深度学习重建可在超高分辨率颞骨CT中实现显著辐射剂量降低：一项遗体供体研究
Deep Learning Reconstruction Enables Substantial Radiation Dose Reduction in Ultra-High-Resolution Temporal Bone CT: a Body Donor Study.
文献信息
| PMID | 42773270 |
|---|---|
| 原文 | 在 PubMed 查看原文 ↗ |
| 发表日期 | 2026 |
| 作者 | Lavinia Brockstedt |
| 作者单位 | Department of Neuroradiology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany. |
| 期刊 | Clinical neuroradiology |
| SCI 分区 | Q2 |
| IF | 2.9 |
| 研究类型 | AI/ML · 临床 |
| 所属专科 | 耳科 |
中文摘要
目的： 深度学习重建可能使超高分辨率（UHR）颞骨CT实现显著辐射剂量降低，但其在临床相关剂量水平下的性能仍定义不足。本研究评估了在UHR容积模式颞骨CT中，厂商特定深度学习重建（DLR）与混合迭代重建（HIR）的比较，并旨在提出一种适应适应证的剂量优化框架。
方法： 在这项单中心遗体供体研究中，对来自10名无病理发现供体的20块颞骨在11个剂量水平（CTDIvol，5.1-30.7 mGy）进行扫描。图像使用标准分辨率（0.5 mm，512²矩阵）和UHR（0.25 mm，1024²和2048²矩阵）的HIR重建，以及UHR（0.25 mm，1024²矩阵）的DLR（AiCE Inner Ear）重建。三名放射科医师使用5点Likert量表独立评估10个解剖结构。在预定义区域测量信噪比。使用探索性结构特异性广义估计方程模型来估计作为辐射剂量和重建技术函数达到最佳图像质量的概率。
结果： 与HIR相比，DLR显著改善了骨性结构的显示（p < 0.001）。探索性剂量-反应分析显示了重建特异性轨迹，DLR在较低剂量水平下达到最佳图像质量的预测概率高于HIR。对于常规临床适应证，DLR在CTDIvol为13.3 mGy时达到诊断足够的图像质量，与HIR（CTDIvol 25.6 mGy）相比代表48%的剂量降低。对于包括镫骨和耳蜗在内的精细微解剖结构的高细节评估，DLR在CTDIvol为17.4 mGy时实现极佳显示，与HIR（CTDIvol 30.7 mGy）相比对应43%的剂量降低。
结论： 厂商特定DLR可在UHR容积模式颞骨CT中实现显著辐射剂量降低，同时保持高诊断图像质量。这些发现支持一种适应适应证的剂量优化框架，提示常规临床方案为CTDIvol 13.3 mGy，微解剖优化方案为CTDIvol 17.4 mGy。
英文摘要
PURPOSE: Deep learning reconstruction may enable substantial radiation dose reduction in ultra-high-resolution (UHR) temporal bone CT, but its performance across clinically relevant dose levels remains insufficiently defined. This study evaluated vendor-specific deep learning reconstruction (DLR) compared with hybrid iterative reconstruction (HIR) in UHR volume-mode temporal bone CT and aimed to propose an indication-adapted framework for dose optimization.
METHODS: In this single-center body donor study, 20 temporal bones from 10 donors without pathologic findings were scanned at 11 dose levels (CTDIvol, 5.1-30.7 mGy). Images were reconstructed using HIR at standard resolution (0.5 mm, 5122 matrix) and UHR (0.25 mm, 10242 and 20482 matrices), as well as DLR (AiCE Inner Ear) at UHR (0.25 mm, 10242 matrix). Three radiologists independently assessed 10 anatomical structures using a 5-point Likert scale. Signal-to-noise ratio was measured in predefined regions. Exploratory structure-specific generalized estimating equation models were used to estimate the probability of achieving optimal image quality as a function of radiation dose and reconstruction technique.
RESULTS: DLR significantly improved visualization of osseous structures compared with HIR (p < 0.001). The exploratory dose-response analysis demonstrated reconstruction-specific trajectories, with DLR achieving higher predicted probabilities of optimal image quality than HIR at lower dose levels. For routine clinical indications, diagnostically adequate image quality was achieved with DLR at a CTDIvol of 13.3 mGy, representing a 48% dose reduction compared with HIR (CTDIvol 25.6 mGy). For high-detail assessment of delicate microanatomical structures, including the stapes and cochlea, DLR achieved excellent visualization at a CTDIvol of 17.4 mGy, corresponding to a 43% dose reduction compared with HIR (CTDIvol 30.7 mGy).
CONCLUSION: Vendor-specific DLR enables substantial radiation dose reduction in UHR volume-mode temporal bone CT while maintaining high diagnostic image quality. These findings support an indication-adapted framework for dose optimization, suggesting a routine clinical protocol at CTDIvol 13.3 mGy and a microanatomy-optimized protocol at CTDIvol 17.4 mGy.