文献速递胸部CT

影像组学视角下的胸腺瘤:CT影像组学特征用于组织学分级与疾病分期的初步证据

Thymomas under the radiomic lens: preliminary evidence of CT-radiomics signatures for histological grading and disease staging.
PubMed 文献 · Radiol Med · 2025-10-01

本研究分析37例胸腺瘤患者的静脉期CT影像,提取107个影像组学特征,评估其与WHO组织学分级及Masaoka-Koga/TNM分期的相关性。11个特征可区分早期与晚期胸腺瘤(p<0.05),7个特征可区分低危与高危胸腺瘤(p<0.05);LASSO模型对Masaoka-Koga/TNM分期的AUC为0.9,对WHO分级的AUC为0.82。

要点

  • 静脉期CT影像组学特征或有助于无创区分胸腺瘤的Masaoka-Koga/TNM分期与WHO风险分级。
  • 形状_球形度、形状_最大三维直径和一阶_偏度对区分早期与晚期胸腺瘤最具预测性。
  • 形状_球形度、一阶_范围和一阶_均方根对区分低危与高危胸腺瘤表现最佳。

核心结论

  • 影像组学特征似乎能有效区分胸腺瘤的分期和风险级别,可能有助于治疗计划和预后判断,并可能支持更个性化的治疗策略和改善临床决策。

研究设计与样本

  • 初步研究,共分析37例胸腺瘤患者,从静脉期CT图像中提取107个影像组学特征,使用PyRadiomics模块提取,参考标准为WHO组织学分级及Masaoka-Koga和TNM分期。

诊断标准与关键数值

  • 根据Masaoka-Koga/TNM分期,11个影像组学特征可区分早期与晚期胸腺瘤(p<0.05),最具预测性的为形状_球形度、形状_最大三维直径和一阶_偏度。
  • 根据WHO分类,7个影像组学特征可区分低危与高危胸腺瘤(p<0.05),表现最高的为形状_球形度、一阶_范围和一阶_均方根。
  • LASSO模型对Masaoka-Koga/TNM分期的AUC为0.9,对WHO分类的AUC为0.82。

临床应用与阅片要点

  • 作者认为影像组学特征可通过无创的肿瘤表征,支持更个性化的治疗策略并改善临床决策。

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

Thymomas are the most common primary tumors of the anterior mediastinum, frequently associated with paraneoplastic syndromes like myasthenia gravis. This preliminary study investigated the correlation between radiomic features extracted from venous-phase CT images, histological grading (WHO), and disease staging (Masaoka-Koga and TNM) in patients with thymomas. A total of 37 patients were analyzed, with 107 radiomic features extracted using PyRadiomics module. Statistical analysis revealed 11 significant radiomic features distinguishing early and advanced thymomas according to Masaoka-Koga/TNM staging (p < 0.05), with shape_Sphericity, shape_Maximum3DDiameter, and firstorder_Skewness being the most predictive. For WHO classification, 7 significant features differentiated low-risk and high-risk thymomas (p < 0.05), with shape_Sphericity, firstorder-Range, and firstorder_RootMeanSquared showing the highest performance. LASSO models demonstrated high accuracy, with an AUC of 0.9 for Masaoka-Koga/TNM staging and 0.82 for WHO classification. These findings suggest that radiomic features can effectively distinguish thymoma stages and risk levels, potentially aiding in treatment planning and prognosis. By enabling noninvasive tumor characterization, radiomic features could support more personalized treatment strategies and improve decision-making in clinical practice.

来源:Radiol Med,查看原文。版权归原作者所有。

引用

  1. Cozzi D, Lugli B, Paolucci S, et al. Thymomas under the radiomic lens: preliminary evidence of CT-radiomics signatures for histological grading and disease staging. Radiol Med. 2025. PMID: 41032229. doi:10.1007/s11547-025-02111-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。