arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.06452cs.LGstat.ML
收藏

阿尔茨海默病分类方法的可重复性评估:框架和对MRI和PET数据的应用

Reproducible evaluation of classification methods in Alzheimer's disease: framework and application to MRI and PET data

Inria Paris(法国国家信息与自动化研究所巴黎分部);Sorbonne Université(索邦大学);UPMC Univ Paris 06(巴黎第六大学);Inserm(法国国家健康与医学研究院);CNRS(法国国家科学研究中心);Institut du cerveau et la moelle (ICM)(大脑与脊髓研究所);AP-HP(巴黎公共医疗集团);Pitié-Salpêtrière Hospital(皮蒂-萨尔皮特里耶医院);INSEAD(欧洲工商管理学院)
Jorge Samper-González, Ninon Burgos, Simona Bottani, Sabrina Fontanella, Pascal Lu, Arnaud Marcoux, Alexandre Routier, Jérémy Guillon, Michael Bacci, Junhao Wen… 展开作者

Jorge Samper-González, Ninon Burgos, Simona Bottani, Sabrina Fontanella, Pascal Lu, Arnaud Marcoux, Alexandre Routier, Jérémy Guillon, Michael Bacci, Junhao Wen, Anne Bertrand, Hugo Bertin, Marie-Odile Habert, Stanley Durrleman, Theodoros Evgeniou, Olivier Colliot

摘要:

大量的论文介绍了新的机器学习和特征提取方法用于AD的自动分类。然而,由于验证的关键组成部分往往不容易获得,因此很难复制。这些组件包括选定的参与者和输入数据,图像预处理和交叉验证程序。不同方法的性能也难以客观比较。特别是,通常很难评估该方法的哪一部分提供了真正的改进,如果有的话。我们提出了一个框架,在AD中使用三个公开可用的数据集(ADNI,AIBL和OASIS)的可重复性和客观的分类实验。该框架包括:i)将三个数据集自动转换为BIDS格式,ii)预处理管道、特征提取和分类方法的模块化集合,以及评估框架,其提供用于对不同组件进行基准测试的基线。我们展示了使用的框架,使用T1 MRI和FDG PET数据对1960名参与者进行大规模评估。在这项评估中,我们评估了不同模式、预处理、特征类型、分类器、训练集大小和数据集的影响。FDG PET在所有分类任务中均优于T1 MRI。使用不同图谱、图像平滑、FDG PET图像的部分容积校正或特征类型时,未发现性能差异。线性SVM和L2-logistic回归导致类似的性能,并且都优于随机森林。分类性能随着用于训练的主题的数量而增加。在ADNI上训练的分类器很好地推广到AIBL和OASIS。框架和实验的所有代码都可以在https://gitlab.icm-institute.org/aramislab/AD-ML上公开获得。

英文摘要:

A large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of AD. However, they are difficult to reproduce because key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method provides a real improvement, if any. We propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into BIDS format, ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types, classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS. All the code of the framework and the experiments is publicly available at: https://gitlab.icm-institute.org/aramislab/AD-ML.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑