[18F]FDOPA PET/CT 多巴胺能去神经支配诊断影像组学模型的开发与验证
本研究利用两个[18F]FDOPA PET数据集(443例用于特征选择,另100例来自不同PET/CT系统用于模型测试),基于43个生物标志物(含32个纹理特征)构建LASSO逻辑回归模型,以区分有无多巴胺能去神经支配。仅用临床数据的模型平均AUROC为63.91,常规影像特征最高达93.47,加入纹理特征后AUROC显著提高至95.73(p<0.001),仅用GLCM_Correlation、偏度和致密度三个特征时达96.10(p<0.001)。外部数据集测试AUROC为96.00,灵敏度95%、特异度97%。
要点
- 仅用三个影像组学特征(GLCM_Correlation、偏度、致密度)的简单模型即可识别异常FDOPA PET扫描。
- 外部数据集测试该模型灵敏度95%、特异度97%,AUROC为96.00。
- GLCM_Correlation在相关分析中独立性较强,且在分类模型中权重始终最重。
核心结论
- 由三个影像组学特征构成的简单模型可识别异常的FDOPA PET扫描,灵敏度与特异度均优良。
- 纹理特征在帕金森综合征诊断中显示出前景。
研究设计与样本
- 研究使用两个[18F]FDOPA PET数据集:443例扫描用于特征选择,另100例来自不同PET/CT系统的扫描用于模型测试。
- 扫描按专家判读标注为多巴胺能去神经支配或无多巴胺能去神经支配。
- 使用43个生物标志物(包括32个纹理特征)构建LASSO逻辑回归模型,并用简化的UPDRS量表收集临床数据。
主要发现
- 仅用临床数据构建的模型平均AUROC为63.91。
- 常规影像特征达到的最高AUROC为93.47,加入纹理特征后AUROC显著提高至95.73(p<0.001)。
- 仅保留GLCM_Correlation、偏度和致密度三个特征时,AUROC为96.10(p<0.001)。
- 在外部数据集上测试模型,AUROC为96.00,灵敏度95%,特异度97%。
- GLCM_Correlation在相关分析中独立性较强,且在分类模型中权重始终最重。
关键数值与推荐
- 仅用临床数据的模型:平均AUROC 63.91。
- 常规影像特征:最高AUROC 93.47。
- 常规影像特征加纹理特征:AUROC 95.73(p<0.001)。
- 仅用GLCM_Correlation、偏度和致密度三个特征:AUROC 96.10(p<0.001)。
- 外部数据集测试:AUROC 96.00,灵敏度95%,特异度97%。
临床怎么用
- 原文未据此给出推荐。
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)。
原文
PURPOSE: FDOPA PET shows good performance for the diagnosis of striatal dopaminergic denervation, making it a valuable tool for the differential diagnosis of Parkinsonism. Textural features are image biomarkers that could potentially improve the early diagnosis and monitoring of neurodegenerative parkinsonian syndromes. We explored the performances of textural features for binary classification of FDOPA scans. METHODS: We used two FDOPA PET datasets: 443 scans for feature selection, and 100 scans from a different PET/CT system for model testing. Scans were labelled according to expert interpretation (dopaminergic denervation versus no dopaminergic denervation). We built LASSO logistic regression models using 43 biomarkers including 32 textural features. Clinical data were also collected using a shortened UPDRS scale. RESULTS: The model built from the clinical data alone had a mean area under the receiver operating characteristics (AUROC) of 63.91. Conventional imaging features reached a maximum score of 93.47 but the addition of textural features significantly improved the AUROC to 95.73 (p < 0.001), and 96.10 (p < 0.001) when limiting the model to the top three features: GLCM_Correlation, Skewness and Compacity. Testing the model on the external dataset yielded an AUROC of 96.00, with 95% sensitivity and 97% specificity. GLCM_Correlation was one of the most independent features on correlation analysis, and systematically had the heaviest weight in the classification model. CONCLUSION: A simple model with three radiomic features can identify pathologic FDOPA PET scans with excellent sensitivity and specificity. Textural features show promise for the diagnosis of parkinsonian syndromes.
引用
- Comte V, Schmutz H, Chardin D, et al. Development and validation of a radiomic model for the diagnosis of dopaminergic denervation on [18F]FDOPA PET/CT. Eur J Nucl Med Mol Imaging. 2022. PMID: 35567626. doi:10.1007/s00259-022-05816-7
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。