文献速递胸部技术与安全CT

基于深度学习的图像域重建提升超低剂量CT联合自适应统计迭代重建-V的图像质量与肺结节检出

Deep learning-based image domain reconstruction enhances image quality and pulmonary nodule detection in ultralow-dose CT with adaptive statistical iterative reconstruction-V.
PubMed 文献 · Eur Radiol · 2025-01-10

210例肺癌筛查患者行低剂量CT(0.81±0.28 mSv)与超低剂量CT(0.17±0.03 mSv),超低剂量CT分别用ASiR-V重建和DLIR后处理;DLIR后处理较ASiR-V降低噪声60%、提高主观图像质量与结节检出率(87.0% vs 82.1%),并提高结节测量准确性与锐利度。

要点

  • DLIR图像域后处理使超低剂量CT噪声较ASiR-V降低60%,并低于低剂量CT(p<0.001)。
  • 超低剂量CT结节总检出率DLIR后处理87.0%(403/463)高于ASiR-V的82.1%(380/463)(p<0.001)。
  • DLIR后处理使直径>1 mm结节的直径差异百分比降至0.5%(对比低剂量CT),ASiR-V为2.9%(p=0.009)。

核心结论

  • 基于DLIR的图像域后处理可改善ASiR-V重建超低剂量CT的图像质量、结节检出率、结节成像锐利度和结节测量准确性。

研究设计与样本

  • 共210例接受肺癌筛查的患者,行低剂量CT(平均±标准差,0.81±0.28 mSv)和超低剂量CT(0.17±0.03 mSv)扫描,超低剂量CT图像用ASiR-V重建(ULDCT-ASiR-V)并经DLIR后处理(ULDCT-DLIR),以低剂量CT结果为参考,由三名放射科医师检出和测量肺结节。

关键影像表现/征象

  • ULDCT-DLIR的图像噪声较ULDCT-ASiR-V降低60%,且低于低剂量CT(p<0.001)。
  • ULDCT-DLIR的主观图像质量评分4.4(4.1,4.6)高于ULDCT-ASiR-V的3.6(3.1,3.9)(p<0.001)。
  • ULDCT-DLIR的结节成像锐利度评分4.0±0.68显著高于ULDCT-ASiR-V的3.2±0.50(p<0.001)。

诊断标准与关键数值

  • 以低剂量CT检出结果为参考,共检出463个结节。
  • 结节总检出率:ULDCT-ASiR-V为82.1%(380/463),ULDCT-DLIR为87.0%(403/463)(p<0.001)。
  • 直径>1 mm结节的直径差异百分比:ULDCT-ASiR-V对比低剂量CT为2.9%,ULDCT-DLIR对比低剂量CT为0.5%(p=0.009)。
  • 结节显示清晰度采用五分Likert量表评估。

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

OBJECTIVES: To evaluate the image quality and lung nodule detectability of ultralow-dose CT (ULDCT) with adaptive statistical iterative reconstruction-V (ASiR-V) post-processed using a deep learning image reconstruction (DLIR)-based image domain compared to low-dose CT (LDCT) and ULDCT without DLIR.

MATERIALS AND METHODS: A total of 210 patients undergoing lung cancer screening underwent LDCT (mean ± SD, 0.81 ± 0.28 mSv) and ULDCT (0.17 ± 0.03 mSv) scans. ULDCT images were reconstructed with ASiR-V (ULDCT-ASiR-V) and post-processed using DLIR (ULDCT-DLIR). The quality of the three CT images was analyzed. Three radiologists detected and measured pulmonary nodules on all CT images, with LDCT results serving as references. Nodule conspicuity was assessed using a five-point Likert scale, followed by further statistical analyses.

RESULTS: A total of 463 nodules were detected using LDCT. The image noise of ULDCT-DLIR decreased by 60% compared to that of ULDCT-ASiR-V and was lower than that of LDCT (p < 0.001). The subjective image quality scores for ULDCT-DLIR (4.4 [4.1, 4.6]) were also higher than those for ULDCT-ASiR-V (3.6 [3.1, 3.9]) (p < 0.001). The overall nodule detection rates for ULDCT-ASiR-V and ULDCT-DLIR were 82.1% (380/463) and 87.0% (403/463), respectively (p < 0.001). The percentage difference between diameters > 1 mm was 2.9% (ULDCT-ASiR-V vs. LDCT) and 0.5% (ULDCT-DLIR vs. LDCT) (p = 0.009). Scores of nodule imaging sharpness on ULDCT-DLIR (4.0 ± 0.68) were significantly higher than those on ULDCT-ASiR-V (3.2 ± 0.50) (p < 0.001).

CONCLUSION: DLIR-based image domain improves image quality, nodule detection rate, nodule imaging sharpness, and nodule measurement accuracy of ASiR-V on ULDCT.

KEY POINTS: Question Deep learning post-processing is simple and cheap compared with raw data processing, but its performance is not clear on ultralow-dose CT. Findings Deep learning post-processing enhanced image quality and improved the nodule detection rate and accuracy of nodule measurement of ultralow-dose CT. Clinical relevance Deep learning post-processing improves the practicability of ultralow-dose CT and makes it possible for patients with less radiation exposure during lung cancer screening.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Ye K, Xu L, Pan B, et al. Deep learning-based image domain reconstruction enhances image quality and pulmonary nodule detection in ultralow-dose CT with adaptive statistical iterative reconstruction-V. Eur Radiol. 2025. PMID: 39792163. doi:10.1007/s00330-024-11317-y

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。