文献速递腹部泌尿生殖MR

深度学习重建实现直肠癌分期加速T2加权MRI:一项关于不同NEX值下诊断一致性的前瞻性研究

Deep learning reconstruction enables accelerated T2-weighted MRI for rectal cancer staging: a prospective study of diagnostic consistency across NEX value reduction.
PubMed 文献 · Abdom Radiol (NY) · 2026-03-24

这项前瞻性研究纳入35例直肠癌初诊分期患者,比较深度学习重建(DLR)与传统重建(ConR)在NEX值4、2、1下T2加权MRI的图像质量、判读一致性和扫描效率。结果显示DLR各NEX序列图像质量均显著优于ConR(均P<0.001),FSENEX2-DLR在定性评分中最高且扫描时间较NEX=4缩短49%,DLR序列间一致性显著高于ConR。结论认为DLR联合降低NEX可维持直肠癌分期诊断一致性,FSENEX2-DLR可能兼顾采集效率与图像质量。

要点

  • FSENEX2-DLR扫描时间2分1秒,较NEX=4的3分55秒缩短49%,定性评分(组织对比、边缘锐利度、肿瘤特征、整体图像质量)最高。
  • DLR序列间分期参数一致性(κ范围0.715-0.964)显著高于ConR序列(κ范围0.505-0.811)。
  • FSENEX4-DLR的SNR和CNR最高,FSENEX2-DLR次之,所有DLR序列定量指标均显著优于对应ConR(均P<0.001)。

核心结论

  • DLR联合降低NEX值可维持直肠癌分期的诊断一致性;FSENEX2-DLR实现49%扫描时间缩短并保持诊断一致性,可能在采集效率与图像质量之间提供合理平衡;未来需病理组织学对照研究验证诊断准确性。

研究设计与样本

  • 前瞻性研究,连续纳入2022年7月至2023年4月因直肠癌初诊分期行MRI的35例患者,每例接受NEX值4、2、1的T2加权MRI,分别用ConR和DLR重建,共生成6组图像;由两名放射科医师独立评估T分期、N分期、EMVI和MRF状态。

关键影像表现/征象

  • 定性评估中,DLR序列在所有NEX值下图像质量均显著优于ConR序列(均P<0.001)。
  • 所有序列中FSENEX2-DLR的组织对比、边缘锐利度、肿瘤特征和整体图像质量定性评分最高。
  • 定量分析显示FSENEX4-DLR的SNR和CNR最高,FSENEX2-DLR次之,所有DLR序列均显著优于对应ConR序列(均P<0.001)。

诊断标准与关键数值

  • 定性评估采用5分制,评分项目包括组织对比、边缘锐利度、直肠壁形态、肿瘤特征、整体图像质量和噪声。
  • 序列间一致性分析显示所有分期参数(T分期、N分期、EMVI、MRF)的平均κ为0.736-0.800,呈中等至几乎完全一致。
  • DLR序列间一致性κ范围为0.715-0.964,ConR序列间一致性κ范围为0.505-0.811。

临床应用与阅片要点

  • DLR联合降低NEX值可在缩短扫描时间的同时维持直肠癌分期判读一致性,FSENEX2-DLR的定性图像质量评分最高。
  • FSENEX4-DLR的SNR和CNR最高,FSENEX2-DLR次之,阅片时可根据对信噪比与扫描效率的需求选择序列。
  • DLR序列间分期一致性高于ConR序列,提示降低NEX值时采用DLR可能减少序列间判读差异。

局限性

  • 原文指出未来需病理组织学对照研究验证诊断准确性。

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, interpretation consistency, and scanning efficiency of deep learning-based reconstruction (DLR) algorithm (AIR™ Recon DL; GE Healthcare) compared with conventional reconstruction (ConR) in T2-weighted MRI for rectal cancer across different number of excitations (NEX) values.

METHODS: This prospective study enrolled consecutive patients undergoing MRI for primary staging of rectal cancer between July 2022 and April 2023. Each patient underwent T2-weighted MRI with three NEX values (4, 2, and 1), reconstructed using both ConR and DLR methods, generating six image sets. Image quality was assessed quantitatively (signal-to-noise ratio, contrast-to-noise ratio) and qualitatively using a 5-point scale for tissue contrast, edge sharpness, rectal wall morphology, tumor characteristics, overall image quality, and noise. Two radiologists independently evaluated staging parameters including T stage, N stage, extramural vascular invasion (EMVI), and mesorectal fascia (MRF) status. Inter-observer and inter-sequence agreement were analyzed.

RESULTS: Thirty-five patients completed all six imaging protocols. Acquisition times were 3 min 55s (NEX = 4), 2 min 1s (NEX = 2, 49% reduction), and 1 min 4s (NEX = 1, 73% reduction). For qualitative assessment, DLR sequences demonstrated significantly superior image quality compared to ConR sequences across all NEX values (all P < 0.001). Among all sequences, FSENEX2-DLR achieved the highest qualitative scores for tissue contrast, edge sharpness, tumor characteristics, and overall image quality. Quantitative analysis showed FSENEX4-DLR demonstrated the highest SNR and CNR values, followed by FSENEX2-DLR, with all DLR sequences significantly outperforming their ConR counterparts (all P < 0.001). Inter-sequence agreement analysis revealed substantial to almost perfect consistency for all staging parameters (mean κ: 0.736-0.800). DLR sequences demonstrated significantly higher inter-sequence agreement (range: 0.715-0.964) compared to ConR sequences (range: 0.505-0.811).

CONCLUSION: DLR with reduced NEX values maintains diagnostic consistency in rectal cancer staging. FSENEX2-DLR, achieving 49% scanning time reduction while preserving diagnostic consistency, may offer a reasonable balance between acquisition efficiency and image quality. Future studies with histopathological correlation are needed to validate diagnostic accuracy.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Yan W, Li S, Liang H, et al. Deep learning reconstruction enables accelerated T2-weighted MRI for rectal cancer staging: a prospective study of diagnostic consistency across NEX value reduction. Abdom Radiol (NY). 2026. PMID: 41874617. doi:10.1007/s00261-026-05460-x

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。