Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Zurich, Switzerland.
Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Zurich, Switzerland.
Eur J Radiol. 2024 Oct;179:111663. doi: 10.1016/j.ejrad.2024.111663. Epub 2024 Aug 4.
To evaluate the impact of deep learning-based reconstruction (DLRecon) on bone assessment in zero echo-time (ZTE) MRI of the knee at 1.5 Tesla.
This retrospective study included 48 consecutive exams of 46 patients (23 females) who underwent clinically indicated knee MRI at 1.5 Tesla. Standard imaging protocol comprised a sagittal prescribed, isotropic ZTE sequence. ZTE image reconstruction was performed with a standard-of-care (non-DL) and prototype DLRecon method. Exams were divided into subsets with and without osseous pathology based on the radiology report. Using a 4-point scale, two blinded readers qualitatively graded features of bone depiction including artifacts and conspicuity of pathology including diagnostic certainty in the respective subsets. Quantitatively, one reader measured signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of bone. Comparative analyses were conducted to assess the differences between the reconstruction methods. In addition, interreader agreement was calculated for the qualitative gradings.
DLRecon significantly improved gradings for bone depiction relative to non-DL reconstruction (all, p < 0.05), while there was no significant difference with regards to artifacts (both, median score of 0; p = 0.058). In the subset with pathologies, conspicuity of pathology and diagnostic confidence were also scored significantly higher in DLRecon compared to non-DL (median 3 vs 2; p ≤ 0.03). Interreader agreement ranged from moderate to almost-perfect (κ = 0.54-0.88). Quantitatively, DLRecon demonstrated significantly enhanced CNR and SNR of bone compared to non-DL (p < 0.001).
ZTE MRI with DLRecon improved bone depiction in the knee, compared to non-DL. Additionally, DLRecon increased conspicuity of osseous findings together with diagnostic certainty.
评估基于深度学习的重建（DLRecon）对 1.5T 膝关节零回波时间（ZTE）MRI 中骨评估的影响。
本回顾性研究纳入了 46 名患者（23 名女性）的 48 例连续膝关节 MRI 检查，这些患者均因临床需要行 MRI 检查。标准成像方案包括矢状位规定的各向同性 ZTE 序列。ZTE 图像重建采用标准护理（非 DL）和原型 DLRecon 方法。根据放射学报告，将检查分为有和无骨病变亚组。两位盲法读者使用 4 分制对骨描绘特征（包括伪影和病变的明显度）进行定性评分，并分别对各亚组进行诊断确定性评分。定量方面，一位读者测量了骨的信噪比（SNR）和对比噪声比（CNR）。进行了对比分析，以评估两种重建方法之间的差异。此外，还计算了定性分级的读者间一致性。
与非 DL 重建相比，DLRecon 显著改善了骨描绘的评分（均为 p<0.05），而在伪影方面则没有显著差异（中位数均为 0；p=0.058）。在有病变的亚组中，DLRecon 组的病变明显度和诊断信心评分也明显高于非 DLRecon 组（中位数分别为 3 分和 2 分；p≤0.03）。读者间的一致性从中度到几乎完美（κ=0.54-0.88）。定量方面，DLRecon 组的骨 CNR 和 SNR 明显高于非 DLRecon 组（p<0.001）。
与非 DL 相比，ZTE MRI 采用 DLRecon 可改善膝关节的骨描绘。此外，DLRecon 提高了骨病变的明显度和诊断信心。
