Literature DB >> 32347527

Standard SPECT myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks.

Isaac Shiri1, Kiarash AmirMozafari Sabet2, Hossein Arabi1, Mozhgan Pourkeshavarz3,4, Behnoosh Teimourian5, Mohammad Reza Ay5,6, Habib Zaidi7,8,9,10.   

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.

Entities:  

Keywords:  SPECT; deep learning; myocardial perfusion imaging; short acquisition

Mesh:

Year:  2020        PMID: 32347527     DOI: 10.1007/s12350-020-02119-y

Source DB:  PubMed          Journal:  J Nucl Cardiol        ISSN: 1071-3581            Impact factor:   5.952


  2 in total

1.  Functional significance of post-myocardial infarction inflammation evaluated by 18F-fluorodeoxyglucose imaging in swine model.

Authors:  Xiao-Ying Xi; Feifei Zhang; Jianfeng Wang; Wei Gao; Yi Tian; Hongyu Xu; Min Xu; Yuetao Wang; Min-Fu Yang
Journal:  J Nucl Cardiol       Date:  2019-11-18       Impact factor: 5.952

2.  Thyroid Diagnosis from SPECT Images Using Convolutional Neural Network with Optimization.

Authors:  Liyong Ma; Chengkuan Ma; Yuejun Liu; Xuguang Wang
Journal:  Comput Intell Neurosci       Date:  2019-01-15
  2 in total
  11 in total

Review 1.  Applications of artificial intelligence in nuclear medicine image generation.

Authors:  Zhibiao Cheng; Junhai Wen; Gang Huang; Jianhua Yan
Journal:  Quant Imaging Med Surg       Date:  2021-06

2.  Pix2Pix generative adversarial network for low dose myocardial perfusion SPECT denoising.

Authors:  Jingzhang Sun; Yu Du; ChienYing Li; Tung-Hsin Wu; BangHung Yang; Greta S P Mok
Journal:  Quant Imaging Med Surg       Date:  2022-07

3.  Direct and indirect strategies of deep-learning-based attenuation correction for general purpose and dedicated cardiac SPECT.

Authors:  Xiongchao Chen; Bo Zhou; Huidong Xie; Luyao Shi; Hui Liu; Wolfgang Holler; MingDe Lin; Yi-Hwa Liu; Edward J Miller; Albert J Sinusas; Chi Liu
Journal:  Eur J Nucl Med Mol Imaging       Date:  2022-02-16       Impact factor: 10.057

4.  Ultra high speed SPECT bone imaging enabled by a deep learning enhancement method: a proof of concept.

Authors:  Boyang Pan; Na Qi; Qingyuan Meng; Jiachen Wang; Siyue Peng; Chengxiao Qi; Nan-Jie Gong; Jun Zhao
Journal:  EJNMMI Phys       Date:  2022-06-13

5.  Deep learning, another important tool for improving acquisition efficiency in SPECT MPI Imaging.

Authors:  Ernest V Garcia
Journal:  J Nucl Cardiol       Date:  2020-05-17       Impact factor: 5.952

6.  Artificial intelligence in nuclear cardiology: Preparing for the fifth industrial revolution.

Authors:  Ernest V Garcia
Journal:  J Nucl Cardiol       Date:  2021-08-03       Impact factor: 5.952

Review 7.  Quantitative clinical nuclear cardiology, part 2: Evolving/emerging applications.

Authors:  Piotr J Slomka; Jonathan B Moody; Robert J H Miller; Jennifer M Renaud; Edward P Ficaro; Ernest V Garcia
Journal:  J Nucl Cardiol       Date:  2020-10-16       Impact factor: 5.952

Review 8.  Artificial intelligence in single photon emission computed tomography (SPECT) imaging: a narrative review.

Authors:  Wenyi Shao; Steven P Rowe; Yong Du
Journal:  Ann Transl Med       Date:  2021-05

9.  Machine Learning Algorithms to Distinguish Myocardial Perfusion SPECT Polar Maps.

Authors:  Erito Marques de Souza Filho; Fernando de Amorim Fernandes; Christiane Wiefels; Lucas Nunes Dalbonio de Carvalho; Tadeu Francisco Dos Santos; Alair Augusto Sarmet M D Dos Santos; Evandro Tinoco Mesquita; Flávio Luiz Seixas; Benjamin J W Chow; Claudio Tinoco Mesquita; Ronaldo Altenburg Gismondi
Journal:  Front Cardiovasc Med       Date:  2021-11-11

10.  COLI-Net: Deep learning-assisted fully automated COVID-19 lung and infection pneumonia lesion detection and segmentation from chest computed tomography images.

Authors:  Isaac Shiri; Hossein Arabi; Yazdan Salimi; Amirhossein Sanaat; Azadeh Akhavanallaf; Ghasem Hajianfar; Dariush Askari; Shakiba Moradi; Zahra Mansouri; Masoumeh Pakbin; Saleh Sandoughdaran; Hamid Abdollahi; Amir Reza Radmard; Kiara Rezaei-Kalantari; Mostafa Ghelich Oghli; Habib Zaidi
Journal:  Int J Imaging Syst Technol       Date:  2021-10-28       Impact factor: 2.177

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.