001) and similar to AC TPD (0.81; 95% CI, 0.75-0.87; P = 0.196). The normalcy rate in the low-likelihood-of-coronary-disease population was higher for DeepAC TPD (70.4%) and AC TPD (75.0%) than for NC TPD (54.6%, P < 0.001 for both). The positive count change (increase in counts) was significantly higher for AC versus NC (median, 9.4; interquartile range, 6.0-14.2; P < 0.001) than for AC versus DeepAC (median, 2.4; interquartile range, 1.3-4.2).

Conclusion

In an independent external dataset, DeepAC provided improved diagnostic accuracy for obstructive CAD, as compared with NC images, and this accuracy was similar to that of actual AC. DeepAC simplifies the task of artifact identification for physicians, avoids misregistration artifacts, and can be performed rapidly without the need for CT hardware and additional acquisitions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningCoronary Artery DiseaseMyocardial Perfusion ImagingHumansSensitivity and SpecificityTomography, Emission-Computed, Single-PhotonROC Curve

Stichwörter der Autor:innen

SPECTartificial intelligenceattenuation correctiondeep learningmyocardial perfusion imaging

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.
  • Cardiac Imaging, Department of Nuclear Medicine, University Hospital Zurich, Zurich, Switzerland.
  • 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

  • NHLBI NIH HHS

Zitieren

APA

Shanbhag, A. D., Miller, R. J. H., Pieszko, K., Lemley, M., Kavanagh, P., Feher, A., Miller, E. J., Sinusas, A. J., Kaufmann, P. A., Han, D., Huang, C., Liang, J. X., Berman, D. S., Dey, D., & Slomka, P. J. (2023). Deep Learning–Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT. Journal of Nuclear Medicine, 64(3), 472-478. https://doi.org/10.2967/jnumed.122.264429

Vancouver

Shanbhag AD, Miller RJH, Pieszko K, Lemley M, Kavanagh P, Feher A, et al. Deep Learning–Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT. Journal of Nuclear Medicine. 2023;64(3):472-478. doi:10.2967/jnumed.122.264429

BibTeX
@article{Shanbhag2023,
  author = {Shanbhag, Aakash D and Miller, Robert J H and Pieszko, Konrad and Lemley, Mark and Kavanagh, Paul and Feher, Attila and Miller, Edward J and Sinusas, Albert J and Kaufmann, Philipp A and Han, Donghee and Huang, Cathleen and Liang, Joanna X and Berman, Daniel S and Dey, Damini and Slomka, Piotr J},
  title = {Deep Learning–Based Attenuation Correction Improves Diagnostic Accuracy of Cardiac SPECT},
  journal = {Journal of Nuclear Medicine},
  year = {2023},
  volume = {64},
  number = {3},
  pages = {472--478},
  doi = {10.2967/jnumed.122.264429}
}
Kostenlos starten →