Radiology Department, Columbia University Irving Medical Center, New York, NY 10032, USA.
GE Healthcare, New York, NY 10032, USA.
Tomography. 2024 Apr 2;10(4):504-519. doi: 10.3390/tomography10040039.
To assess the impact of a deep learning (DL) denoising reconstruction algorithm applied to identical patient scans acquired with two different voxel dimensions, representing distinct spatial resolutions, this IRB-approved prospective study was conducted at a tertiary pediatric center in compliance with the Health Insurance Portability and Accountability Act. A General Electric Signa Premier unit (GE Medical Systems, Milwaukee, WI) was employed to acquire two DTI (diffusion tensor imaging) sequences of the left knee on each child at 3T: an in-plane 2.0 × 2.0 mm2 with section thickness of 3.0 mm and a 2 mm isovolumetric voxel; neither had an intersection gap. For image acquisition, a multi-band DTI with a fat-suppressed single-shot spin-echo echo-planar sequence (20 non-collinear directions; b-values of 0 and 600 s/mm) was utilized. The MR vendor-provided a commercially available DL model which was applied with 75% noise reduction settings to the same subject DTI sequences at different spatial resolutions. We compared DTI tract metrics from both DL-reconstructed scans and non-denoised scans for the femur and tibia at each spatial resolution. Differences were evaluated using Wilcoxon-signed ranked test and Bland-Altman plots. When comparing DL versus non-denoised diffusion metrics in femur and tibia using the 2 mm × 2 mm × 3 mm voxel dimension, there were no significant differences between tract count ( = 0.1, = 0.14) tract volume ( = 0.1, = 0.29) or tibial tract length ( = 0.16); femur tract length exhibited a significant difference ( < 0.01). All diffusion metrics (tract count, volume, length, and fractional anisotropy (FA)) derived from the DL-reconstructed scans, were significantly different from the non-denoised scan DTI metrics in both the femur and tibial physes using the 2 mm voxel size ( < 0.001). DL reconstruction resulted in a significant decrease in femorotibial FA for both voxel dimensions ( < 0.01). Leveraging denoising algorithms could address the drawbacks of lower signal-to-noise ratios (SNRs) associated with smaller voxel volumes and capitalize on their better spatial resolutions, allowing for more accurate quantification of diffusion metrics.
为了评估应用于具有不同体素尺寸的相同患者扫描的深度学习 (DL) 去噪重建算法的影响，该符合 HIPAA 规定的前瞻性研究在一家三级儿科中心进行，使用的是 General Electric Signa Premier 设备（GE Medical Systems，Milwaukee，WI），在每个孩子的 3T 上获取左膝的两个 DTI（弥散张量成像）序列：一个是 2.0×2.0mm2 的体素，层厚为 3.0mm，另一个是 2mm 的等体素；两者都没有交叉间隙。对于图像采集，使用带有脂肪抑制的单次激发自旋回波平面序列的多频带 DTI（20 个非共线方向；b 值为 0 和 600 s/mm）。MR 供应商提供了一个商用的 DL 模型，该模型以 75%的降噪设置应用于不同空间分辨率的同一对象 DTI 序列。我们比较了不同空间分辨率下股骨和胫骨的来自 DL 重建扫描和非去噪扫描的 DTI 束流指标。使用 Wilcoxon 符号秩检验和 Bland-Altman 图评估差异。当使用 2mm×2mm×3mm 体素尺寸比较股骨和胫骨的 DL 与非去噪扩散指标时，束流计数（=0.1，=0.14）、束流体积（=0.1，=0.29）或胫骨束流长度（=0.16）之间没有显著差异；股骨束流长度存在显著差异（<0.01）。来自 DL 重建扫描的所有扩散指标（束流计数、体积、长度和各向异性分数（FA））与使用 2mm 体素尺寸的股骨和胫骨骨骺的非去噪扫描 DTI 指标均有显著差异（<0.001）。DL 重建导致两种体素尺寸的股胫 FA 显著降低（<0.01）。利用去噪算法可以解决与较小体素体积相关的较低信噪比（SNR）的缺点，并利用其更好的空间分辨率，从而更准确地量化扩散指标。
