文献速递头颈神经MR

深度学习加速DIR序列在视神经病变MRI中的应用

Deep Learning Assisted Double Inversion Recovery improves Focal Lesion Detection in Optic Neuropathy.
PubMed 文献 · AJNR Am J Neuroradiol · 2026-06-17

该前瞻性研究纳入75例疑似视神经病变患者,比较DL加速DIR与常规MRI的采集时间、图像质量和诊断信心。结果显示DL重建使总采集时间缩短43.57%,DIR-DL图像质量优级比例达87.56%,DIR与STIR相比检出更长病灶,且DIR与DIR-DL具有可互换性。

要点

  • DIR-DL显著缩短扫描时间,总采集时间从22分55秒降至12分56秒
  • DIR序列较STIR可检出更长的视神经病灶范围
  • DIR-DL与常规DIR图像质量和诊断信心相当,可互换使用

核心结论

  • DIR-DL在临床应用中可显著缩短扫描时间,同时提供优于常规STIR的图像质量和相当的诊断信心

研究设计与样本

  • 前瞻性研究,纳入75例疑似视神经病变患者(平均年龄37±20岁,47例女性),2024年4月至9月期间临床转诊行视神经MRI
  • 每位受试者均接受常规MRI(含STIR、T2-FS、T1WI、Cube T1-FS序列)和DL加速方案(另加DIR序列)
  • 三位放射科医师采用4分Likert量表独立评估病灶范围、整体图像质量、感知SNR、锐利度、伪影和诊断信心

关键影像表现/征象

  • DIR-DL整体图像质量优级比例高于常规序列(87.56%对82.89%)
  • DIR和DIR-DL检出的病灶长度显著长于STIR(Beta=7.59%和7.40%,均Padj<0.001)
  • STIR与STIR-DL及DIR与DIR-DL之间具有几乎完美/极佳的一致性(κ=0.95和0.85)

诊断标准与关键数值

  • STIR与STIR-DL可互换(IEI=0.02,90%CI在±0.05内)
  • DIR与DIR-DL可互换(IEI=0.04,90%CI在±0.05内)
  • DIR和DIR-DL特异度高于STIR和STIR-DL

临床应用与阅片要点

  • 视神经MRI评估中DIR序列较STIR对病灶范围显示更敏感,建议纳入常规方案
  • DL加速DIR可在不损失诊断信心的前提下大幅缩短扫描时间,适合临床推广应用

局限性

  • 采用零膨胀两阶段方法(检测用逻辑回归,病灶范围用线性混合模型)进行分析
  • 研究为单中心前瞻性设计,样本量75例

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 compare the acquisition time, image quality, and diagnostic confidence of DL-accelerated DIR (DIR-DL) with conventional MRI in patients undergoing imaging for suspected optic neuropathy.

MATERIALS AND METHODS: This prospective, study enrolled 75 consecutive patients (mean age, 37 ± 20 years; 47 female) with suspected optic neuropathy who were clinically referred for optic nerve MRI between April and September 2024. Each participant underwent both conventional MRI (including STIR, T2-FS, T1WI, and Cube T1-FS sequences) and DL-accelerated protocol (with DIR sequence in addition). Three radiologists independently assessed lesion extent, overall image quality, perceived SNR, sharpness, artifacts, and diagnostic confidence using a 4-point Likert scale (1 = poor; 4 = excellent). Lesion lengths were normalized to optic nerve length and expressed as percentages. Because of zero inflation, a two-stage approach (logistic regression for detection, linear mixed model for lesion extent) was applied. Inter-method agreement between sequence pairs was assessed using weighted Cohen's κ (quadratic weights) for segmental, total lesion length percentages and image quality scores. Interchangeability between sequences was tested using the individual equivalence index (IEI, margin 5%). Paired t-tests compared signal-to-noise ratios, and all P values were FDR-adjusted.

RESULTS: DL reconstruction reduced total acquisition time by 43.57% (from 22 min 55 s to 12 min 56 s). DIR-DL presented a higher proportion of excellent overall image quality than conventional sequences (87.56% excellent readings vs. 82.89%). DIR and DIR-DL detected significantly longer lesion lengths than STIR (Beta = 7.59% and 7.40%, both Padj<0.001). STIR vs STIR-DL and DIR vs DIR-DL were interchangeable (IEI = 0.02 and 0.04, 90% CI within ±0.05), with almost perfect/excellent agreement (κ = 0.95 and 0.85). DIR and DIR-DL had higher specificity than STIR and STIR-DL.

CONCLUSION: In a clinical setting, DIR-DL reduced scan time while providing superior image quality and comparable diagnostic confidence to standard STIR MRI for optic nerve evaluation.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Zhang, Cheng, Liu, et al. Deep Learning Assisted Double Inversion Recovery improves Focal Lesion Detection in Optic Neuropathy. AJNR Am J Neuroradiol. 2026. PMID: 42309650. doi:10.3174/ajnr.A9480

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。