人工智能去噪在心脏光子计数CT中的应用：减轻BMI相关噪声恶化并保持临床可互换性
本研究回顾性纳入100例接受非对比冠状动脉钙化评分和增强冠状动脉CT血管成像的双源光子计数探测器CT患者，比较标准量子迭代重建与基于人工智能的去噪算法。结果显示AID显著改善主观图像质量，降低总体噪声幅度约64%（CAC）和78%（CCTA），并稳健衰减BMI驱动的噪声升级44%（CAC）和78%（CCTA），同时保持空间分辨率稳定。贝叶斯等效区间分析证实两种重建在Agatston评分、CAD-RADS分级和斑块特征方面具有严格诊断等效性（概率>0.999）。
要点
- AID可显著降低CAC和CCTA图像噪声并减轻BMI相关噪声恶化，且不损失空间分辨率。
- AID与QIR在Agatston评分、CAD-RADS分级和斑块特征方面诊断等效，可互换使用。
- CAC数据集噪声纹理出现平滑化，但CCTA噪声纹理稳定，阅片时需注意。
关键影像表现/征象
- AID显著改善主观图像质量，并降低总体噪声幅度约64%（CAC）和78%（CCTA）（p<0.001）。
- AID稳健衰减BMI驱动的噪声升级44%（CAC）和78%（CCTA）（交互作用p<0.001）。
- CCTA数据集噪声纹理稳定，而CAC数据集显示平滑化。
- 空间分辨率得以保留，并在不同患者体型间保持稳定。
诊断标准与关键数值
- 贝叶斯ROPE分析显示QIR与AID在连续Agatston评分、分类CAD-RADS严重程度和特定冠状动脉斑块成分方面实际等效概率>0.999。
临床应用与阅片要点
- 日常阅片和报告中，AID重建图像可用于CAC评分和CCTA评估，与QIR结果可互换。
- 注意CAC数据集AID可能导致噪声纹理平滑化，但空间分辨率保持稳定，不影响诊断等效性。
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
OBJECTIVES: To evaluate whether an artificial intelligence-based denoising (AID) algorithm can effectively attenuate body mass index (BMI)-related noise degradation in cardiac photon-counting detector CT (PCD-CT) while maintaining strict quantitative diagnostic equivalence and clinical interchangeability compared with quantum iterative reconstruction (QIR).
MATERIALS AND METHODS: This retrospective study included 100 patients undergoing non-contrast coronary artery calcium (CAC) scoring and contrast-enhanced coronary CT angiography (CCTA) on a dual-source PCD-CT. Images were reconstructed using standard QIR and a PCD-CT-weighted AID algorithm. Subjective image quality was assessed by four blinded raters. Objective metrics included noise magnitude (noise power spectrum) and spatial resolution (edge rise distance). Frequentist generalized estimating equations (GEE) evaluated reconstruction effects and BMI interactions. Clinical interchangeability (Agatston scoring, coronary age, CAD-RADS, and plaque characterization) was assessed using Bayesian regions of practical equivalence (ROPE).
RESULTS: AID significantly improved subjective image quality and reduced overall noise magnitude by approximately 64 % in CAC and 78 % in CCTA (p<0.001). GEE models revealed that AID robustly attenuated BMI-driven noise escalation by 44 % (CAC) and 78 % (CCTA, p<0.001 for interactions in both). Noise texture was stable in CCTA datasets, but revealed smoothening in CAC datasets. However, spatial resolution was preserved and remained stable across varying patient habitus. ROPE analysis proved strict diagnostic equivalence between QIR and AID, yielding near-certain probabilities (>0.999) of practical equivalence for continuous Agatston scores, categorical CAD-RADS severity classification, and specific coronary plaque composition.
CONCLUSIONS: The PCD-CT-weighted AID algorithm improves subjective and objective image quality in both CAC and CCTA, while maintaining diagnostic equivalence and workflow efficiency compared to QIR.
引用
- Urban L, Berger J, Brendel JM, et al. Artificial intelligence denoising in cardiac photon-counting CT: mitigating BMI-related noise degradation while maintaining clinical interchangeability. Eur J Radiol. 2026. PMID: 42142519. doi:10.1016/j.ejrad.2026.112921
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。