冠状动脉支架的CTA评估:超分辨率深度学习重建与其他重建算法的图像质量比较
本回顾性研究纳入24例患者共51枚冠状动脉支架,比较混合迭代重建、基于模型的迭代重建、常规分辨率深度学习重建与超分辨率深度学习重建的图像质量。超分辨率深度学习重建在支架伪影、支架内管腔显示及小直径支架可评估率方面均优于其他算法,可能有助于320排常规分辨率扫描仪的支架评估。
要点
- 超分辨率深度学习重建(SR-DLR)较其他三种重建算法降低支架伪影、提高支架内管腔直径显示和支架支撑杆锐利度。
- 对于直径≤3.0 mm的支架,SR-DLR的可评估率(观察者1为86.5%,观察者2为89.2%)高于其他算法。
- SR-DLR在图像锐利度、噪声纹理及支架结构 delineation 等主观评分上均获最高分(中位4.0分)。
核心结论
- 与混合迭代重建、基于模型的迭代重建和常规分辨率深度学习重建相比,SR-DLR改善了支架支撑杆和支架内管腔的显示,图像锐利度更好,噪声和开花伪影更少,可能有助于320排常规分辨率扫描仪的冠状动脉支架评估,尤其对小直径支架。
研究设计与样本
- 回顾性研究,纳入2020年1月至2020年12月期间接受冠状动脉CTA且至少有一枚冠状动脉支架的患者24例(男18例,女6例;平均年龄72.5±9.8岁),共51枚支架;使用320排常规分辨率扫描仪检查,分别以混合迭代重建(HIR)、基于模型的迭代重建(MBIR)、常规分辨率深度学习重建(NR-DLR)和超分辨率深度学习重建(SR-DLR)算法重建;由两名放射科医生独立评价图像质量。
关键影像表现/征象
- SR-DLR较其他重建算法降低支架相关开花伪影(中位数40.3 vs 53.4-58.2)、支架所致衰减增加比(0.17 vs 0.27-0.31)和定量图像噪声(18.1 vs 20.9-30.4 HU),并提高支架内管腔直径(2.4 vs 1.7-1.9 mm)、支架支撑杆锐利度(327 vs 147-210 ΔHU/mm)和CNR(30.0 vs 16.0-25.6)(均p < .001)。
- 两名观察者对所有主观排名指标(图像锐利度、图像噪声、噪声纹理、支架支撑杆、支架内管腔、冠状动脉壁及支架周围钙化斑块的 delineation)和诊断信心均给予SR-DLR更高评分(所有特征中位数4.0分),其他重建算法范围为1.0-3.0分(均p < .001)。
诊断标准与关键数值
- 主观排名采用4分制:1分为最差重建,4分为最佳重建。
- 诊断信心采用5分制:评分≥3分表示支架可评估。
- 对于直径≤3.0 mm的支架(n=37),SR-DLR的可评估率为观察者1 86.5%、观察者2 89.2%,高于HIR(35.1%和43.2%)、MBIR(59.5%和62.2%)和NR-DLR(62.2%和64.9%)(均p < .05)。
临床应用与阅片要点
- SR-DLR可改善支架支撑杆和支架内管腔的 delineation,图像锐利度更好、噪声和开花伪影更少,尤其对直径≤3.0 mm的支架可评估率更高。
- SR-DLR可能有助于320排常规分辨率扫描仪的冠状动脉支架评估。
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. A super-resolution deep learning reconstruction (SR-DLR) algorithm may provide better image sharpness than earlier reconstruction algorithms and thereby improve coronary stent assessment on coronary CTA. OBJECTIVE. The purpose of our study was to compare SR-DLR and other reconstruction algorithms in terms of image quality measures related to coronary stent evaluation in patients undergoing coronary CTA. METHODS. This retrospective study included patients with at least one coronary artery stent who underwent coronary CTA between January 2020 and December 2020. Examinations were performed using a 320-row normal-resolution scanner and were reconstructed with hybrid iterative reconstruction (HIR), model-based iterative reconstruction (MBIR), normal-resolution deep learning reconstruction (NR-DLR), and SR-DLR algorithms. Quantitative image quality measures were determined. Two radiologists independently reviewed images to rank the four reconstructions (4-point scale: 1 = worst reconstruction, 4 = best reconstruction) for qualitative measures and to score diagnostic confidence (5-point scale: score ≥ 3 indicating an assessable stent). The assessability rate was calculated for stents with a diameter of 3.0 mm or less. RESULTS. The sample included 24 patients (18 men, six women; mean age, 72.5 ± 9.8 [SD] years), with 51 stents. SR-DLR, in comparison with the other reconstructions, yielded lower stent-related blooming artifacts (median, 40.3 vs 53.4-58.2), stent-induced attenuation increase ratio (0.17 vs 0.27-0.31), and quantitative image noise (18.1 vs 20.9-30.4 HU) and higher in-stent lumen diameter (2.4 vs 1.7-1.9 mm), stent strut sharpness (327 vs 147-210 ΔHU/mm), and CNR (30.0 vs 16.0-25.6) (all p < .001). For both observers, all ranked measures (image sharpness; image noise; noise texture; delineation of stent strut, in-stent lumen, coronary artery wall, and calcified plaque surrounding the stent) and diagnostic confidence showed a higher score for SR-DLR (median, 4.0 for all features) than for the other reconstructions (range, 1.0-3.0) (all p < .001). The assessability rate for stents with a diameter of 3.0 mm or less (n = 37) was higher for SR-DLR (86.5% for observer 1 and 89.2% for observer 2) than for HIR (35.1% and 43.2%), MBIR (59.5% and 62.2%), and NR-DLR (62.2% and 64.9%) (all p < .05). CONCLUSION. SR-DLR yielded improved delineation of the stent strut and in-stent lumen, with better image sharpness and less image noise and blooming artifacts, in comparison with HIR, MBIR, and NR-DLR. CLINICAL IMPACT. SR-DLR may facilitate coronary stent assessment on a 320-row normal-resolution scanner, particularly for small-diameter stents.
引用
- Nagayama, Emoto, Hayashi, et al. Coronary Stent Evaluation by CTA: Image Quality Comparison Between Super-Resolution Deep Learning Reconstruction and Other Reconstruction Algorithms. AJR Am J Roentgenol. 2023. PMID: 37377362. doi:10.2214/AJR.23.29506
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。