We propose a novel framework for Alzheimer's disease (AD) detection using brain MRIs. The framework starts with a data augmentation method called Brain-Aware Replacements (BAR), which leverages a standard brain parcellation to replace medically-relevant 3D brain regions in an anchor MRI from a randomly picked MRI to create synthetic samples. Ground truth "hard" labels are also linearly mixed depending on the replacement ratio in order to create "soft" labels. BAR produces a great variety of realistic-looking synthetic MRIs with higher local variability compared to other mix-based methods, such as CutMix. On top of BAR, we propose using a soft-label-capable supervised contrastive loss, aiming to learn the relative similarity of representations that reflect how mixed are the synthetic MRIs using our soft labels. This way, we do not fully exhaust the entropic capacity of our hard labels, since we only use them to create soft labels and synthetic MRIs through BAR. We show that a model pre-trained using our framework can be further fine-tuned with a cross-entropy loss using the hard labels that were used to create the synthetic samples. We validated the performance of our framework in a binary AD detection task against both from-scratch supervised training and state-of-the-art self-supervised training plus fine-tuning approaches. Then we evaluated BAR's individual performance compared to another mix-based method CutMix by integrating it within our framework. We show that our framework yields superior results in both precision and recall for the AD detection task.
On self-supervised multi-modal representation learning: An application to Alzheimer's disease
Georgia Institute of Technology（佐治亚理工学院）；Georgia State University（佐治亚州立大学）；Emory University（埃默里大学）；Center for Translational Research in Neuroimaging and Data Science（神经影像与数据科学转化研究中心）；Mila（米拉）；Université de Montréal（蒙特利尔大学）
Self-Supervised Multimodal Domino: in Search of Biomarkers for Alzheimer's Disease
Georgia Institute of Technology（佐治亚理工学院）；Georgia State University（佐治亚州立大学）；Emory University（埃默里大学）；Center for Translational Research in Neuroimaging and Data Science（神经影像学与数据科学转化研究中心）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Delft University of Technology（代尔夫特理工大学）
LEAD: An EEG Foundation Model for Alzheimer's Disease Detection
Department of Computer Science, University of North Carolina at Charlotte, United States（北卡罗来纳州立大学计算机科学系）；DICEAM Department, University Mediterranea of Reggio Calabria, Italy（雷焦卡拉布里亚地中海大学DICEAM系）
Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
Johns Hopkins University（约翰斯·霍普金斯大学）
在最近的研究中，自我监督的预训练模型在迁移学习中往往优于监督的预训练模型。特别地，话语级语音表示的自监督学习（SSL）可以用于需要话语内的一致属性（说话者、语言、情感和年龄）的区别性表示的语音应用中。现有的帧级自监督语音表示，例如，wav 2 vec可以用作具有池化的话语级表示，但是模型通常很大。也有SSL技术来学习话语级表示。最成功的方法之一是对比方法，该方法需要负采样：选择替代样本与当前样本（锚点）进行对比。然而，这并不能确保所有阴性样本属于与没有标签的锚点类不同的类。本文采用一种非对比的自监督方法来学习话语级嵌入。我们将DINO（Distillation with NO Labels）从计算机视觉应用到语音。与对比方法不同，DINO不需要负采样。我们将DINO与以监督方式训练的x向量进行了比较。当转移到下游任务（说话人验证，语音情感识别（SER）和阿尔茨海默病检测）时，DINO的表现优于x-vector。我们研究了迁移学习过程中几个方面的影响，例如将微调过程划分为步骤，块长度或增强。在微调过程中，首先调整最后一个仿射层，然后整个网络一次性超过微调。使用较短的块长度，尽管它们生成更多样化的输入，但并不一定提高性能，这意味着每个应用程序需要至少具有特定长度的语音片段才能获得更好的性能。增强对SER有帮助。
VisTA: Vision-Text Alignment Model with Contrastive Learning using Multimodal Data for Evidence-Driven, Reliable, and Explainable Alzheimer's Disease Diagnosis
Centre hospitalier universitaire vaudois (CHUV)（洛桑大学医院中心（CHUV））；Université de Lausanne (UNIL)（洛桑大学（UNIL））；VNU University of Engineering and Technology, Vietnam National University（越南国家大学下属越南工程技术大学）；University of Science, Vietnam National University Ho Chi Minh City（胡志明市越南国家大学下属科学大学）；Military Hospital 175（175军事医院）；School of Biomedical Engineering, International University, Vietnam National University（越南国家大学下属国际大学生物医学工程学院）
HIBMatch: Hypergraph Information Bottleneck for Semi-supervised Alzheimer's Progression
Department of Applied Mathematics and Theoretical Physics, University of Cambridge（应用数学与理论物理系，剑桥大学）；Department of Biomedical Engineering, The Hong Kong Polytechnic University（生物医学工程系，香港理工大学）；Research Institute for Artificial Intelligence of Things, The Hong Kong Polytechnic University（物联网人工智能研究所，香港理工大学）；Yau Mathematical Sciences Centre, Tsinghua University（叶德平数学科学中心，清华大学）
GMN4AD: Graph Matching Network for Alzheimer's Disease Diagnosis with Test-Time Domain Adaptation using Multi-centered Structure Magnetic Resonance Imaging
Department of Computer Science, Kennesaw State University（肯纳邦大学计算机科学系）；Department of Information Technology, Kennesaw State University（肯纳邦大学信息技术系）；School of Data Science and Analytics, Kennesaw State University（肯纳邦大学数据科学与分析学院）；Department of Applied Computing, Michigan Technological University（密歇根技术大学应用计算系）
REMEMBER: Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis
Lausanne University Hospital (CHUV)（洛桑大学医院（CHUV））；University of Lausanne (UNIL)（洛桑大学（UNIL））；Vietnam National University（越南国立大学）；University of Science, Vietnam National University Ho Chi Minh City（越南国立大学胡志明市科学大学）；International University, Vietnam National University Ho Chi Minh City（越南国立大学胡志明市国际大学）
Self-Supervised Cross-Encoder for Neurodegenerative Disease Diagnosis
School of Mathematics and Statistics, Glasgow, UK（数学与统计学学院，英国格拉斯哥）；Department of Computer and Information Sciences, University of Strathclyde, Glasgow, UK（计算机与信息科学系，斯特拉斯克莱德大学，英国格拉斯哥）
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Youtu Lab, Tencent（腾讯优图实验室）；Peking University（北京大学）；Wechat Pay, Tencent（腾讯微信支付）；School of Software Technology, Zhejiang University（浙江大学软件技术学院）
