Alzheimer's Disease (AD) is the world leading cause of dementia, a progressively impairing condition leading to high hospitalization rates and mortality. To optimize the diagnostic process, numerous efforts have been directed towards the development of deep learning approaches (DL) for the automatic AD classification. However, their typical black box outline has led to low trust and scarce usage within clinical frameworks. In this work, we propose two state-of-the art DL models, trained respectively on structural MRI (ResNet18) and brain connectivity matrixes (BC-GCN-SE) derived from diffusion data. The models were initially evaluated in terms of classification accuracy. Then, results were analyzed using an Explainable Artificial Intelligence (XAI) approach (Grad-CAM) to measure the level of interpretability of both models. The XAI assessment was conducted across 132 brain parcels, extracted from a combination of the Harvard-Oxford and AAL brain atlases, and compared to well-known pathological regions to measure adherence to domain knowledge. Results highlighted acceptable classification performance as compared to the existing literature (ResNet18: TPRmedian = 0.817, TNRmedian = 0.816; BC-GCN-SE: TPRmedian = 0.703, TNRmedian = 0.738). As evaluated through a statistical test (p < 0.05) and ranking of the most relevant parcels (first 15%), Grad-CAM revealed the involvement of target brain areas for both the ResNet18 and BC-GCN-SE models: the medial temporal lobe and the default mode network. The obtained interpretabilities were not without limitations. Nevertheless, results suggested that combining different imaging modalities may result in increased classification performance and model reliability. This could potentially boost the confidence laid in DL models and favor their wide applicability as aid diagnostic tools.
Towards improving Alzheimer's intervention: a machine learning approach for biomarker detection through combining MEG and MRI pipelines
Universiti Teknologi PETRONAS(马来西亚国油大学);Hospital Universiti Sains Malaysia(马来西亚理科大学医院);Universiti Sains Malaysia(马来西亚理科大学);Ulster University(阿尔斯特大学);University of Calgary(卡尔加里大学);University of Bath(巴斯大学)
本文基于 324 名 BioFIND 参与者的 MEG 与 MRI 数据,通过交叉验证机器学习分类识别 MCI,发现融合未校正 MEG 与 z-score 校正 MRI 特征效果最佳。
Cross-Modality Translation with Generative Adversarial Networks to Unveil Alzheimer's Disease Biomarkers
School of Electrical and Computer Engineering, Georgia Institute of Technology(佐治亚理工学院电气与计算机工程学院);Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University(佐治亚州立大学神经影像学与数据科学转化研究三机构中心(TReNDS));College of Pharmacy, University of Florida(佛罗里达大学药学院)
An Interpretable Machine Learning Model with Deep Learning-based Imaging Biomarkers for Diagnosis of Alzheimer's Disease
Erasmus MC(伊拉斯姆斯医学中心);University Medical Center Groningen(格罗宁根大学医学中心);University Medical Center Utrecht(乌得勒支大学医学中心);Radboud University Medical Center(拉德堡德大学医学中心);Leiden University Medical Center(莱顿大学医学中心);Leiden University(莱顿大学);Amsterdam University Medical Center(阿姆斯特丹大学医学中心);Maastricht University Medical Center(马斯特里赫特大学医学中心)
Predicting Early Stages Of Alzheimer's Disease And Identifying Key Biomarkers Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies
Uncovering Neuroimaging Biomarkers of Brain Tumor Surgery with AI-Driven Methods
Department of Communication Engineering University of Málaga(通信工程系马德里大学);Department of Clinical Neurosciences University of Cambridge(临床神经科学系剑桥大学);Department of Neuroscience University of Padova(神经科学系帕多瓦大学);Department of Signal Theory, Telematics and Communications, University of Granada(信号理论、电信与通信系格拉纳达大学);Department of Computer Science and Technology University of Cambridge(计算机科学与技术系剑桥大学);Department of Psychiatry University of Cambridge(精神病学系剑桥大学);NHS Foundation Trust United Kingdom(国家健康服务基金会信托英国)
An Interpretable Ensemble Framework for Multi-Omics Dementia Biomarker Discovery Under HDLSS Conditions
Department of Mathematics and Physics, Mathematics Major, Gangneung-Wonju National University(数学与物理系,数学专业,江陵-Wonju国立大学);Department of Data Science, Gangneung-Wonju National University(数据科学系,江陵-Wonju国立大学)
Enhancing Alzheimer's Diagnosis: Leveraging Anatomical Landmarks in Graph Convolutional Neural Networks on Tetrahedral Meshes
School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, USA(计算与增强智能学院,亚利桑那州立大学);Amazon AGI, Redmond, WA, USA(亚马逊人工智慧部门);Banner Alzheimer’s Institute, Phoenix, AZ, USA(贝纳尔德阿尔茨海默病研究所)
Is a PET all you need? A multi-modal study for Alzheimer's disease using 3D CNNs
Lab for Artificial Intelligence in Medical Imaging (AI-Med), KJP, LMU Klinikum(慕尼黑大学附属医院儿童与青少年精神病学系医学影像人工智能实验室);Technical University of Munich, School of Medicine(慕尼黑工业大学医学院)
阿尔茨海默病(AD)是痴呆症的最常见形式,并且由于痴呆症的多因素病因学而通常难以诊断。最近关于使用深度神经网络(DNN)进行基于神经成像的计算机辅助诊断的研究表明,融合结构磁共振图像(sMRI)和氟脱氧葡萄糖正电子发射断层扫描(FDG-PET)可以提高健康对照和AD受试者研究人群的准确性。然而,这一结果与FDG-PET比sMRI更好地捕获AD特异性病理的既定临床知识相冲突。因此,我们提出了一个系统评价多模态DNN的框架,并基于FDG-PET和sMRI对二元健康与AD以及三向健康/轻度认知障碍/AD分类的单模态和多模态DNN进行了严格的重新评价。我们的实验表明,使用FDG-PET的单模态网络的性能优于MRI(准确度为0.91 vs 0.87),并且在组合时没有显示出改善。这与AD生物标志物的既定临床知识一致,但对多模式DNN的真正益处提出了疑问。我们认为,未来关于多模式融合的工作应该按照我们提出的评估框架系统地评估各个模式的贡献。最后,我们鼓励社区超越健康与AD分类,专注于痴呆症的鉴别诊断,融合多模态图像信息符合临床需求。
Deep Learning Approaches with Explainable AI for Differentiating Alzheimer Disease and Mild Cognitive Impairment
School of Mathematical and Natural Sciences(数学与自然科学学院);Arizona State University(亚利桑那州立大学);Department of Mathematics(数学系);Florida Gulf Coast University(佛罗里达海岸大学);Department of Public Health(公共卫生系);Julia Jones Matthews School of Population and Public Health(朱莉亚·琼斯·马修斯人口与公共卫生学院);Texas Tech University Health Sciences Center(德克萨斯农工大学健康科学中心)