基于深度学习算法在磁敏感图加权MRI上自动量化黑质小体-1并分类帕金森综合征
本研究回顾性收集训练集450例(特发性帕金森病210例、对照组240例)和验证集237例(特发性帕金森病168例、特发性震颤58例、药物诱发性帕金森综合征11例),利用多回波梯度回波重建的磁敏感图加权成像,评估深度学习自动量化(Heuron NI)和分类(Heuron IPD)模型诊断特发性帕金森病的效能。结果显示Heuron IPD分类的曲线下面积左侧0.967、右侧0.976,Heuron NI量化的曲线下面积左侧0.915、右侧0.928;H&Y评分≥3分者黑质高信号体积小于H&Y评分1-2.5分者。
要点
- 深度学习模型可自动量化黑质高信号并分类异常,辅助特发性帕金森病诊断。
- 分类模型曲线下面积左侧0.967、右侧0.976,量化模型左侧0.915、右侧0.928。
- H&Y评分≥3分者黑质高信号体积小于评分1-2.5分者(P=.008)。
核心结论
- 基于深度学习的模型可快速、准确地自动量化黑质高信号,有助于特发性帕金森病诊断、症状严重程度预测和个体化治疗的患者分层。
研究设计与样本
- 回顾性研究,训练集450例(特发性帕金森病210例、对照组240例,2022年11月至2023年5月),验证集237例(特发性帕金森病168例、特发性震颤58例、药物诱发性帕金森综合征11例,2021年7月至2022年1月);磁敏感图加权成像由多回波梯度回波重建;特发性帕金森病参考标准为N-3-氟丙基-2-β-甲氧羰基-3-β-(4-碘苯基)去甲托烷PET。
关键影像表现/征象
- 黑质高信号异常分类模型(Heuron IPD)曲线下面积左侧0.967(95%CI 0.936-0.986)、右侧0.976(95%CI 0.948-0.992)。
- 黑质高信号量化模型(Heuron NI)曲线下面积左侧0.915(95%CI 0.872-0.947)、右侧0.928(95%CI 0.887-0.957)。
- H&Y评分≥3分者黑质高信号体积1.43±1.19 mm3,小于H&Y评分1-2.5分者的1.98±1.63 mm3(P=.008)。
诊断标准与关键数值
- Heuron IPD分类黑质高信号异常的曲线下面积左侧0.967(95%CI 0.936-0.986)、右侧0.976(95%CI 0.948-0.992)。
- Heuron NI量化黑质高信号的曲线下面积左侧0.915(95%CI 0.872-0.947)、右侧0.928(95%CI 0.887-0.957)。
- 特发性帕金森病诊断参考标准为N-3-氟丙基-2-β-甲氧羰基-3-β-(4-碘苯基)去甲托烷PET。
临床应用与阅片要点
- 深度学习模型可自动量化黑质高信号并分类异常,辅助特发性帕金森病诊断。
- 黑质高信号体积与H&Y评分相关,评分≥3分者体积1.43±1.19 mm3,小于评分1-2.5分者的1.98±1.63 mm3。
局限性
- 原文结论指出需进一步研究以在不同临床环境中验证这些发现。
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: The diagnostic performance of deep learning model that simultaneously detecting and quantifying nigrosome-1 abnormality by using susceptibility map-weighted imaging (SMwI) remains unexplored. This study aimed to develop and validate a deep learning-based automatic quantification for nigral hyperintensity and a classification algorithm for neurodegenerative parkinsonism.
MATERIALS AND METHODS: We retrospectively collected 450 participants (210 with idiopathic Parkinson disease [IPD] and 240 individuals in the control group) for training data between November 2022 and May 2023, and 237 participants (168 with IPD, 58 with essential tremor, and 11 with drug-induced parkinsonism) for validation data between July 2021 and January 2022. SMwI data were reconstructed from multiecho gradient echo. Diagnostic performance for diagnosing IPD was assessed by using deep learning-based automatic quantification (Heuron NI) and classification (Heuron IPD) models. Reference standard for IPD was based on N-3-fluoropropyl-2-β-carbomethoxy-3-β-(4-iodophenyl) nortropane PET finding. Additionally, the correlation between the Hoehn and Yahr (H&Y) stage and volume of nigral hyperintensity in patients with IPD was assessed.
RESULTS: Quantification of nigral hyperintensity by using Heuron NI showed an area under the curve (AUC) of 0.915 (95% CI, 0.872-0.947) and 0.928 (95% CI, 0.887-0.957) on the left and right, respectively. Classification of nigral hyperintensity abnormality by using Heuron IPD showed area under the curve of 0.967 (95% CI, 0.936-0.986) and 0.976 (95% CI, 0.948-0.992) on the left and right, respectively. H&Y score ≥3 showed smaller nigral hyperintensity volume (1.43 ± 1.19 mm3) compared with H&Y score 1-2.5 (1.98 ± 1.63 mm3; P = .008).
CONCLUSIONS: Our deep learning-based model proves rapid, accurate automatic quantification of nigral hyperintensity, facilitating IPD diagnosis, symptom severity prediction, and patient stratification for personalized therapy. Further study is warranted to validate the findings across various clinical settings.
引用
- Suh PS, Heo H, Suh CH, et al. Deep Learning-Based Algorithm for Automatic Quantification of Nigrosome-1 and Parkinsonism Classification Using Susceptibility Map-Weighted MRI. AJNR Am J Neuroradiol. 2025. PMID: 39547802. doi:10.3174/ajnr.A8585
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。