A Novel Solution of an Elastic Net Regularization for Dementia Knowledge Discovery using Deep Learning
Charles Sturt University（查尔斯特大学）；Al Iraqia University（伊拉克大学）；University of Western Sydney（西悉尼大学）；Kent Institute Australia（澳大利亚肯特学院）；Asia Pacific International College（亚太国际学院）；University of Kurdistan Hewler（库尔德斯坦赫勒大学）；AL Nisour University College（阿尔尼苏尔大学学院）
Kshitiz Shrestha, Omar Hisham Alsadoon, Abeer Alsadoon, Tarik A. Rashid, Rasha S. Ali, P. W. C. Prasad, Oday D. Jerew
备注：
20 pages
发表信息：
Journal of Experimental & Theoretical Artificial Intelligence, 2021
Background and Aim: Accurate classification of Magnetic Resonance Images (MRI) is essential to accurately predict Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) conversion. Meanwhile, deep learning has been successfully implemented to classify and predict dementia disease. However, the accuracy of MRI image classification is low. This paper aims to increase the accuracy and reduce the processing time of classification through Deep Learning Architecture by using Elastic Net Regularization in Feature Selection. Methodology: The proposed system consists of Convolutional Neural Network (CNN) to enhance the accuracy of classification and prediction by using Elastic Net Regularization. Initially, the MRI images are fed into CNN for features extraction through convolutional layers alternate with pooling layers, and then through a fully connected layer. After that, the features extracted are subjected to Principle Component Analysis (PCA) and Elastic Net Regularization for feature selection. Finally, the selected features are used as an input to Extreme Machine Learning (EML) for the classification of MRI images. Results: The result shows that the accuracy of the proposed solution is better than the current system. In addition to that, the proposed method has improved the classification accuracy by 5% on average and reduced the processing time by 30 ~ 40 seconds on average. Conclusion: The proposed system is focused on improving the accuracy and processing time of MCI converters/non-converters classification. It consists of features extraction, feature selection, and classification using CNN, FreeSurfer, PCA, Elastic Net, Extreme Machine Learning. Finally, this study enhances the accuracy and the processing time by using Elastic Net Regularization, which provides important selected features for classification.
Early Prediction of Alzheimer's Disease Dementia Based on Baseline Hippocampal MRI and 1-Year Follow-Up Cognitive Measures Using Deep Recurrent Neural Networks
Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）
ARMARecon: An ARMA Convolutional Filter based Graph Neural Network for Neurodegenerative Dementias Classification
IEEE International Symposium on Biomedical Imaging (ISBI) 2026（IEEE生物医学成像国际会议（ISBI）2026）；VSS Tejaswi Abburi；Ananya Singhal；Saurabh J. Shigwan；Nitin Kumar
Probability-Invariant Random Walk Learning on Gyral Folding-Based Cortical Similarity Networks for Alzheimer's and Lewy Body Dementia Diagnosis
Department of Computer Science and Engineering, University of Texas at Arlington, United States（德克萨斯理工大学计算机科学与工程系）；School of Computing, University of Georgia, United States（佐治亚大学计算机学院）；Department of Psychiatry, University of Cambridge, United Kingdom（剑桥大学精神病学系）；Sheffield Institute for Translational Neuroscience, University of Sheffield, United Kingdom（谢菲尔德大学转化神经科学研究所）
Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics
Lab for AI in Medical Imaging, Institute for Diagnostic and Interventional Radiology, School of Medicine and Health（人工智能在医学影像中的实验室，诊断与介入放射学研究所，医学院与健康学院）；Technical University of Munich (TUM)（慕尼黑技术大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；University Medical Center Hamburg-Eppendorf（汉堡-埃本达大学医学中心）；Department of Neuroradiology, TUM University Hospital, School of Medicine and Health（神经放射学部，慕尼黑技术大学医院，医学院与健康学院）；Department of Neurology, TUM University Hospital, School of Medicine and Health（神经病学部，慕尼黑技术大学医院，医学院与健康学院）
Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshes
Northwestern University（西北大学）；Northwestern Memorial Hospital（西北纪念医院）
A Two-Scan Deep Learning Model for Predicting Dementia in Mild Cognitive Impairment
organization= School of Business Law；Entrepreneurship, Swinburne University of Technology , city= Melbourne , state= VIC , country= Australia；organization= Australian Regenerative Medicine Institute, Monash University , city= Melbourne , state= VIC , country= Australia；organization= Data Science \& Big Data Lab, Universidad Pablo de Olavide , city= Seville , country= Spain；organization= The Maersk Mc-Kinney M ller Institute, University of Southern Denmark , city= Odense , country= Denmark
Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with Dementia
University of Toronto（多伦多大学）；KITE Research Institute, Toronto Rehabilitation Institute, University Health Network（多伦多康复研究所KITE研究所，大学健康网络）；The Hospital for Sick Children（病童医院）；Morton and Gloria Shulman Movement Disorders Clinic, Toronto Western Hospital, University Health Network（多伦多西部医院莫顿与格洛丽亚·舒尔曼运动障碍诊所，大学健康网络）；Krembil Brain Institute, University Health Network（大学健康网络克雷姆比尔脑研究所）；Center for Advancing Neurotechnological Innovation to Application（神经技术创新应用推进中心）；Centre for Mental Health, University Health Network（大学健康网络心理健康中心）
Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease
German Center for Neurodegenerative Diseases (DZNE)（德国神经退行性疾病中心）；University of Rostock（罗斯托克大学）；Charité – Universitätsmedizin Berlin（夏里特医学院）；University Hospital Bonn（波恩大学医院）；Ludwig Maximilian University（慕尼黑大学）；Rostock University Medical Center（罗斯托克大学医学中心）；Georg-August-University（哥廷根大学）；Otto-von-Guericke University（奥托·冯·古里克大学）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Hertie Institute for Clinical Brain Research（赫蒂临床脑研究所）；University of Tuebingen（图宾根大学）；University of Cologne（科隆大学）；Darmstadt University of Technology（达姆施塔特工业大学）；Imperial College London（伦敦帝国理工学院）；Technical University Munich（慕尼黑工业大学）；University Medical Center Goettingen（哥廷根大学医学中心）；Leibniz Institute for Neurobiology（莱布尼茨神经生物学研究所）；University of Toronto（多伦多大学）；University of Aveiro（阿威罗大学）
背景资料：尽管卷积神经网络（CNN）基于磁共振成像（MRI）扫描实现了用于检测阿尔茨海默病（AD）痴呆的高诊断准确性，但它们尚未应用于临床常规。其中一个重要原因是缺乏模型的可理解性。最近开发的用于导出CNN相关性图的可视化方法可能有助于填补这一空白。我们研究了具有更高准确度的模型是否也更多地依赖于由先验知识预定义的区分性大脑区域。研究方法：我们训练了一个CNN，用于在N=663例痴呆和遗忘型轻度认知障碍（MCI）患者的T1加权MRI扫描中检测AD，并通过交叉验证和包括N=1655例病例的三个独立样本验证了模型的准确性。我们评估了相关性分数和海马体积的相关性，以验证这种方法的临床实用性。为了提高模型的可理解性，我们实现了3D CNN相关图的交互式可视化。结果如下：在三个独立的数据集中，组分离显示AD痴呆与对照组相比具有高准确性（AUC $\geq$ 0.92），MCI与对照组相比具有中等准确性（AUC $\approx$ 0.75）。相关图表明，海马萎缩被认为是AD检测的最具信息性的因素，其他皮质和皮质下区域的萎缩也有贡献。海马内的相关性分数与海马体积高度相关（Pearson r $\approx$-0.86，p<0.001）。结论：相关图突出显示了我们事先假设的区域萎缩。这增强了CNN模型的可理解性，这些模型是基于扫描和诊断标签以纯数据驱动的方式进行训练的。
