Literature DB >> 36097242

Deep-learning-based estimation of attenuation map improves attenuation correction performance over direct attenuation estimation for myocardial perfusion SPECT.

Hao Xu1, Greta S P Mok2,3, Yu Du4,5, Jingjie Shang1, Jingzhang Sun4, Lu Wang1, Yi-Hwa Liu6.   

Abstract

BACKGROUND: Deep learning (DL)-based attenuation correction (AC) is promising to improve myocardial perfusion (MP) SPECT. We aimed to optimize and compare the DL-based direct and indirect AC methods, with and without SPECT and CT mismatch.
METHODS: One hundred patients with different 99mTc-sestamibi activity distributions and anatomical variations were simulated by a population of XCAT phantoms. Additionally, 34 patients 99mTc-sestamibi stress/rest SPECT/CT scans were retrospectively recruited. Projections were reconstructed by OS-EM method with or without AC. Mismatch between SPECT and CT images was modeled. A 3D conditional generative adversarial network (cGAN) was optimized for two DL-based AC methods: (i) indirect approach, i.e., non-attenuation corrected (NAC) SPECT paired with the corresponding attenuation map for training. The projections were reconstructed with the DL-generated attenuation map for AC; (ii) direct approach, i.e., NAC SPECT paired with the corresponding AC SPECT for training to perform direct AC.
RESULTS: Mismatch between SPECT and CT degraded DL-based AC performance. The indirect approach is superior to direct approach for various physical and clinical indices, even with mismatch modeled.
CONCLUSION: DL-based estimation of attenuation map for AC is superior and more robust to direct generation of AC SPECT.
© 2022. The Author(s) under exclusive licence to American Society of Nuclear Cardiology.

Entities:  

Keywords:  Deep learning; attenuation correction; generative adversarial network; mismatch; myocardial perfusion SPECT

Year:  2022        PMID: 36097242     DOI: 10.1007/s12350-022-03092-4

Source DB:  PubMed          Journal:  J Nucl Cardiol        ISSN: 1071-3581            Impact factor:   3.872


  4 in total

1.  The effects of mismatch between SPECT and CT images on quantitative activity estimation - A simulation study.

Authors:  Yingqing Lyu; Gefei Chen; Zhonglin Lu; Yue Chen; Greta S P Mok
Journal:  Z Med Phys       Date:  2022-05-26       Impact factor: 4.820

2.  Pulmonary artery imaging with 68 Ga-FAPI-04 in patients with chronic thromboembolic pulmonary hypertension.

Authors:  Juan-Ni Gong; Bi-Xi Chen; Hai-Qun Xing; Li Huo; Yuan-Hua Yang; Min-Fu Yang
Journal:  J Nucl Cardiol       Date:  2022-08-04       Impact factor: 3.872

3.  Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECT.

Authors:  Jingzhang Sun; Han Jiang; Yu Du; Chien-Ying Li; Tung-Hsin Wu; Yi-Hwa Liu; Bang-Hung Yang; Greta S P Mok
Journal:  J Nucl Cardiol       Date:  2022-08-18       Impact factor: 3.872

4.  Predictive values of left ventricular mechanical dyssynchrony for CRT response in heart failure patients with different pathophysiology.

Authors:  Zhuo He; Dianfu Li; Chang Cui; Hui-Yuan Qin; Zhongqiang Zhao; Xiaofeng Hou; Jiangang Zou; Ming-Long Chen; Cheng Wang; Weihua Zhou
Journal:  J Nucl Cardiol       Date:  2021-09-17       Impact factor: 3.872

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.