文献速递骨肌CTMRDR

基于机器学习的增强CT与MRI局灶性骨肿瘤分层分类:一项多中心回顾性研究

Enhanced CT and MRI Focal Bone Tumor Classification with Machine Learning-based Stratification: A Multicenter Retrospective Study.
PubMed 文献 · Radiology · 2025-01-01

这项多中心回顾性研究纳入1113例孤立性骨肿瘤患者,利用XGBoost分类器从影像与临床特征中筛选27个特征进行良恶性鉴别,并据此提出BTI-RADS 2.0七级风险分层系统。模型F1为0.81(95%CI 0.78-0.84),略低于28名放射科医师的0.83(95%CI 0.80-0.85;P<.001)。BTI-RADS 2.0的II-V级恶性率分别为0%、8.3%、45%、92%,识别恶性病变的敏感度为96%(95%CI 94-98)。

要点

  • BTI-RADS 2.0的II-V级恶性率分别为0%、8.3%、45%和92%,可用于风险分层。
  • 模型识别恶性病变的敏感度为96%(373/387,95%CI 94-98)。
  • XGBoost模型F1为0.81,略低于28名放射科医师的0.83(P<.001)。

核心结论

  • 基于机器学习的算法与风险分层系统实现了准确、标准化的骨肿瘤恶性度分级。

研究设计与样本

  • 多中心回顾性研究,纳入2009年11月至2022年3月10个中心的1113例接受X线或CT及MRI的孤立性骨肿瘤患者,分为训练集298例与测试集815例。

关键影像表现/征象

  • 从80个多模态特征中经χ2分析筛选出27个特征用于建模。
  • 训练集用于自助法χ2特征选择,XGBoost分类器经嵌套交叉验证优化。

诊断标准与关键数值

  • BTI-RADS 2.0将患者分为七个恶性风险等级,II-V级的恶性率分别为0%(0/102;95%CI 0-0)、8.3%(14/168;95%CI 4-13)、45%(121/271;95%CI 39-50)和92%(252/274;95%CI 89-95)。
  • 模型识别恶性病变的敏感度为96%(373/387;95%CI 94-98)。
  • XGBoost模型(27个特征)的F1为0.81(95%CI 0.78-0.84),28名经验丰富的放射科医师的F1为0.83(95%CI 0.80-0.85),模型表现略低于医师(P<.001)。

临床应用与阅片要点

  • 原文未据此给出推荐。
  • 作者提出BTI-RADS 2.0用于进一步风险分层。

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

Background Standardized bone tumor reporting is crucial for consistent, risk-aligned patient management. Current systems are based on expert consensus and/or lack multicenter validation. Purpose To evaluate a machine learning-based approach for differentiating between benign and malignant focal bone lesions and to propose a Bone Tumor Imaging Reporting and Data System (BTI-RADS) 2.0 for further risk stratification. Materials and Methods This retrospective multicenter trial included patients with solitary bone tumors undergoing (a) radiography or CT and (b) MRI at 10 centers from November 2009 to March 2022. Patients were divided into training and test datasets. Predefined radioclinical features were extracted. The training dataset was considered for bootstrapped χ2 feature selection, and extreme gradient boosting (XGBoost) classifiers were optimized using nested cross-validation. Continuous classifier outputs were thresholded to stratify patients into seven malignancy risk classes (BTI-RADS 2.0), and malignancy rates were assessed for the test set. XGBoost and human expert performances were compared using the Wilcoxon signed-rank significance test with a significance level of .05. Results In total, 1113 patients (mean age, 39 years ± 22 [SD]; 623 men) were included: 298 in the training and 815 in the test datasets. Twenty-seven of 80 (34%) multimodal features were selected based on χ2 analysis. Best classification performances were achieved by an XGBoost model trained on 27 features, with an F1 score of 0.81 (95% CI: 0.78, 0.84). This model performed slightly inferior to 28 experienced radiologists, who demonstrated an F1 score of 0.83 (95% CI: 0.80, 0.85; P < .001). BTI-RADS 2.0 risk grades II-V were associated with malignancy rates of 0% (0 of 102; 95% CI: 0, 0), 8.3% (14 of 168; 95% CI: 4, 13), 45% (121 of 271; 95% CI: 39, 50), and 92% (252 of 274; 95% CI: 89, 95), respectively, identifying malignant lesions with a sensitivity of 96% (373 of 387; 95% CI: 94, 98). Conclusion A machine learning algorithm and risk stratification system achieved accurate and standardized bone tumor malignancy grading. Clinical trial registration no. NCT04884048 © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Tordjman and Murphey in this issue.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Lemore A, Vogt N, Oster J, et al. Enhanced CT and MRI Focal Bone Tumor Classification with Machine Learning-based Stratification: A Multicenter Retrospective Study. Radiology. 2025. PMID: 40261174. doi:10.1148/radiol.232834

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。