基于深度学习的MRI预测PET淀粉样蛋白状态
该研究利用ADNI、OASIS3和A4三个公开数据集的多对比度MRI和PET定量Aβ沉积数据,回顾性训练两种EfficientNet模型预测淀粉样蛋白阳性,多对比度模型(T1w+T2 FLAIR)在内部测试集AUC为0.67,优于仅T1w模型的0.61,外部测试集AUC为0.65。
要点
- 多对比度MRI模型(T1w+T2 FLAIR)预测Aβ阳性的内部测试集AUC为0.67,仅T1w模型为0.61。
- 轻度认知障碍亚组的AUC最高,为0.71。
- 外部测试集AUC为0.65,准确度为0.62。
核心结论
- 在T1w图像基础上加入T2 FLAIR的多对比度MRI,通过深度学习方法显著提高了从MRI预测PET确定的淀粉样蛋白状态的预测准确性。
研究设计与样本
- 回顾性研究,使用ADNI、OASIS3和A4三个公开数据集共4056次检查用于网络开发,149次检查用于外部测试,参考标准为各数据集推荐的Centiloid阈值定义的Aβ阳性。
诊断标准与关键数值
- Aβ阳性定义为各数据集推荐的Centiloid阈值;多对比度模型内部测试集AUC 0.67(95% CI 0.65-0.70),准确度0.63(95% CI 0.62-0.65);仅T1w模型AUC 0.61,准确度0.59;外部测试集AUC 0.65(95% CI 0.60-0.71),准确度0.62(95% CI 0.58-0.65)。
临床应用与阅片要点
- 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)。
英文原文(摘要)· 点击展开
BACKGROUND AND PURPOSE: Identifying amyloid-beta (Aβ)-positive patients is essential for Alzheimer disease clinical trials and disease-modifying treatments but currently requires PET or CSF sampling. Previous MRI-based deep learning models using only T1-weighted (T1w) images have shown moderate performance.
MATERIALS AND METHODS: Multicontrast MRI- and PET-based quantitative Aβ deposition were retrospectively obtained from 3 public data sets: ADNI, OASIS3, and A4. Aβ positivity was defined using the recommended Centiloid threshold of each data set. Two EfficientNet models were trained to predict amyloid-positivity: one by using only T1w images and another incorporating both T1w and T2 FLAIR. Model performance was assessed using an internal held-out test set, evaluating area under the curve (AUC), accuracy, sensitivity, and specificity. External validation was conducted using an independent cohort from Stanford Alzheimer Disease Research Center. DeLong and McNemar tests were used to compare AUC and accuracy, respectively.
RESULTS: A total of 4056 examinations (mean age: 71.6 [SD, 6.3] years; 55% female; 55% amyloid-positive) were used for network development, and 149 examinations were used for external testing (mean age: 72.1 [SD] 9.6] years; 57% female; 56% amyloid-positive). The multicontrast model outperformed the single-technique model in the internal held-out test set (AUC: 0.67; 95% CI, 0.65-0.70; P < .001; accuracy: 0.63; 95% CI, 0.62-0.65; P < .001) compared with the T1w-only model (AUC: 0.61; accuracy: 0.59). Among cognitive subgroups, the highest performance (AUC: 0.71) was observed in mild cognitive impairment. The multicontrast model also demonstrated consistent performance in the external test set (AUC: 0.65; 95% CI, 0.60-0.71; P = .014; accuracy: 0.62; 95% CI, 0.58-0.65; P < .001).
CONCLUSIONS: The use of multicontrast MRI, specifically incorporating T2 FLAIR in addition to T1w images, significantly improved the predictive accuracy of PET-determined amyloid status from MRIs by using a deep learning approach.
引用
- Kim D, Ottesen JA, Kumar A, et al. Deep Learning-Based Prediction of PET Amyloid Status Using MRI. AJNR Am J Neuroradiol. 2025. PMID: 40579043. doi:10.3174/ajnr.A8899
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。