18F-FDG PET/CT放射组学在感染性心内膜炎中的诊断价值与可解释性
本研究评估[18F]FDG PET/CT放射组学在感染性心内膜炎(IE)诊断中的价值,纳入3个中心447例疑似IE患者。放射组学特征经降维后用于单变量分析、随机森林模型预测PET/CT视觉分析结果、聚类模型预测最终诊断及逻辑回归评估各标准贡献。结果显示放射组学特征能有效区分PET/CT结果,尤其有助于解读不确定的PET表现。
要点
- 放射组学特征可辅助解读感染性心内膜炎中不确定的PET/CT结果
- 结合放射组学与视觉评估的模型诊断性能优于单独视觉评估
- 聚类分析可将患者分组,支持基于放射组学的风险评分解读
核心结论
- 放射组学特征采用监督与无监督方法,能有效描述和区分大型IE队列中的[18F]FDG PET/CT结果。
- 针对模棱两可PET/CT表现的特定特征签名提示放射组学可辅助解读不确定的PET结果,从而影响患者管理。
研究设计与样本
- 多中心研究,纳入3个中心447例疑似感染性心内膜炎患者,收集[18F]FDG PET/CT和临床数据。
- 放射组学特征经降维后,进行单变量检验、随机森林模型预测PET/CT视觉分析结局、聚类放射组学模型预测最终诊断及逻辑回归评估各标准的相对贡献。
主要发现
- 9/17个临床变量和7/11个放射组学变量可单变量分层患者。
- 随机森林模型在明确病例中准确预测PET/CT视觉评估,对可疑病例的分类类似「IE阴性」放射组学签名。
- 聚类分析将患者分为两组,逻辑回归表明纳入放射组学的模型性能优于仅含视觉图像评估的模型。
临床怎么用
- 放射组学特征可辅助解读感染性心内膜炎中不确定的PET/CT结果,可能影响患者管理决策。
- 结合放射组学与视觉评估可能提高诊断性能,聚类分析支持进一步风险评分解读。
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)。
原文
BACKGROUND: to assess the value of [18 F]FDG PET/CT radiomics in infective endocarditis (IE) diagnosis. We evaluated and collected [18 F]FDG PET/CT and clinical data of 447 patients, with suspected IE studied in 3 centers. Radiomic features were calculated and after dimensionality reduction, we performed: (1) univariate testing for assessing the discrimination power of clinical variables and radiomics; (2) a multivariate random forest-based model fed by radiomics to predict the outcome of PET/CT visual analysis; (3) a clustering-based radiomic model to predict final diagnosis; (4) a series of Logistic Regression (LR) models to assess the relative contribution of each criterion in relation with final diagnosis. RESULTS: 9/17 clinical and 7/11 radiomics variables were able to univariately stratify patients. The random forest model accurately predicted PET/CT visual assessment in definite cases, providing a classification of doubtful cases resembling the “IE-negative” radiomic signature. The clustering-based analysis divided patients in two groups. LRs demonstrated that the richer the information fed into the model, the higher the performances: the models including radiomics performed better than the one solely including visual image assessment. CONCLUSION: Radiomic signature, employing both supervised and unsupervised approaches, effectively described and differentiated [18 F]FDG PET/CT outcomes in a large IE cohort. The identification of specific signatures for equivocal PET/CT findings suggests that radiomic features can assist in interpreting ambiguous PET results, thus significantly impacting patient management. Clustering algorithm successfully associated patients with varying conditions, allowing for further assessment and characterization within the radiomics framework, potentially leading to risk score-based interpretations.
引用
- Erba PA, Zanca R, Sollini M, et al. Diagnostic value and interpretability of [18F]FDG-PET/CT radiomics in infective endocarditis. EJNMMI Res. 2026. PMID: 41691141. doi:10.1186/s13550-025-01366-9
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。