文献速递神经MR

多发性硬化患者QSM上顺磁性边缘病灶的深度学习自动检测与负荷评估

Deep Learning-Based Automated Detection and Burden Assessment of Paramagnetic Rim Lesions on Quantitative Susceptibility Mapping in Patients With Multiple Sclerosis.
PubMed 文献 · Korean J Radiol · 2026-06-16

该研究回顾性纳入106例疑似多发性硬化患者及117例临床意义队列,基于QSM及QSM联合FLAIR构建3D nnU-Net模型,自动检测顺磁性边缘病灶并评估其负荷。内部测试集中QSM单序列模型病灶级敏感度与精确度更高,两模型患者级敏感度在时间测试集均达100%。自动PRL负荷较高与认知功能较差相关(P=0.002)。

要点

  • QSM单序列模型检测PRL性能可与QSM+FLAIR相当,临床可考虑简化流程
  • 两模型在时间测试集对PRL阳性患者识别敏感度均为100%(8/8)
  • 自动评估的PRL负荷与认知损害相关,提示其可作为MS评估标志物

核心结论

  • QSM单序列模型在PRL检测与负荷评估方面与QSM+FLAIR配置性能相当,同时提供更简化的单序列流程
  • 自动PRL负荷与认知损害相关,提示其具有作为多发性硬化评估生物标志物的潜力

研究设计与样本

  • 回顾性研究,收集2025年1月至12月106例疑似多发性硬化患者的脑MRI数据,包括QSM和三维FLAIR序列
  • 数据集分为探索集84例(训练54例、内部测试30例)和时间测试集22例,PRL由人工分割建立金标准
  • 采用3D nnU-Net框架训练QSM-only和QSM+FLAIR两种配置,用于患者级分类、病灶级检测及PRL负荷评估
  • 另设117例临床意义队列,用于评估自动PRL负荷与临床结局的关联

关键影像表现/征象

  • 探索集67.9%为女性,中位年龄40.0岁,82.1%(69/84)患者为PRL阳性,共705个PRL
  • 病灶表现为顺磁性边缘,需在定量磁敏感图上结合人工分割作为训练金标准进行识别

诊断标准与关键数值

  • 内部测试集病灶级敏感度:QSM-only模型为72.4%(147/203),高于QSM+FLAIR模型的62.1%(126/203),P=0.004
  • 内部测试集病灶级精确度:QSM-only模型为78.2%(147/188),高于QSM+FLAIR模型的65.6%(126/192),P=0.009
  • 时间测试集病灶级敏感度:QSM-only模型为45.3%(29/64),QSM+FLAIR模型为54.7%(35/64),P=0.181
  • 时间测试集患者级敏感度:两个模型均为100%(8/8);两测试集患者级分类无显著差异
  • 自动PRL负荷较高与认知功能较差相关,P=0.002

临床应用与阅片要点

  • QSM单序列可作为检测PRL的简化流程,无需额外依赖FLAIR序列即可完成自动检测
  • 对MS患者影像报告中PRL负荷较高的病例,应关注其认知功能损害的潜在风险
  • 人工分割仍为训练金标准,临床部署前需注意模型在不同时间数据上的泛化表现

局限性

  • 回顾性研究设计,可能存在选择偏倚
  • 时间测试集病灶级敏感度不高,QSM-only为45.3%,QSM+FLAIR为54.7%
  • 研究纳入疑似MS患者,未说明最终确诊标准及排除条件

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

OBJECTIVE: This study aimed to develop a deep learning (DL) framework for automated detection and burden assessment of paramagnetic rim lesions (PRLs) by using quantitative susceptibility mapping (QSM) in multiple sclerosis (MS), compare QSM-only and QSM + fluid-attenuated inversion recovery (FLAIR) configurations, and evaluate the clinical relevance of the automated PRL burden.

MATERIALS AND METHODS: Brain magnetic resonance imaging data, including QSM and three-dimensional (3D) FLAIR data, obtained between January and December 2025, were retrospectively collected from 106 patients suspected of having MS. The dataset consisted of an exploration set (n = 84)-divided into training (n = 54) and internal test (n = 30) sets-and a temporal test set (n = 22). The PRLs were manually segmented to establish the ground truth. A 3D nnU-Net framework was trained using the QSM-only and QSM + FLAIR configurations for patient-level classification, lesion-level detection, and PRL burden assessment. A separate clinical implication cohort (n = 117) was used to assess the associations between the automated PRL burden and clinical outcomes.

RESULTS: In the exploration set (median age: 40.0 years; 67.9% female), 69 (82.1%) patients were PRL-positive, with a total of 705 PRLs. In the internal test set, the QSM-only model showed higher lesion-level sensitivity (72.4% [147/203] vs. 62.1% [126/203], P = 0.004) and precision (78.2% [147/188] vs. 65.6% [126/192], P = 0.009). In the temporal test set, the lesion-level sensitivity was 45.3% (29/64) for the QSM-only model and 54.7% (35/64) for the QSM + FLAIR model (P = 0.181), whereas both models achieved 100% (8/8) patient-level sensitivity. No significant differences were observed in patient-level classification in either test set. A higher automated PRL burden was associated with poorer cognition (P = 0.002).

CONCLUSION: QSM-based DL models enabled automated detection and burden assessment of PRLs in MS, with the QSM-only model performing comparably to QSM + FLAIR while offering a simplified single-sequence pipeline. The association between the automated PRL burden and cognitive impairment highlights its potential as a biomarker for MS assessment.

来源:Korean J Radiol,查看原文。版权归原作者所有。

引用

  1. Jeong, Seo, Moon, et al. Deep Learning-Based Automated Detection and Burden Assessment of Paramagnetic Rim Lesions on Quantitative Susceptibility Mapping in Patients With Multiple Sclerosis. Korean J Radiol. 2026. PMID: 42366024. doi:10.3348/kjr.2026.0103

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。