Xie Huidong, Thorn Stephanie, Chen Xiongchao, Zhou Bo, Liu Hui, Liu Zhao, Lee Supum, Wang Ge, Liu Yi-Hwa, Sinusas Albert J, Liu Chi
Department of Biomedical Engineering, Yale University, 801 Howard Avenue, New Haven, CT, 06520, USA.
Department of Internal Medicine (Cardiology), Yale University, New Haven, CT, USA.
J Nucl Cardiol. 2023 Feb;30(1):86-100. doi: 10.1007/s12350-022-02972-z. Epub 2022 May 4.
The GE Discovery NM (DNM) 530c/570c are dedicated cardiac SPECT scanners with 19 detector modules designed for stationary imaging. This study aims to incorporate additional projection angular sampling to improve reconstruction quality. A deep learning method is also proposed to generate synthetic dense-view image volumes from few-view counterparts.
By moving the detector array, a total of four projection angle sets were acquired and combined for image reconstructions. A deep neural network is proposed to generate synthetic four-angle images with 76 ([Formula: see text]) projections from corresponding one-angle images with 19 projections. Simulated data, pig, physical phantom, and human studies were used for network training and evaluation. Reconstruction results were quantitatively evaluated using representative image metrics. The myocardial perfusion defect size of different subjects was quantified using an FDA-cleared clinical software.
Multi-angle reconstructions and network results have higher image resolution, improved uniformity on normal myocardium, more accurate defect quantification, and superior quantitative values on all the testing data. As validated against cardiac catheterization and diagnostic results, deep learning results showed improved image quality with better defect contrast on human studies.
Increasing angular sampling can substantially improve image quality on DNM, and deep learning can be implemented to improve reconstruction quality in case of stationary imaging.
GE Discovery NM（DNM）530c/570c是专门用于心脏单光子发射计算机断层扫描（SPECT）的扫描仪，具有19个探测器模块，设计用于静态成像。本研究旨在增加投影角度采样以提高重建质量。还提出了一种深度学习方法，用于从少视图图像生成合成的密集视图图像体积。
通过移动探测器阵列，总共获取并组合了四组投影角度用于图像重建。提出了一种深度神经网络，用于从具有19个投影的相应单角度图像生成具有76个（[公式：见正文]）投影的合成四角度图像。模拟数据、猪、物理模型和人体研究用于网络训练和评估。使用代表性图像指标对重建结果进行定量评估。使用美国食品药品监督管理局（FDA）批准的临床软件对不同受试者的心肌灌注缺损大小进行量化。
多角度重建和网络结果在所有测试数据上具有更高的图像分辨率、改善的正常心肌均匀性、更准确的缺损量化和优异的定量值。在与心脏导管检查和诊断结果进行验证时，深度学习结果显示在人体研究中图像质量得到改善，缺损对比度更好。
增加角度采样可以显著提高DNM上的图像质量，并且在静态成像情况下可以实施深度学习以提高重建质量。
