Quantitative magnetic resonance imaging (qMRI) offers tissue-specific physical parameters with significant potential for neuroscience research and clinical practice. However, lengthy scan times for 3D multiparametric qMRI acquisition limit its clinical utility. Here, we propose SUMMIT, an innovative imaging methodology that includes data acquisition and an unsupervised reconstruction for simultaneous multiparametric qMRI. SUMMIT first encodes multiple important quantitative properties into highly undersampled k-space. It further leverages implicit neural representation incorporated with a dedicated physics model to reconstruct the desired multiparametric maps without needing external training datasets. SUMMIT delivers co-registered T, T, T, and subvoxel quantitative susceptibility mapping. Extensive simulations, phantom, and in vivo brain imaging demonstrate SUMMIT's high accuracy. Notably, SUMMIT uniquely unravels microstructural alternations in patients with white matter hyperintense lesions with high sensitivity and specificity. Additionally, the proposed unsupervised approach for qMRI reconstruction also introduces a novel zero-shot learning paradigm for multiparametric imaging applicable to various medical imaging modalities.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.media.2025.103530 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
An Integrated Fuzzy Neural Network and Topological Data Analysis for Molecular Graph Representation Learning and Property Forecasting.
Mol Inform
March 2025
Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam.
Within a recent decade, graph neural network (GNN) has emerged as a powerful neural architecture for various graph-structured data modelling and task-driven representation learning problems. Recent studies have highlighted the remarkable capabilities of GNNs in handling complex graph representation learning tasks, achieving state-of-the-art results in node/graph classification, regression, and generation. However, most traditional GNN-based architectures like GCN and GraphSAGE still faced several challenges related to the capability of preserving the multi-scaled topological structures.
View Article and Find Full Text PDFBreast cancer is the most prevalent cancer among women and poses a significant global health challenge due to its association with uncontrolled cell proliferation. Artificial intelligence (AI) integration into medical practice has shown promise in boosting diagnosis accuracy and treatment protocol optimisation, thus contributing to improved survival rates globally. This paper presents a comprehensive analysis utilizing the Wisconsin Breast Cancer dataset, comprising data from 569 patients and 30 attributes.
View Article and Find Full Text PDFThis study presents a novel deep learning approach for surface electromyography (sEMG) gesture recognition using stacked autoencoder neural network (SAE)s. The method leverages hierarchical representation learning to extract meaningful features from raw sEMG signals, enhancing the precision and robustness of gesture classification.•Feature Extraction and Classification MODWT Decomposition: The sEMG signals were decomposed using the MODWT DECOMPOSITION(Maximal Overlap Discrete Wavelet Transform) to capture various frequency components.
View Article and Find Full Text PDFCoordinate-based neural representation enabling zero-shot learning for fast 3D multiparametric quantitative MRI.
Med Image Anal
March 2025
School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China; National Engineering Research Center of Advanced Magnetic Resonance Technologies for Diagnosis and Therapy, Shanghai Jiao Tong University, Shanghai, China. Electronic address:
Quantitative magnetic resonance imaging (qMRI) offers tissue-specific physical parameters with significant potential for neuroscience research and clinical practice. However, lengthy scan times for 3D multiparametric qMRI acquisition limit its clinical utility. Here, we propose SUMMIT, an innovative imaging methodology that includes data acquisition and an unsupervised reconstruction for simultaneous multiparametric qMRI.
View Article and Find Full Text PDFStudy-phase reinstatement predicts subsequent recall.
Nat Neurosci
March 2025
Department of Psychology, University of Pennsylvania, Philadelphia, PA, USA.
Can the brain improve the retrievability of an experience after it has occurred? Systems consolidation theory proposes that item-specific cortical reactivation during post-encoding rest periods facilitates the formation of stable memory representations, a prediction supported by neural evidence in humans and animals. Such reactivation may also occur on shorter timescales, offering a potential account of classic list memory phenomena but lacking in support from neural data. Leveraging the high temporal specificity of intracranial electroencephalography (EEG), we investigate spontaneous reactivation of previously experienced items during brief intervals between individual encoding events.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!