使用可解释的深度学习影像组学模型诊断和预测早期阿尔茨海默病疾病谱进展:一项初步[18F]FDG PET研究
这项多中心研究纳入来自两个独立队列的1962名受试者,构建基于[18F]FDG PET图像的可解释深度学习影像组学(IDLR)模型,用于诊断阿尔茨海默病临床谱并预测轻度认知障碍向阿尔茨海默病进展。IDLR模型在不同认知状态及MCI轨迹分类中准确率76.51%[72.88%, 79.60%],优于影像组学模型(69.13%[66.28%, 73.12%])和深度学习模型(73.89%[68.99%, 77.89%]);Cox模型显示IDLR模型的风险比HR为1.465(95%CI: 1.236-1.737,p < 0.001)。
要点
- IDLR模型基于[18F]FDG PET图像,分类准确率76.51%[72.88%, 79.60%],优于影像组学模型和深度学习模型。
- IDLR模型对MCI向AD进展的预测风险比HR为1.465(95%CI: 1.236-1.737,p < 0.001)。
- 三个关键IDLR特征在不同认知阶段间有显著差异,且与认知量表评分显著相关(p < 0.01)。
核心结论
- 初步结果表明,基于[18F]FDG PET图像的可解释深度学习影像组学模型提高了诊断阿尔茨海默病临床谱的准确率。
研究设计与样本
- 多中心研究,纳入1962名受试者,来自两个种族多样化的独立队列(ADNI的白人队列和中国两家医院合并的亚洲队列);IDLR模型包括特征提取、特征选择和分类/预测;与影像组学模型和深度学习模型比较;Cox模型检验IDLR签名对MCI向AD进展的预测能力;相关分析识别关键IDLR特征并验证其临床诊断价值。
关键影像表现/征象
- 三个关键IDLR特征在不同认知阶段间有显著差异,且与认知量表评分显著相关(p < 0.01)。
诊断标准与关键数值
- IDLR模型分类准确率为76.51%[72.88%, 79.60%](95%CI),影像组学模型为69.13%[66.28%, 73.12%],深度学习模型为73.89%[68.99%, 77.89%]。
- Cox模型中IDLR模型的风险比HR为1.465(95%CI: 1.236-1.737,p < 0.001)。
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
OBJECTIVES: In this study, we propose an interpretable deep learning radiomics (IDLR) model based on [18F]FDG PET images to diagnose the clinical spectrum of Alzheimer's disease (AD) and predict the progression from mild cognitive impairment (MCI) to AD.
METHODS: This multicentre study included 1962 subjects from two ethnically diverse, independent cohorts (a Caucasian cohort from ADNI and an Asian cohort merged from two hospitals in China). The IDLR model involved feature extraction, feature selection, and classification/prediction. We evaluated the IDLR model's ability to distinguish between subjects with different cognitive statuses and MCI trajectories (sMCI and pMCI) and compared results with radiomic and deep learning (DL) models. A Cox model tested the IDLR signature's predictive capability for MCI to AD progression. Correlation analyses identified critical IDLR features and verified their clinical diagnostic value.
RESULTS: The IDLR model achieved the best classification results for subjects with different cognitive statuses as well as in those with MCI with distinct trajectories, with an accuracy of 76.51% [72.88%, 79.60%], (95% confidence interval, CI) while those of radiomic and DL models were 69.13% [66.28%, 73.12%] and 73.89% [68.99%, 77.89%], respectively. According to the Cox model, the hazard ratio (HR) of the IDLR model was 1.465 (95% CI: 1.236-1.737, p < 0.001). Moreover, three crucial IDLR features were significantly different across cognitive stages and were significantly correlated with cognitive scale scores (p < 0.01).
CONCLUSIONS: Preliminary results demonstrated that the IDLR model based on [18F]FDG PET images enhanced accuracy in diagnosing the clinical spectrum of AD.
KEY POINTS: Question The study addresses the lack of interpretability in existing DL classification models for diagnosing the AD spectrum. Findings The proposed interpretable DL radiomics model, using radiomics-supervised DL features, enhances interpretability from traditional DL models and improves classification accuracy. Clinical relevance The IDLR model interprets DL features through radiomics supervision, potentially advancing the application of DL in clinical classification tasks.
引用
- Jiang J, Li C, Lu J, et al. Using interpretable deep learning radiomics model to diagnose and predict progression of early AD disease spectrum: a preliminary [18F]FDG PET study. Eur Radiol. 2024. PMID: 39477837. doi:10.1007/s00330-024-11158-9
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。