文献速递腹部技术与安全CT

深度学习重建改善直肠癌40 keV虚拟单能图像质量

Deep learning image reconstruction improves 40 keV virtual monoenergetic image quality in rectal cancer.
PubMed 文献 · Eur J Radiol · 2026-01-03

结果显示40 keV DLIR-H图像质量主观评分最高,显著降低噪声并提高CNR;对壁外静脉侵犯和T分期诊断效能仅轻度改善。

要点

  • 直肠癌双能CT低keV结合DLIR可在降低碘剂量同时改善图像质量
  • 40 keV DLIR-H主观图像质量最佳,可作为直肠癌术前评估优先重建方案
  • 低keV提高碘对比但诊断EMVI和T分期的增益有限,需结合形态学征象

核心结论

  • DLIR尤其是DLIR-H可显著改善40 keV虚拟单能图像质量,但对直肠癌EMVI和T分期的诊断效能仅轻度提升。

研究设计与样本

  • 图像行70 keV ASIR-V 40%、40 keV ASIR-V 40%、40 keV DLIR-M和DLIR-H四种重建,以病理结果为EMVI和T分期参考标准

关键影像表现/征象

  • 40 keV ASIR-V及DLIR图像较70 keV ASIR-V在CT衰减值、噪声、CNR、SNR、边缘上升斜率及噪声功率谱曲线下面积均显著改善
  • DLIR-M和DLIR-H的图像噪声和CNR优于40 keV ASIR-V,DLIR-H主观图像质量评分最高

诊断标准与关键数值

  • EMVI诊断AUC:DLIR-H为0.882,略高于ASIR-V但原文未给出具体对照数值
  • T分期诊断AUC:DLIR-H为0.592,略高于ASIR-V但原文未给出具体对照数值
  • 与70 keV ASIR-V相比,40 keV ASIR-V、DLIR-M和DLIR-H在CT衰减、噪声、CNR、SNR、ERS和NPS曲线下面积均P<0.001

临床应用与阅片要点

  • 直肠癌术前双能CT评估可优先采用40 keV VMI配合DLIR-H重建以平衡碘对比与噪声
  • 低keV加DLIR方案有助于降低碘对比剂用量,适合肾功能受限或需减少碘负荷的患者
  • EMVI和T分期判读不能单纯依赖重建算法改善,仍应重点观察血管旁软组织、肠周脂肪间隙等形态学征象

局限性

  • 原文为单中心研究且样本量较小,相关诊断效能数值解读需谨慎
  • 未提供DLIR与ASIR-V之间诊断效能差异的显著性检验结果

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

BACKGROUND: Accurate preoperative evaluation of rectal cancer is essential for staging and treatment planning. Low-energy virtual monoenergetic imaging (VMI) enhances iodine contrast in dual-energy computed tomography (DECT) but increases image noise. Deep learning image reconstruction (DLIR) may mitigate this issue, but its effectiveness for 40 keV VMI in rectal cancer is underexplored.

OBJECTIVE: To evaluate the impact of DLIR on 40 keV VMI image quality and its diagnostic performance in assessing extramural venous invasion (EMVI) and T staging, compared to adaptive statistical iterative reconstruction (ASIR-V).

METHODS: Sixty-two patients with rectal adenocarcinoma underwent preoperative DECT using a low-iodine contrast protocol (1 mL/kg, 300 mg iodine/mL). Images were reconstructed at 70 keV ASIR-V 40 %, 40 keV ASIR-V 40 %, and 40 keV DLIR (medium [DLIR-M] and high [DLIR-H] settings). Objective and subjective image quality were compared using repeated-measures ANOVA or Friedman tests. Pathological findings were used as the reference standard for EMVI and T staging.

RESULTS: Both 40 keV ASIR-V 40 %, DLIR-M, and DLIR-H significantly improved image quality compared to 70 keV ASIR-V, with improvements in CT attenuation, image noise, contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), edge rise slope (ERS), and the area under the noise power spectrum (NPS) curve (all P < 0.001). DLIR-M and DLIR-H outperformed 40 keV ASIR-V in terms of image noise and CNR. Subjective image quality scores were highest with DLIR-H. In diagnostic performance, DLIR-H achieved slightly better results for EMVI (AUC = 0.882) and T staging (AUC = 0.592) compared to ASIR-V.

CONCLUSION: DLIR, particularly DLIR-H, significantly improves 40 keV VMI image quality but offers mild improvement in diagnostic performance for EMVI and T staging. The combination of low-keV VMI and DLIR provides high-quality imaging with reduced iodine doses, making it a promising approach for optimized DECT protocols in rectal cancer.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhang, Long, Zhang, et al. Deep learning image reconstruction improves 40 keV virtual monoenergetic image quality in rectal cancer. Eur J Radiol. 2026. PMID: 41520415. doi:10.1016/j.ejrad.2025.112646

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。