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)
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.
Impact of automatic speech recognition quality on Alzheimer's disease detection from spontaneous speech: a reproducible benchmark study with lexical modeling and statistical validation
Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation
Institut du Cerveau et de la Moelle épinière, ICM(大脑与脊髓研究所(ICM));Sorbonne Université(索邦大学);Inserm(法国国家健康与医学研究院);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);AP-HP(巴黎公共医疗集团);Hôpital de la Pitié Salpêtrière(皮蒂-萨尔皮特里耶医院)
Reproducible evaluation of diffusion MRI features for automatic classification of patients with Alzheimers disease
Institut du Cerveau et de la Moelle épinière, ICM(大脑与脊髓研究所(ICM));Inserm(法国国家健康与医学研究院);CNRS(法国国家科学研究中心);Sorbonne Université(索邦大学);Inria(法国国家信息与自动化研究院);AP-HP(巴黎公共医疗集团)
Modality Contribution Score - A Per-Patient Framework for Quantifying the Relative Diagnostic Contribution of Structural MRI and Amyloid PET in Alzheimer's Disease
Taipei Medical University(台北医学大学);University of Memphis(孟菲斯大学);Chitkara University(奇特卡拉大学);University College London(伦敦大学学院);UPES(石油与能源研究大学);University of Eastern Finland(东芬兰大学);CNRS(法国国家科学研究中心);University Bordeaux(波尔多大学);Bordeaux INP(波尔多国立理工学院)
Flexible Multimodal Neuroimaging Fusion for Alzheimer's Disease Progression Prediction
Department of Computer Science and Engineering(计算机科学与工程系);Department of Biomedical Informatics(生物医学信息学系);Department of Neurology(神经病学系);Translational Data Analytics Institute(转化数据分析研究所)
Behavior Score-Embedded Brain Encoder Network for Improved Classification of Alzheimer Disease Using Resting State fMRI
National Tsing Hua University(国立清华大学);MOST Joint Research Center for AI Technology and All Vista Healthcare(科技部人工智能技术与全视野医疗联合研究中心);National Health Research Institutes(国家卫生研究院)
准确检测痴呆症发作的能力在疾病的治疗中是重要的。临床上,阿尔茨海默病(AD)和轻度认知障碍(MCI)患者的诊断基于心理测试和脑成像(例如正电子发射断层扫描(PET)和解剖磁共振成像(MRI))的综合评估。在这项工作中,使用两个不同的数据集,我们提出了一个行为分数嵌入编码器网络(BSEN),集成定期管理的心理测试信息到编码过程中表示主题的静息状态fMRI数据的自动分类任务。BSEN基于3D卷积自动编码器结构,具有对比度损失,使用MiniMental State Examination(MMSE)和临床痴呆评级(CDR)的行为评分进行联合优化。我们提出的使用BSEN的分类框架实现了59.44%的总体识别准确率(3类分类:AD,MCI和健康对照),我们进一步提取了健康对照(HC)和AD患者之间最具区分力的区域。
Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data
University of Pennsylvania(宾夕法尼亚大学);Stony Brook University(石溪大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Medical University of South Carolina(南卡罗来纳医科大学);Cedars-Sinai Medical Center(西格拉姆山医疗中心)
Identification of Causal Relationship between Amyloid-beta Accumulation and Alzheimer's Disease Progression via Counterfactual Inference
University of Georgia(佐治亚大学);Beijing Normal University(北京师范大学);The University of Texas at Arlington(德克萨斯大学阿灵顿分校);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);Brigham and Women’s Hospital(布莱根妇女医院);Shanghai Jiao Tong University(上海交通大学);The University of Virginia(弗吉尼亚大学)
Detection of Alzheimer's Disease Using Graph-Regularized Convolutional Neural Network Based on Structural Similarity Learning of Brain Magnetic Resonance Images
Lakehead University(湖首大学);University of Calgary(卡尔加里大学)
Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers
Washington University in St Louis(圣路易斯华盛顿大学);Washington University School of Medicine in St Louis(圣路易斯华盛顿大学医学院);Mallinckrodt Institute of Radiology(马林克罗特放射学研究所)
Improved Prediction of Beta-Amyloid and Tau Burden Using Hippocampal Surface Multivariate Morphometry Statistics and Sparse Coding
Arizona State University(亚利桑那州立大学);Banner Alzheimer’s Institute(班纳阿尔茨海默病研究所);Children’s Hospital Los Angeles(洛杉矶儿童医院);Mayo Clinic Arizona(梅奥诊所亚利桑那分院);University of Southern California(南加州大学)
Synthesizing PET images from High-field and Ultra-high-field MR images Using Joint Diffusion Attention Model
Inner Mongolia University(内蒙古大学);Inner Mongolia Medical University(内蒙古医科大学);SIAT, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Inner Mongolia Medical University Affiliated Hospital(内蒙古医科大学附属医院);Shenzhen Children’s Hospital(深圳市儿童医院)
Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET
Sorbonne Université(索邦大学);Institut du Cerveau - Paris Brain Institute - ICM(大脑研究所 - 巴黎大脑研究所 - ICM);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Inserm(法国国家健康与医学研究院);AP-HP(巴黎公共医疗集团);Hôpital de la Pitié Salpêtrière(皮蒂-萨尔皮特里耶医院)
针对脑部 FDG PET 无监督异常检测中残差图像方法的局限性,提出受 Z-scores 启发、利用健康人群变异性的新方法,在 ADNI 数据库上证明其能准确识别阿尔茨海默病相关异常。
Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer
Washington University in St. Louis(圣路易斯华盛顿大学);The Hong Kong Polytechnic University(香港理工大学);Institute for Informatics (I2)(信息学研究所(I2));Peking University(北京大学);Washington University School of Medicine(华盛顿大学医学院)
Predicting Tau Accumulation in Cerebral Cortex with Multivariate MRI Morphometry Measurements, Sparse Coding, and Correntropy
Arizona State University(亚利桑那州立大学);Banner Alzheimer’s Institute(班纳阿尔茨海默病研究所);Southeast University(东南大学);Children’s Hospital Los Angeles(洛杉矶儿童医院);Mayo Clinic Arizona(梅奥诊所亚利桑那分院);University of Southern California(南加州大学)
生物标志物辅助诊断和干预阿尔茨海默病(AD)可能是预防突破的关键。AD的标志之一是tau斑块在人脑中的积累。然而,目前检测tau病理学的方法要么是侵入性的(腰椎穿刺),要么是相当昂贵且不广泛可用的(Tau PET)。在我们以前的工作中,基于结构MRI的海马多变量形态统计学(MMS)显示出优越的性能,作为临床前AD的有效神经退行性生物标志物,基于斑块分析的表面Correntropy-induced Sparse coding and max-pooling(PASCS-MP)具有出色的能力,能够生成具有强大统计能力的低维表示,用于脑淀粉样蛋白预测。在这项工作中,我们将这个框架与岭回归模型一起应用于分别预测Braak 12和Braak 34脑区的Tau沉积。我们评估了我们的框架925个科目从阿尔茨海默病神经影像学倡议(ADNI)。每名受试者都有一对由PET图像和MRI扫描组成的图像,它们是在大约相同的时间收集的。实验结果表明,从我们的MMS和PASCS-MP的表示有更强的预测能力和他们的预测Braak 12和Braak 34更接近真实值相比,从其他方法,如海马表面积和体积,形状形态特征的基础上,球谐函数(SPHARM)。
Reconstructing and forecasting disease trajectories of patients with Alzheimer's disease using routine data in resource-constrained settings
Yardi School of Artificial Intelligence (ScAI), Indian Institute of Technology Delhi(印度理工学院德里分校亚迪人工智能学院);Department of Neurology, Vardhman Mahavir Medical College and Safdarjung Hospital(瓦尔丹·马哈维尔医学院和萨夫达戎医院神经内科);Department of Applied Mechanics, Indian Institute of Technology Delhi(印度理工学院德里分校应用力学系)
DIVE: A spatiotemporal progression model of brain pathology in neurodegenerative disorders
University College London(伦敦大学学院);Inria(法国国家信息与自动化研究所);Université Côte d'Azur(蔚蓝海岸大学)
在这里,我们提出了DIVE:数据驱动的顶点进化推理。DIVE是一种基于图像的疾病进展模型,具有单顶点分辨率,旨在从短期纵向数据集重建大脑病理学的长期模式。DIVE对在患者群体中具有类似时间动态的皮质表面上的逐顶点生物标志物测量进行聚类,并且同时估计每个聚类中的顶点测量的平均轨迹。DIVE独特地将皮质分割成具有共同进展模式的区域,从而为个体疾病提供新的签名。DIVE进一步估计每个受试者每次访视的疾病分期和进展速度,可能增强临床试验或管理的分层。在模拟数据上,DIVE可以恢复地面实况集群及其底层轨迹,前提是集群之间的平均轨迹有足够的差异。我们证明了DIVE的数据来自两个队列:阿尔茨海默病神经影像学倡议(ADNI)和痴呆症研究中心(DRC),英国,包含患者与后皮质萎缩(PCA)以及典型的阿尔茨海默病(tAD)。DIVE在两个独立的数据集(ADNI和DRC)中发现了tAD受试者的萎缩的相似空间模式,并进一步揭示了不同疾病(tAD vs PCA)和不同类型生物标志物数据的不同病理模式:来自磁共振成像(MRI)的皮质厚度vs来自正电子发射断层扫描(PET)的淀粉样蛋白负荷。最后,DIVE可用于使用任何种类的逐体素或逐顶点测量(包括雅可比压缩图、来自扩散成像的分数各向异性(FA)图或其他PET测量)来估计脑中病理的细粒度空间分布。DIVE源代码可在线获得:https://github.com/m…
Modality-Agnostic Style Transfer for Holistic Feature Imputation
Pohang University of Science and Technology(浦项科技大学);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);University of North Carolina at Greensboro(北卡罗来纳大学格林斯伯勒分校)
An explainable framework for the relationship between dementia and glucose metabolism patterns
Department of Signal Processing and Biomedical Applications, University of Granada(信号处理与生物医学应用系,格拉纳达大学);Department of Statistics and Operations Research, University of Valencia(统计与运筹学系,瓦伦西亚大学);Department of Communication Engineering, University of Malaga(通信工程系,马拉加大学)
A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis
College of Computer Science and Technology, Nanjing Forestry University(南京林业大学计算机科学与技术学院);College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)
Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation
Istituto Nazionale di Fisica Nucleare(意大利国家核物理研究所);Università degli Studi di Bari(巴里大学);INAF - Astronomical Observatory of Capodimonte(意大利国家天体物理研究所-卡波迪蒙特天文台);Università degli Studi di Genova(热那亚大学);Università degli Studi di Napoli Federico II(那不勒斯费德里克二世大学);Istituto di Studi sui Sistemi Intelligenti per l’Automazione, CNR(意大利国家研究委员会智能系统与自动化研究所)