超高清CT联合深度学习图像重建用于神经血管成像的增强效果
本研究为回顾性单中心研究,纳入100例因急性神经系统症状行头颅CT和CTA的患者,在超高清CT系统上比较深度学习重建的超高清CTA(DL-UHR-CTA)与标准混合迭代重建的常规分辨率CTA(NR-CTA)及超高清CTA(UHR-CTA)。结果显示DL-UHR-CTA在皮层下血管的SNR和CNR优于NR-CTA,且图像质量、对比度、诊断信心和血管可评估性均显著优于UHR-CTA和NR-CTA。
要点
- DL-UHR-CTA在皮层下血管的SNR和CNR显著优于NR-CTA(P < .001)。
- DL-UHR-CTA在各血管节段的图像质量、对比度、诊断信心和血管可评估性均显著优于UHR-CTA和NR-CTA(P < .05)。
- DL-UHR-CTA的斜率绝对值(-359.6 ± 116.0)显著大于NR-CTA(-226.5 ± 64.2 HU)和UHR-CTA(-249.2 ± 67.1 HU)(P < .001)。
核心结论
- 深度学习重建的超高清CTA图像在神经血管成像中显著改善整体图像质量、血管描绘、SNR和CNR,优于单独使用混合迭代重建。
研究设计与样本
- 回顾性单中心研究,纳入100例连续患者,因急性神经系统症状行头颅CT和CTA,使用超高清CT系统,比较NR-CTA(512×512矩阵、0.5 mm层厚)、UHR-CTA(1024×1024矩阵、0.25 mm层厚)及DL-UHR-CTA(深度学习算法应用于UHR-CTA数据集)。
关键影像表现/征象
- DL-UHR-CTA在皮层下血管的SNR和CNR显著优于NR-CTA(P < .001)。
- NR-CTA在基底动脉和大脑中动脉的SNR显著低于UHR-CTA(P < .05),基底动脉的CNR也显著低于UHR-CTA(P = .02)。
- NR-CTA与UHR-CTA之间大脑中动脉的CNR和皮层下血管的SNR无显著差异。
- DL-UHR-CTA的斜率(-359.6 ± 116.0)显著陡于NR-CTA(-226.5 ± 64.2 HU)和UHR-CTA(-249.2 ± 67.1 HU)(P < .001)。
- 定性分析显示DL-UHR-CTA在整体图像质量、对比度、诊断信心和各血管节段可评估性方面显著优于UHR-CTA和NR-CTA,伪影更少(P < .05)。
诊断标准与关键数值
- 定量分析包括SNR、CNR和斜率,评估大脑中动脉、基底动脉和皮层下血管3个血管节段。
- 定性评估由2名放射科医生使用4分Likert量表对图像质量、对比度、伪影、诊断信心和血管可评估性(近端、中间、皮层下节段)进行评分。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND AND PURPOSE: CTA is an established technique for imaging intracranial arteries, enabling rapid assessment of stenosis, vessel occlusions and aneurysm in various acute and elective clinical settings. This study aims to evaluate. Our purpose was to evaluate the diagnostic benefits of deep learning-based image reconstruction for neurovascular imaging by using ultra-high-resolution (UHR)-CT compared with standard hybrid iterative reconstruction (HIR) applied to both UHR-CT and normal-resolution (NR)-CT data sets.
MATERIALS AND METHODS: This retrospective, single-center study included 100 consecutive patients who underwent cranial CT and CTA for acute neurologic symptoms. Imaging was performed on a UHR-CT system. HIR was applied to CTA data sets reconstructed with: 1) an NR matrix of 512 × 512 pixels and 0.5 mm slice thickness (NR-CTA) and 2) a UHR matrix of 1024 × 1024 pixels and 0.25 mm slice thickness (UHR-CTA). Downscaling from the UHR data was performed for the NR-CTA by averaging 4 voxels (2 × 2) into 1 voxel, effectively converting the 1024 × 1024 matrix to a 512 × 512 matrix. A vendor-specific deep-learning algorithm trained for neurovascular analysis was additionally applied to UHR-CTA data sets (deep-learning UHR-CTA [DL-UHR-CTA]). Quantitative analyses included SNR, contrast-to-noise ratio (CNR), and slope evaluations in 3 vessel sections: the MCA, basilar artery (BA), and a subcortical vessel (SV) by using a Matlab-tool. Qualitative assessments of image quality, contrast, artifacts, diagnostic confidence, and vessel assessability (proximal, intermediate, and subcortical segments) were conducted by 2 radiologists by using a 4-point Likert scale.
RESULTS: No significant differences between DL-UHR-CTA and NR-CTA were observed in SNR and CNR for BA and MCA; however, DL-UHR-CTA outperformed NR-CTA in SNR and CNR for SV (P < .001). NR-CTA revealed significantly lower SNR for BA and MCA (P < .05) and lower CNR for BA (P = .02) compared with UHR-CTA. No significant differences in CNR for MCA and SNR for SV were observed between NR-CTA and UHR-CTA. DL-UHR-CTA (-359.6 ± 116.0) was significantly steeper than both NR-CTA (-226.5 ± 64.2 Hounsfield unit [HU]) and UHR-CTA (-249.2 ± 67.1 HU) across all vessel segments (P < .001). Qualitative analysis showed DL-UHR-CTA provided significantly better overall image quality, contrast, diagnostic confidence, and accessibility across all vessel segments, with fewer artifacts, compared with UHR-CTA and NR-CTA (P < .05).
CONCLUSIONS: Deep learning-based reconstruction of UHR-CTA images in neurovascular imaging significantly improves overall image quality, vascular delineation, SNR, and CNR compared with HIR alone.
引用
- Steinmetz S, Mercado MAA, Frenzel M, et al. Enhanced Neurovascular Imaging Using Ultra-High-Resolution CT and Deep Learning-Based Image Reconstruction. AJNR Am J Neuroradiol. 2026. PMID: 41436283. doi:10.3174/ajnr.A8964
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。