基于噪声对噪声训练的深度学习用于 SPECT 心肌灌注成像去噪。
Deep learning with noise-to-noise training for denoising in SPECT myocardial perfusion imaging.
机构信息
Medical Imaging Research Center and Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL, 60616, USA.
Department of Radiology, University of Massachusetts Medical School, Worcester, MA, 01655, USA.
出版信息
Med Phys. 2021 Jan;48(1):156-168. doi: 10.1002/mp.14577. Epub 2020 Nov 23.
PURPOSE
Post-reconstruction filtering is often applied for noise suppression due to limited data counts in myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT). We study a deep learning (DL) approach for denoising in conventional SPECT-MPI acquisitions, and investigate whether it can be more effective for improving the detectability of perfusion defects compared to traditional postfiltering.
METHODS
Owing to the lack of ground truth in clinical studies, we adopt a noise-to-noise (N2N) training approach for denoising in SPECT-MPI images. We consider a coupled U-Net (CU-Net) structure which is designed to improve learning efficiency through feature map reuse. For network training we employ a bootstrap procedure to generate multiple noise realizations from list-mode clinical acquisitions. In the experiments we demonstrated the proposed approach on a set of 895 clinical studies, where the iterative OSEM algorithm with three-dimensional (3D) Gaussian postfiltering was used to reconstruct the images. We investigated the detection performance of perfusion defects in the reconstructed images using the non-prewhitening matched filter (NPWMF), evaluated the uniformity of left ventricular (LV) wall in terms of image intensity, and quantified the effect of smoothing on the spatial resolution of the reconstructed LV wall by using its full-width at half-maximum (FWHM).
RESULTS
Compared to OSEM with Gaussian postfiltering, the DL denoised images with CU-Net significantly improved the detection performance of perfusion defects at all contrast levels (65%, 50%, 35%, and 20%). The signal-to-noise ratio (SNR ) in the NPWMF output was increased on average by 8% over optimal Gaussian smoothing (P < 10 , paired t-test), while the inter-subject variability was greatly reduced. The CU-Net also outperformed a 3D nonlocal means (NLM) filter and a convolutional autoencoder (CAE) denoising network in terms of SNR . In addition, the FWHM of the LV wall in the reconstructed images was varied by less than 1%. Furthermore, CU-Net also improved the detection performance when the images were processed with less post-reconstruction smoothing (a trade-off of increased noise for better LV resolution), with SNR improved on average by 23%.
CONCLUSIONS
The proposed DL with N2N training approach can yield additional noise suppression in SPECT-MPI images over conventional postfiltering. For perfusion defect detection, DL with CU-Net could outperform conventional 3D Gaussian filtering with optimal setting as well as NLM and CAE.
目的
由于单光子发射计算机断层扫描（SPECT）心肌灌注成像（MPI）的数据计数有限，因此通常应用后重建滤波来抑制噪声。我们研究了一种用于传统 SPECT-MPI 采集去噪的深度学习（DL）方法，并研究了与传统后滤波相比，它是否可以更有效地提高灌注缺陷的可检测性。
方法
由于在临床研究中缺乏真实情况，我们采用噪声到噪声（N2N）训练方法对 SPECT-MPI 图像进行去噪。我们考虑了一种设计用于通过特征图重用来提高学习效率的耦合 U-Net（CU-Net）结构。对于网络训练，我们采用引导程序过程从列表模式临床采集生成多个噪声实现。在实验中，我们在一组 895 项临床研究中演示了所提出的方法，其中使用三维（3D）高斯后滤波的迭代 OSEM 算法重建图像。我们使用非预白化匹配滤波器（NPWMF）评估了重建图像中灌注缺陷的检测性能，根据图像强度评估了左心室（LV）壁的均匀性，并通过使用其半高全宽（FWHM）量化了平滑对重建 LV 壁空间分辨率的影响。
结果
与高斯后滤波的 OSEM 相比，具有 CU-Net 的 DL 去噪图像在所有对比度水平（65％，50％，35％和 20％）下均显著提高了灌注缺陷的检测性能。NPWMF 输出的信噪比（SNR）平均提高了 8％，而最佳高斯平滑（P<10，配对 t 检验），同时大大降低了个体间的可变性。在 SNR 方面，CU-Net 也优于三维非局部均值（NLM）滤波器和卷积自动编码器（CAE）去噪网络。此外，重建图像中 LV 壁的 FWHM 变化小于 1％。此外，当图像经过较少的后重建平滑处理（增加噪声以改善 LV 分辨率的折衷）时，CU-Net 还改善了检测性能，平均 SNR 提高了 23％。
结论
所提出的具有 N2N 训练方法的 DL 可以在传统后滤波的基础上在 SPECT-MPI 图像中获得额外的噪声抑制。对于灌注缺陷检测，具有 CU-Net 的 DL 可以胜过具有最佳设置的传统 3D 高斯滤波以及 NLM 和 CAE。
Zotero 插件