文献速递神经核医学

基于[123I]FP-CIT SPECT图像的帕金森病有效自动计算机辅助诊断的特征提取、选择与比较

Extraction, selection and comparison of features for an effective automated computer-aided diagnosis of Parkinson's disease based on [123I]FP-CIT SPECT images.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2017-12-23

本研究旨在评估从[123I]FP-CIT SPECT脑图像提取的特征集在计算机辅助体内确认多巴胺能退变及辅助帕金森病临床诊断中的潜力。从每个大脑半球计算七个特征,在帕金森病进展标志物倡议的652例[123I]FP-CIT SPECT脑图像数据集上测试,使用支持向量机、k近邻和逻辑回归三种机器学习技术评估各特征及特征组的区分能力。基于支持向量机的交叉验证结果显示,纹状体区域长度、壳核结合潜力和纹状体结合潜力分别产生最高准确率96.5%、95.4%和93.9%,三者间无统计学显著差异;同时使用所有特征获得最高分类准确率97.9%、灵敏度98%和特异度97.6%。结论认为纹状体区域摄取长度具有临床实用性,作者提出将其与基于摄取比的特征联合用于帕金森病多巴胺能退变的计算机辅助诊断的日常临床使用。

要点

  • 纹状体区域长度特征单独分类准确率最高,达96.5%。
  • 同时使用所有特征时准确率97.9%、灵敏度98%、特异度97.6%。
  • 作者提出将纹状体区域长度与摄取比特征联合用于日常计算机辅助诊断。

核心结论

  • 纹状体区域摄取长度在体内确认多巴胺能退变以辅助帕金森病诊断方面具有临床实用性和高度价值。
  • 纹状体区域长度与基于摄取比的标准特征相比达到至少相似的准确率,且更易于自动获取。
  • 作者提出将其与基于摄取比的特征联合用于帕金森病多巴胺能退变的计算机辅助诊断的日常临床使用。

研究设计与样本

  • 从帕金森病进展标志物倡议的652例[123I]FP-CIT SPECT脑图像数据集中提取特征。
  • 从每个大脑半球计算七个特征:五个与纹状体摄取比相关的标准特征,两个与正常摄取纹状体区域的估计体积和长度相关的特征。
  • 使用支持向量机、k近邻和逻辑回归三种机器学习技术评估各特征及特征组的区分能力。

主要发现

  • 基于支持向量机的交叉验证中,纹状体区域长度准确率96.5%、壳核结合潜力95.4%、纹状体结合潜力93.9%,三者间无统计学显著差异。
  • 同时使用所有特征时分类准确率97.9%、灵敏度98%、特异度97.6%。
  • 使用支持向量机时结果一般略好,对大多数特征与其他分类器无统计学显著差异。

关键数值与推荐

  • 纹状体区域长度单独准确率96.5%。
  • 壳核结合潜力单独准确率95.4%。
  • 纹状体结合潜力单独准确率93.9%。
  • 全部特征联合:准确率97.9%、灵敏度98%、特异度97.6%。

临床怎么用

  • 作者提出将纹状体区域长度与基于摄取比的特征联合用于帕金森病多巴胺能退变的计算机辅助诊断的日常临床使用。

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: This work aimed to assess the potential of a set of features extracted from [123I]FP-CIT SPECT brain images to be used in the computer-aided "in vivo" confirmation of dopaminergic degeneration and therefore to assist clinical decision to diagnose Parkinson's disease. METHODS: Seven features were computed from each brain hemisphere: five standard features related to uptake ratios on the striatum and two features related to the estimated volume and length of the striatal region with normal uptake. The features were tested on a dataset of 652 [123I]FP-CIT SPECT brain images from the Parkinson's Progression Markers Initiative. The discrimination capacities of each feature individually and groups of features were assessed using three different machine learning techniques: support vector machines (SVM), k-nearest neighbors and logistic regression. RESULTS: Cross-validation results based on SVM have shown that, individually, the features that generated the highest accuracies were the length of the striatal region (96.5%), the putaminal binding potential (95.4%) and the striatal binding potential (93.9%) with no statistically significant differences among them. The highest classification accuracy was obtained using all features simultaneously (accuracy 97.9%, sensitivity 98% and specificity 97.6%). Generally, slightly better results were obtained using the SVM with no statistically significant difference to the other classifiers for most of the features. CONCLUSIONS: The length of the striatal region uptake is clinically useful and highly valuable to confirm dopaminergic degeneration "in vivo" as an aid to the diagnosis of Parkinson's disease. It compares fairly well to the standard uptake ratio-based features, reaching, at least, similar accuracies and is easier to obtain automatically. Thus, we propose its day to day clinical use, jointly with the uptake ratio-based features, in the computer-aided diagnosis of dopaminergic degeneration in Parkinson's disease.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Oliveira FPM, Faria DB, Costa DC, et al. Extraction, selection and comparison of features for an effective automated computer-aided diagnosis of Parkinson's disease based on [123I]FP-CIT SPECT images. Eur J Nucl Med Mol Imaging. 2017. PMID: 29275487. doi:10.1007/s00259-017-3918-7

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。