随机森林特征选择、融合和集成策略：结合多种形态磁共振成像指标对健康老年人、MCI、cMCI 和阿尔茨海默病患者进行分类：来自阿尔茨海默病神经影像学倡议（ADNI）数据库。
Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healhy elderly, MCI, cMCI and alzheimer's disease patients: From the alzheimer's disease neuroimaging initiative (ADNI) database.
机构信息
Neuroscience and Mental Health Research Institute, Cardiff University, Cardiff, UK; Cardiff University Brain Research Imaging Centre (CUBRIC), School of Psychology, Cardiff University, Cardiff, UK; MRC Centre for Neuropsychiatric Genetics and Genomics, Institute of Psychological Medicine and Clinical Neurosciences, Cardiff School of Medicine, Cardiff University, Cardiff, UK; Neuroinformatics Group, (CUBRIC), School of Psychology, Cardiff University, Cardiff, UK; School of Psychology, Cardiff University, Cardiff, UK; 3rd Department of Neurology, Medical School, Aristotle University of Thessaloniki, Thessaloniki, Greece.
High Performance Computing Center Stuttgart (HLRS), University of Stuttgart, Stuttgart, Germany; Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece.
出版信息
J Neurosci Methods. 2018 May 15;302:14-23. doi: 10.1016/j.jneumeth.2017.12.010. Epub 2017 Dec 18.
BACKGROUND
In the era of computer-assisted diagnostic tools for various brain diseases, Alzheimer's disease (AD) covers a large percentage of neuroimaging research, with the main scope being its use in daily practice. However, there has been no study attempting to simultaneously discriminate among Healthy Controls (HC), early mild cognitive impairment (MCI), late MCI (cMCI) and stable AD, using features derived from a single modality, namely MRI.
NEW METHOD
Based on preprocessed MRI images from the organizers of a neuroimaging challenge, we attempted to quantify the prediction accuracy of multiple morphological MRI features to simultaneously discriminate among HC, MCI, cMCI and AD. We explored the efficacy of a novel scheme that includes multiple feature selections via Random Forest from subsets of the whole set of features (e.g. whole set, left/right hemisphere etc.), Random Forest classification using a fusion approach and ensemble classification via majority voting. From the ADNI database, 60 HC, 60 MCI, 60 cMCI and 60 CE were used as a training set with known labels. An extra dataset of 160 subjects (HC: 40, MCI: 40, cMCI: 40 and AD: 40) was used as an external blind validation dataset to evaluate the proposed machine learning scheme.
RESULTS
In the second blind dataset, we succeeded in a four-class classification of 61.9% by combining MRI-based features with a Random Forest-based Ensemble Strategy. We achieved the best classification accuracy of all teams that participated in this neuroimaging competition.
COMPARISON WITH EXISTING METHOD(S): The results demonstrate the effectiveness of the proposed scheme to simultaneously discriminate among four groups using morphological MRI features for the very first time in the literature.
CONCLUSIONS
Hence, the proposed machine learning scheme can be used to define single and multi-modal biomarkers for AD.
背景
在各种脑部疾病的计算机辅助诊断工具时代，阿尔茨海默病（AD）占据了神经影像学研究的很大比例，主要应用于日常实践。然而，迄今为止，尚无研究尝试使用单一模态（即 MRI）的特征同时区分健康对照（HC）、早期轻度认知障碍（MCI）、晚期 MCI（cMCI）和稳定 AD。
新方法
基于神经影像学挑战赛组织者提供的预处理 MRI 图像，我们尝试定量评估多种形态 MRI 特征的预测准确性，以同时区分 HC、MCI、cMCI 和 AD。我们探索了一种新方案的功效，该方案通过随机森林从特征全集中的子集（例如整个集合、左右半球等）进行多次特征选择、使用融合方法的随机森林分类以及多数投票的集成分类。从 ADNI 数据库中，我们使用了 60 个 HC、60 个 MCI、60 个 cMCI 和 60 个 CE 作为具有已知标签的训练集。另外还使用了 160 个受试者数据集（HC：40、MCI：40、cMCI：40 和 AD：40）作为外部盲验证数据集，以评估所提出的机器学习方案。
结果
在第二个盲数据集，我们通过结合基于 MRI 的特征和基于随机森林的集成策略，成功实现了 61.9%的四分类。我们在所有参与该神经影像学竞赛的团队中实现了最佳的分类准确性。
与现有方法的比较
结果证明了该方案的有效性，这是首次在文献中使用形态 MRI 特征同时区分四组。
结论
因此，所提出的机器学习方案可用于定义 AD 的单模态和多模态生物标志物。
Zotero 插件