文献速递神经技术与安全CT

基于深度学习的去噪算法使神经放射创伤CT在25%辐射剂量下实现高质量全诊断

Deep Learning-Based Denoising Enables High-Quality, Fully Diagnostic Neuroradiological Trauma CT at 25% Radiation Dose.
PubMed 文献 · Acad Radiol · 2024-09-18

这项回顾性单中心研究纳入100例神经放射创伤CT患者,比较全剂量(100%)与低剂量(25%)模拟扫描经迭代重建(IR2)和深度学习去噪(DLD)处理后的图像质量与临床终点。结果显示25%剂量DLD的主观评分与100%剂量IR2无显著差异,骨折检出等效,出血检出敏感性在25%剂量IR2下降而DLD维持与100%IR2相当,特异性均稳健。

要点

  • 25%剂量DLD的主观图像质量与100%剂量IR2无显著差异。
  • 25%剂量IR2在出血检出上出现敏感性损失,而DLD在25%和100%剂量下均保持与100%IR2相当的敏感性。
  • 所有比较均显示稳健的特异性。

核心结论

  • 所评估的DLD算法能在初始辐射剂量的25%下实现高质量、完全可诊断的CT扫描,并通过减少不必要辐射暴露改善患者护理。

研究设计与样本

  • 回顾性单中心研究,纳入100例神经放射创伤CT患者,全剂量(100%)与低剂量(25%)模拟扫描分别经迭代重建(IR2)和深度学习去噪(DLD)处理,由四名神经放射科医生进行主观与客观图像质量评估及临床终点分析,采用贝叶斯方法计算敏感度和特异度及其95%可信区间。

诊断标准与关键数值

  • 主观分析:100% DLD评分优于100% IR2和25% IR2(p < 0.001);25% DLD与100% IR2无显著差异。
  • 客观分析:CT值无显著差异;25%剂量下DLD和IR2的噪声高于100%剂量(p < 0.001);DLD在两种剂量水平下噪声均低于IR2(p < 0.001)。
  • 临床终点:所有数据集骨折检出与100% IR2等效;25% IR2出血检出敏感性损失;DLD(25%和100%)维持与100% IR2相当的敏感性;所有比较特异性均稳健。

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

RATIONALE AND OBJECTIVES: Traumatic neuroradiological emergencies necessitate rapid and accurate diagnosis, often relying on computed tomography (CT). However, the associated ionizing radiation poses long-term risks. Modern artificial intelligence reconstruction algorithms have shown promise in reducing radiation dose while maintaining image quality. Therefore, we aimed to evaluate the dose reduction capabilities of a deep learning-based denoising (DLD) algorithm in traumatic neuroradiological emergency CT scans.

MATERIALS AND METHODS: This retrospective single-center study included 100 patients with neuroradiological trauma CT scans. Full-dose (100%) and low-dose (25%) simulated scans were processed using iterative reconstruction (IR2) and DLD. Subjective and objective image quality assessments were performed by four neuroradiologists alongside clinical endpoint analysis. Bayesian sensitivity and specificity were computed with 95% credible intervals.

RESULTS: Subjective analysis showed superior scores for 100% DLD compared to 100% IR2 and 25% IR2 (p < 0.001). No significant differences were observed between 25% DLD and 100% IR2. Objective analysis revealed no significant CT value differences but higher noise at 25% dose for DLD and IR2 compared to 100% (p < 0.001). DLD exhibited lower noise than IR2 at both dose levels (p < 0.001). Clinical endpoint analysis indicated equivalence to 100% IR2 in fracture detection for all datasets, with sensitivity losses in hemorrhage detection at 25% IR2. DLD (25% and 100%) maintained comparable sensitivity to 100% IR2. All comparisons demonstrated robust specificity.

CONCLUSIONS: The evaluated algorithm enables high-quality, fully diagnostic CT scans at 25% of the initial radiation dose and improves patient care by reducing unnecessary radiation exposure.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Gohla G, Estler A, Zerweck L, et al. Deep Learning-Based Denoising Enables High-Quality, Fully Diagnostic Neuroradiological Trauma CT at 25% Radiation Dose. Acad Radiol. 2024. PMID: 39294053. doi:10.1016/j.acra.2024.08.018

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。