Tehran University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Standard Spect Myocardial Perfusion Estimation From Half-Time Acquisitions Using Deep Convolutional Residual Neural Networks Publisher Pubmed



Shiri I1 ; Amirmozafari Sabet K2 ; Arabi H1 ; Pourkeshavarz M3, 4 ; Teimourian B5 ; Ay MR5, 6 ; Zaidi H1, 7, 8, 9
Authors
Show Affiliations
Authors Affiliations
  1. 1. Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, Geneva 4, 1211, Switzerland
  2. 2. School of Electrical Engineering, Sharif University of Technology, Tehran, Iran
  3. 3. Rajaie Cardiovascular Medical and Research Center, Iran University of Medical Science, Tehran, Iran
  4. 4. Department of Computer Engineering, Shahid Beheshti University, Tehran, Iran
  5. 5. Research Center for Molecular and Cellular Imaging, Tehran University of Medical Sciences, Tehran, Iran
  6. 6. Department of Medical Physics and Biomedical Engineering, Tehran University of Medical Sciences, Tehran, Iran
  7. 7. Geneva University Neurocenter, Geneva University, Geneva, Switzerland
  8. 8. Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands
  9. 9. Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark

Source: Journal of Nuclear Cardiology Published:2021


Abstract

Introduction: The purpose of this work was to assess the feasibility of acquisition time reduction in MPI-SPECT imaging using deep leering techniques through two main approaches, namely reduction of the acquisition time per projection and reduction of the number of angular projections. Methods: SPECT imaging was performed using a fixed 90° angle dedicated dual-head cardiac SPECT camera. This study included a prospective cohort of 363 patients with various clinical indications (normal, ischemia, and infarct) referred for MPI-SPECT. For each patient, 32 projections for 20 seconds per projection were acquired using a step and shoot protocol from the right anterior oblique to the left posterior oblique view. SPECT projection data were reconstructed using the OSEM algorithm (6 iterations, 4 subsets, Butterworth post-reconstruction filter). For each patient, four different datasets were generated, namely full time (20 seconds) projections (FT), half-time (10 seconds) acquisition per projection (HT), 32 full projections (FP), and 16 half projections (HP). The image-to-image transformation via the residual network was implemented to predict FT from HT and predict FP from HP images in the projection domain. Qualitative and quantitative evaluations of the proposed framework was performed using a tenfold cross validation scheme using the root mean square error (RMSE), absolute relative error (ARE), structural similarity index, peak signal-to-noise ratio (PSNR) metrics, and clinical quantitative parameters. Results: The results demonstrated that the predicted FT had better image quality than the predicted FP images. Among the generated images, predicted FT images resulted in the lowest error metrics (RMSE = 6.8 ± 2.7, ARE = 3.1 ± 1.1%) and highest similarity index and signal-to-noise ratio (SSIM = 0.97 ± 1.1, PSNR = 36.0 ± 1.4). The highest error metrics (RMSE = 32.8 ± 12.8, ARE = 16.2 ± 4.9%) and the lowest similarity and signal-to-noise ratio (SSIM = 0.93 ± 2.6, PSNR = 31.7 ± 2.9) were observed for HT images. The RMSE decreased significantly (P value <.05) for predicted FT (8.0 ± 3.6) relative to predicted FP (6.8 ± 2.7). Conclusion: Reducing the acquisition time per projection significantly increased the error metrics. The deep neural network effectively recovers image quality and reduces bias in quantification metrics. Further research should be undertaken to explore the impact of time reduction in gated MPI-SPECT. © 2020, American Society of Nuclear Cardiology.
Related Docs
1. Deep Learning–Based Denoising of Low-Dose Spect Myocardial Perfusion Images: Quantitative Assessment and Clinical Performance, European Journal of Nuclear Medicine and Molecular Imaging (2022)
2. Deep-Jasc: Joint Attenuation and Scatter Correction in Whole-Body 18F-Fdg Pet Using a Deep Residual Network, European Journal of Nuclear Medicine and Molecular Imaging (2020)
3. Deep-Learning-Based Attenuation Correction For68 Ga-Dotatate Whole-Body Pet Imaging: A Dual-Center Clinical Study; [68Ga-Dotatate Tum Vucut Pet Goruntuleme Icin Derin Ogrenme Tabanli Atenuasyon Duzeltmesi: Cift Merkezli Bir Klinik Calisma], Molecular Imaging and Radionuclide Therapy (2024)
4. Fully Automated Gross Tumor Volume Delineation From Pet in Head and Neck Cancer Using Deep Learning Algorithms, Clinical Nuclear Medicine (2021)
5. Investigation of Noise Reduction in Low-Dose Spect Myocardial Perfusion Images With a Generative Adversarial Network, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
6. Improved Diagnostic Accuracy for Myocardial Perfusion Imaging Using Artificial Neural Networks on Different Input Variables Including Clinical and Quantification Data; [Precision Diagnostica Mejorada Para La Imagen De Perfusion Miocardica Usando Redes Neuronales Artificiales En Diferentes Variables De Entrada Incluyendo Datos Clinicos Y De Cuantificacion], Revista Espanola de Medicina Nuclear e Imagen Molecular (2019)
7. Deep Learning-Based Partial Volume Correction in Standard and Low-Dose Positron Emission Tomography-Computed Tomography Imaging, Quantitative Imaging in Medicine and Surgery (2024)
8. Deep Learning-Based Low-Dose Cardiac Gated Spect: Implementation in Projection Space Vs. Image Space, 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record# NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors# RTSD 2022 (2021)
Experts (# of related papers)
View all Related Experts
Peyman Sheikhzadeh (4)
Parham Geramifar (4)