深度学习图像重建在超低剂量鼻窦CT中的定量与定性评估:与混合迭代重建的比较
本研究回顾性纳入132例接受非增强超低剂量鼻窦CT(0.03 mSv)的患者,比较混合迭代重建与深度学习图像重建的图像质量。DLR显著降低图像噪声、提高SNR和CNR、增强图像锐利度,放射科医师主观评价DLR在整体图像质量、骨结构显示和诊断信心方面更优。DLR在超低剂量鼻窦CT中优于混合IR,有望以最小辐射剂量支持术前规划。
要点
- 超低剂量鼻窦CT(0.03 mSv)采用DLR可显著降低图像噪声并提高SNR和CNR。
- DLR在骨结构显示和诊断信心方面主观评分优于混合IR。
- DLR图像锐利度更高,有利于FESS术前规划的精细解剖显示。
关键影像表现/征象
- DLR图像噪声为28.62 ± 4.83 HU,显著低于混合IR的140.70 ± 16.04 HU(p < 0.001),图像更平滑均匀。
- DLR的SNR为22.47 ± 5.82,显著高于混合IR的9.14 ± 2.45(p < 0.001)。
- DLR的CNR为71.88 ± 14.03,显著高于混合IR的11.81 ± 1.50(p < 0.001)。
- NPS分析显示DLR降低了噪声幅度和NPS峰值。
- DLR的无参考感知锐利度指标为0.56 ± 0.04,显著高于混合IR的0.36 ± 0.01。
诊断标准与关键数值
- 超低剂量鼻窦CT协议的有效剂量为0.03 mSv。
- DLR图像噪声28.62 ± 4.83 HU,混合IR为140.70 ± 16.04 HU(p < 0.001)。
- DLR的SNR为22.47 ± 5.82,混合IR为9.14 ± 2.45(p < 0.001)。
- DLR的CNR为71.88 ± 14.03,混合IR为11.81 ± 1.50(p < 0.001)。
- DLR无参考感知锐利度为0.56 ± 0.04,混合IR为0.36 ± 0.01。
临床应用与阅片要点
- 在超低剂量鼻窦CT术前规划中可优先选用DLR重建,以在极低辐射剂量下获得满足手术规划需求的图像质量。
- DLR图像噪声更低、SNR和CNR更高,读片时应注意其平滑效果对细微骨结构边缘显示的影响。
- DLR在骨结构显示和诊断信心方面主观评分更优,可用于FESS术前评估关键解剖结构。
局限性
- 本研究为回顾性分析。
- 原文未报告多中心数据。
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
OBJECTIVES: This study aimed to evaluate the quantitative and qualitative performances of ultra-low-dose computed tomography (CT) with deep learning image reconstruction (DLR) compared with those of hybrid iterative reconstruction (IR) for preoperative paranasal sinus (PNS) imaging.
MATERIALS AND METHODS: This retrospective analysis included 132 patients who underwent non-contrast ultra-low-dose sinus CT (0.03 mSv). Images were reconstructed using hybrid IR and DLR. Objective image quality metrics, including image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), noise power spectrum (NPS), and no-reference perceptual image sharpness, were assessed. Two board-certified radiologists independently performed subjective image quality evaluations.
RESULTS: The ultra-low-dose CT protocol achieved a low radiation dose (effective dose: 0.03 mSv). DLR showed significantly lower image noise (28.62 ± 4.83 Hounsfield units) compared to hybrid IR (140.70 ± 16.04, p < 0.001), with DLR yielding smoother and more uniform images. DLR demonstrated significantly improved SNR (22.47 ± 5.82 vs 9.14 ± 2.45, p < 0.001) and CNR (71.88 ± 14.03 vs 11.81 ± 1.50, p < 0.001). NPS analysis revealed that DLR reduced the noise magnitude and NPS peak values. Additionally, DLR demonstrated significantly sharper images (no-reference perceptual sharpness metric: 0.56 ± 0.04) compared to hybrid IR (0.36 ± 0.01). Radiologists rated DLR as superior in overall image quality, bone structure visualization, and diagnostic confidence compared to hybrid IR at ultra-low-dose CT.
CONCLUSION: DLR significantly outperformed hybrid IR in ultra-low-dose PNS CT by reducing image noise, improving SNR and CNR, enhancing image sharpness, and maintaining critical anatomical visualization, demonstrating its potential for effective preoperative planning with minimal radiation exposure.
KEY POINTS: Question Ultra-low-dose CT for paranasal sinuses is essential for patients requiring repeated scans and functional endoscopic sinus surgery (FESS) planning to reduce cumulative radiation exposure. Findings DLR outperformed hybrid IR in ultra-low-dose paranasal sinus CT. Clinical relevance Ultra-low-dose CT with DLR delivers sufficient image quality for detailed surgical planning, effectively minimizing unnecessary radiation exposure to enhance patient safety.
引用
- Otgonbaatar C, Lee D, Choi J, et al. Quantitative and qualitative assessment of ultra-low-dose paranasal sinus CT using deep learning image reconstruction: a comparison with hybrid iterative reconstruction. Eur Radiol. 2025. PMID: 40514598. doi:10.1007/s00330-025-11763-2
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。