Foundation models for discovering robust biomarkers of neurological disorders from dynamic functional connectivity
College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算与数据科学学院，新加坡）；Department of Biomedical Engineering and the School of Artificial Intelligence and Data Engineering, Indian Institute of Technology Ropar, India（印度理工学院罗帕尔分校生物医学工程系和人工智能与数据工程学院）；College of Instrument and Computer Science, Zhejiang University, China（浙江大学仪器与计算机科学学院）
Deepank Girish, Yi Hao Chan, Sukrit Gupta, Jing Xia, Jagath C. Rajapakse
Several brain foundation models (FM) have recently been proposed to predict brain disorders by modelling dynamic functional connectivity (FC). While they demonstrate remarkable model performance and zero- or few-shot generalization, the salient features identified as potential biomarkers are yet to be thoroughly evaluated. We propose RE-CONFIRM, a framework for evaluating the robustness of potential biomarker candidates elucidated by deep learning (DL) models including FMs. From experiments on five large datasets of Autism Spectrum Disorder (ASD), Attention-deficit Hyperactivity Disorder (ADHD), and Alzheimer's Disease (AD), we found that although commonly used performance metrics provide an intuitive assessment of model predictions, they are insufficient for evaluating the robustness of biomarkers identified by these models. RE-CONFIRM metrics revealed that simply finetuning FMs leads to models that fail to capture regional hubs effectively, even in disorders where hubs are known to be implicated, such as ASD and ADHD. In view of this, we propose Hub-LoRA (Low-Rank Adaptation) as a fine-tuning technique that enables FMs to not only outperform customised DL models but also produce neurobiologically faithful biomarkers supported by meta-analyses. RE-CONFIRM is generalizable and can be easily applied to ascertain the robustness of DL models trained on functional MRI datasets. Code is available at: https://github.com/SCSE-Biomedical-Computing-Group/RE-CONFIRM.
Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic review
College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Department of Computer Science and Engineering, Indian Institute of Technology（印度理工学院计算机科学与工程系）
Yale University（耶鲁大学）；Yale School of Medicine（耶鲁医学院）
Autism spectrum disorder (ASD) is a complex neurodevelopmental disorder. Finding the biomarkers associated with ASD is extremely helpful to understand the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. Although Deep Neural Networks (DNNs) have been applied in functional magnetic resonance imaging (fMRI) to identify ASD, understanding the data-driven computational decision making procedure has not been previously explored. Therefore, in this work, we address the problem of interpreting reliable biomarkers associated with identifying ASD; specific…
Deep learning and whole-brain networks for biomarker discovery: modeling the dynamics of brain fluctuations in resting-state and cognitive tasks
Electric and Computer Engineering Department, Universidad Nacional del Sur（国家南方大学电子与计算机工程系）；Institute of Computer Science and Engineering, National Scientific and Technological Research Council of Argentina (CONICET)（阿根廷国家科学与技术研究理事会计算机科学与工程研究所）；Center for Brain and Cognition, Computational Neuroscience Group, Department of Information and Communication Technologies, Universitat Pompeu Fabra（庞培法布拉大学脑认知中心、信息与通信技术系计算神经科学组）；Institució Catalana de la Recerca i Estudis Avançats (ICREA)（加泰罗尼亚高级研究与教育研究所）；Department of Information and Communication Technologies, Universitat Pompeu Fabra（庞培法布拉大学信息与通信技术系）；ViRVIG, University of Girona（吉罗纳大学ViRVIG）
BrainPrompt: Multi-Level Brain Prompt Enhancement for Neurological Condition Identification
College of Computing and Data Science, Nanyang Technological University, Singapore（南洋理工大学计算与数据科学学院）；Saw Swee Hock School of Public Health at National University of Singapore, Singapore（新加坡国立大学 Saw Swee Hock 公共卫生学院）；Xi’an Jiaotong University, Xi’an, Shaanxi（西安交通大学）；S-Lab, Nanyang Technological University, Singapore（南洋理工大学 S 实验室）
Discovering Subtypes of Neurodegenerative Progression with a Scalable Connectome-Constrained Dynamic Model
Illinois Institute of Technology（伊利诺伊理工学院）；Amsterdam UMC（阿姆斯特丹大学医学中心）；Inria, Université Côte d’Azur（法国国家信息与自动化研究所，蔚蓝海岸大学）；University of Southern California（南加州大学）
National Institute of Technology Silchar（西尔查尔国家理工学院）；Indian Institute of Technology Indore（印多尔印度理工学院）
In the human brain, essential iron molecules for proper neurological functioning exist in transferrin (tf) and ferritin (Fe3) forms. However, its unusual increment manifests iron overload, which reacts with hydrogen peroxide. This reaction will generate hydroxyl radicals, and irons higher oxidation states. Further, this reaction causes tissue damage or cognitive decline in the brain and also leads to neurodegenerative diseases. The susceptibility difference due to iron overload within the volume of interest (VOI) responsible for field perturbation of MRI and can benefit in estimating the neura…
Traumatic brain injury is a global public health problem associated with chronic neurological complications and long-term disability. Biomarkers that map onto the underlying brain pathology driving these complications are urgently needed to identify individuals at risk for poor recovery and to inform design of clinical trials of neuroprotective therapies. Neuroinflammation and neurodegeneration are two endophenotypes associated with increases in brain extracellular water content after trauma. The objective of this study was to describe the relationship between a neuroimaging biomarker of extra…
Ageing impacts the brain's structural and functional organization and over time leads to various disorders, such as Alzheimer's disease and cognitive impairment. The process also impacts sensory function, bringing about a general slowing in various perceptual and cognitive functions. Here, we analyze the Cambridge Centre for Ageing and Neuroscience (Cam-CAN) resting-state magnetoencephalography (MEG) dataset -- the largest ageing cohort available -- in light of the quasicriticality framework, a novel organizing principle for brain functionality which relates information processing and scaling …
Evidence suggests that brain network dynamics is a key determinant of brain function and dysfunction. Here we propose a new framework to assess the dynamics of brain networks based on recurrence analysis. Our framework uses recurrence plots and recurrence quantification analysis to characterize dynamic networks. For resting-state magnetoencephalographic dynamic functional networks (dFNs), we have found that functional networks recur more quickly in people with epilepsy than healthy controls. This suggests that recurrence of dFNs may be used as a biomarker of epilepsy. For stereo electroencepha…
A cry for help: Early detection of brain injury in newborns
Ubenwa Health（乌本科健康）；Mila-Québec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）；Enugu State University Teaching Hospital（埃努古州立大学教学医院）；Lagos State University Teaching Hospital（拉各斯州立大学教学医院）；Lagos State University College of Medicine（拉各斯州立大学医学院）；Rivers State University Teaching Hospital（河流州立大学教学医院）；Université de Montréal（蒙特利尔大学）；DeepMind（深度思考）
Wavelet methods are widely used to decompose fMRI, EEG, or MEG signals into time series representing neurophysiological activity in fixed frequency bands. Using these time series, one can estimate frequency-band specific functional connectivity between sensors or regions of interest, and thereby construct functional brain networks that can be examined from a graph theoretic perspective. Despite their common use, however, practical guidelines for the choice of wavelet method, filter, and length have remained largely undelineated. Here, we explicitly explore the effects of wavelet method (MODWT …
