文献速递神经头颈MR

分形分析与磁共振成像语义特征鉴别颅内孤立性纤维性肿瘤与非典型脑膜瘤

Fractal analysis and magnetic resonance imaging (MRI) semantic features to identify intracranial solitary fibrous tumours and atypical meningiomas.
PubMed 文献 · Clin Radiol · 2026-02-10

回顾性纳入2019年1月至2023年12月诊断的81例患者(30例孤立性纤维性肿瘤、51例非典型脑膜瘤),在肿瘤最大横断面用ImageJ计算分形维数和空隙度,并结合临床数据与术前MRI语义特征构建逻辑回归列线图;孤立性纤维性肿瘤组硬膜尾征更少见、坏死率更高、空隙度更高,联合列线图鉴别AUC达0.968。

要点

  • 孤立性纤维性肿瘤较非典型脑膜瘤硬膜尾征更少见(P<.001)、坏死率更高(P<.001)。
  • 孤立性纤维性肿瘤的空隙度明显升高,单独鉴别AUC为0.770。
  • 联合硬膜尾征、坏死与空隙度的列线图AUC达0.968,特异度1.000。

核心结论

  • 术前MRI语义特征联合分形分析可无创鉴别孤立性纤维性肿瘤与非典型脑膜瘤,为优化临床治疗策略和手术决策提供理论依据。

研究设计与样本

  • 回顾性研究,共纳入81例患者(30例孤立性纤维性肿瘤、51例非典型脑膜瘤),诊断时间为2019年1月至2023年12月;在肿瘤最大横断面使用开源软件ImageJ(版本1.53k;美国国立卫生研究院)计算肿瘤区域的分形维数和空隙度;通过逻辑回归模型整合临床数据、术前MRI语义特征和分形分析参数构建可视化列线图。

关键影像表现/征象

  • 与星形细胞瘤?不,原文为:与ATM相比,SFT组硬膜尾征出现率显著更低(P<.001)。
  • 与ATM相比,SFT组坏死率显著更高(P<.001)。
  • 与ATM相比,SFT组空隙度明显升高。

诊断标准与关键数值

  • 硬膜尾征鉴别孤立性纤维性肿瘤与非典型脑膜瘤的AUC为0.825。
  • 坏死鉴别孤立性纤维性肿瘤与非典型脑膜瘤的AUC为0.741。
  • 空隙度鉴别孤立性纤维性肿瘤与非典型脑膜瘤的AUC为0.770。
  • 整合上述特征的诊断列线图AUC为0.968,准确度0.914、敏感度0.863、特异度1.000、阳性预测值1.000、阴性预测值0.811。

临床应用与阅片要点

  • 阅片时可关注硬膜尾征和坏死这两个MRI语义特征,并结合分形分析的空隙度参数辅助鉴别孤立性纤维性肿瘤与非典型脑膜瘤。

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

AIM: Atypical meningioma (ATM) and solitary fibrous tumour (SFT) are two prevalent meningeal tumours that pose significant challenges in preoperative differentiation. This study aims to distinguish between them using fractal analysis and magnetic resonance imaging (MRI) semantic features.

MATERIALS AND METHODS: This retrospective study included a total of 81 patients, comprising 30 SFTs and 51 ATMs, diagnosed between January 2019 and December 2023. At the maximal tumour cross-section, fractal dimension (FD) and lacunarity were computed for the tumour region using the open-source software ImageJ (version 1.53k; National Institutes of Health). A visual nomogram was subsequently developed to differentiate SFT from ATM by integrating clinical data, preoperative MRI semantic features, and fractal analysis parameters through logistic regression model.

RESULTS: Compared with ATM, the SFT group exhibited a significantly lower prevalence of dural tail sign (P<.001) but a higher necrosis rate (P<.001), along with markedly elevated lacunarity. The area under the curve (AUC) for differentiating the two groups was 0.825 for dural tail sign, 0.741 for necrosis, and 0.770 for lacunarity. The diagnostic nomogram incorporating these features demonstrated further improved performance, achieving an AUC of 0.968, with corresponding accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of 0.914, 0.863, 1.000, 1.000, and 0.811, respectively.

CONCLUSION: Preoperative MRI semantic features combined with fractal analysis enable noninvasive differentiation between SFT and ATM, providing a valuable theoretical foundation for optimising clinical treatment strategies and surgical decision-making.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Zhao Z, Bai R, Zhang J, et al. Fractal analysis and magnetic resonance imaging (MRI) semantic features to identify intracranial solitary fibrous tumours and atypical meningiomas. Clin Radiol. 2026. PMID: 41875738. doi:10.1016/j.crad.2026.107282

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。