Comparison of deep learning and particle smoother EM methods for estimation of Rb‐82 myocardial perfusion PET kinetic parameters
Medical Physics · 2026-06 · 53 (6)
DOI: 10.1002/mp.70512 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Medical Physics, online erschienen am 08.06.2026. Verfasst von Myungheon Chin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering, Stanford University, Stanford, California, USA. Hauptthemen laut MEDLINE: Myocardial Perfusion Imaging, Positron-Emission Tomography, Rubidium Radioisotopes, Deep Learning. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Sun-Pan Family Fellowship Fund, Wu Tsai Neurosciences Institute, Stanford University.
Abstract (Originalsprache)
Background
Positron emission tomography (PET) enables quantification of dynamic physiological processes through time‐resolved imaging. In myocardial perfusion PET, kinetic compartment modeling is used to estimate physiological parameters and derive myocardial blood flow. However, conventional nonlinear least squares (NLLS) estimation is sensitive to model misspecification when not all parameters can be reliably estimated and must instead be fixed or initialized using population averages, which can degrade accuracy.
Purpose
This work develops and evaluates two alternative kinetic analysis approaches for PET: a particle smoother‐based Expectation–Maximization method (PSEM) and a convolutional neural network (CNN).
Methods
Both methods were evaluated using simulated dynamic myocardial perfusion studies and compared against NLLS and a Kalman‐smoother‐based Expectation–Maximization (KEM) algorithm across multiple frame durations and noise levels.
Results
Across 2–10 s frames, the CNN achieved the lowest relative errors for all parameters (: 8.78%–4.98%, : 26.05%–25.50%, : 34.34%–22.76%), significantly outperforming NLLS, KEM, and PSEM (Holm‐adjusted at 1.0 noise, 2‐s frames), although performance degraded under out‐of‐distribution input‐function conditions.
Conclusions
Overall, the CNN provided the most accurate and robust in‐distribution kinetic parameter estimates across frame durations. In contrast, PSEM exhibited parameter‐dependent behavior, improving estimation while underperforming for , suggesting that further methodological refinement is needed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Electrical Engineering, Stanford University, Stanford, California, USA.
- Department of Radiology and Molecular Imaging Program at Stanford (MIPS), Stanford University, Stanford, California, USA.
- Departments of Bioengineering and Physics, Stanford University, Stanford, California, USA.
Förderung
- Sun-Pan Family Fellowship Fund
- Wu Tsai Neurosciences Institute, Stanford University
Zitieren
APA
Chin, M., Zou, S. J., Chinn, G., & Levin, C. S. (2026). Comparison of deep learning and particle smoother EM methods for estimation of Rb‐82 myocardial perfusion PET kinetic parameters. Medical Physics, 53(6). https://doi.org/10.1002/mp.70512
Vancouver
Chin M, Zou SJ, Chinn G, Levin CS. Comparison of deep learning and particle smoother EM methods for estimation of Rb‐82 myocardial perfusion PET kinetic parameters. Medical Physics. 2026;53(6). doi:10.1002/mp.70512
BibTeX
@article{Chin2026,
author = {Chin, Myungheon and Zou, Sarah J and Chinn, Garry and Levin, Craig S},
title = {Comparison of deep learning and particle smoother EM methods for estimation of Rb‐82 myocardial perfusion PET kinetic parameters},
journal = {Medical Physics},
year = {2026},
volume = {53},
number = {6},
doi = {10.1002/mp.70512}
}
EUVIMED