Late combination shows that MEG adds to MRI in classifying MCI versus controls.

Neuroimage

MRC Cognition and Brain Sciences Unit, University of Cambridge, UK; Department of Psychiatry, University of Cambridge, UK. Electronic address:

Published: May 2022

Early detection of Alzheimer's disease (AD) is essential for developing effective treatments. Neuroimaging techniques like Magnetic Resonance Imaging (MRI) have the potential to detect brain changes before symptoms emerge. Structural MRI can detect atrophy related to AD, but it is possible that functional changes are observed even earlier. We therefore examined the potential of Magnetoencephalography (MEG) to detect differences in functional brain activity in people with Mild Cognitive Impairment (MCI) - a state at risk of early AD. We introduce a framework for multimodal combination to ask whether MEG data from a resting-state provides complementary information beyond structural MRI data in the classification of MCI versus controls. More specifically, we used multi-kernel learning of support vector machines to classify 163 MCI cases versus 144 healthy elderly controls from the BioFIND dataset. When using the covariance of planar gradiometer data in the low Gamma range (30-48 Hz), we found that adding a MEG kernel improved classification accuracy above kernels that captured several potential confounds (e.g., age, education, time-of-day, head motion). However, accuracy using MEG alone (68%) was worse than MRI alone (71%). When simply concatenating (normalized) features from MEG and MRI into one kernel (Early combination), there was no advantage of combining MEG with MRI versus MRI alone. When combining kernels of modality-specific features (Intermediate combination), there was an improvement in multimodal classification to 74%. The biggest multimodal improvement however occurred when we combined kernels from the predictions of modality-specific classifiers (Late combination), which achieved 77% accuracy (a reliable improvement in terms of permutation testing). We also explored other MEG features, such as the variance versus covariance of magnetometer versus planar gradiometer data within each of 6 frequency bands (delta, theta, alpha, beta, low gamma, or high gamma), and found that they generally provided complementary information for classification above MRI. We conclude that MEG can improve on the MRI-based classification of MCI.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8987738PMC
http://dx.doi.org/10.1016/j.neuroimage.2022.119054DOI Listing

Publication Analysis

Top Keywords

meg
9
mri
9
late combination
8
combination meg
8
mci versus
8
versus controls
8
structural mri
8
classification mci
8
planar gradiometer
8
gradiometer data
8

Similar Publications

SN1-type alkylating reagents generate O6-methylguanine (meG) lesions that activate the mismatch repair (MMR) response. Since post-replicative MMR specifically targets the nascent strand, meG on the template strand is refractory to rectification by MMR and, therefore, can induce non-productive MMR reactions. The cycling of futile MMR attempts is proposed to cause DNA double-strand breaks in the subsequent S phase, leading to ATR-checkpoint-mediated G2 arrest and apoptosis.

View Article and Find Full Text PDF

Do machines and humans process language in similar ways? Recent research has hinted at the affirmative, showing that human neural activity can be effectively predicted using the internal representations of language models (LMs). Although such results are thought to reflect shared computational principles between LMs and human brains, there are also clear differences in how LMs and humans represent and use language. In this work, we systematically explore the divergences between human and machine language processing by examining the differences between LM representations and human brain responses to language as measured by Magnetoencephalography (MEG) across two datasets in which subjects read and listened to narrative stories.

View Article and Find Full Text PDF

Corrigendum to "Extended homogeneous field correction method based on oblique projection in OPM-MEG" [NeuroImage 306(2025) 120991].

Neuroimage

January 2025

Key Laboratory of Ultra-Weak Magnetic Field Measurement Technology, Ministry of Education, School of Instrumentation and Optoelectronic Engineering, Beihang University, 100191, Beijing, China; Hangzhou Institute of Extremely-Weak Magnetic Field Major National Science and Technology Infrastructure, Hangzhou, 310051, China; State Key Laboratory of Traditional Chinese Medicine Syndrome/Health Construction Center, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, 510120, China; Hefei National Laboratory, Hefei, 230088, China. Electronic address:

View Article and Find Full Text PDF

Functional near-infrared spectroscopy (fNIRS) is an increasingly popular neuroimaging technique that measures cortical hemodynamic activity in a non-invasive and portable fashion. Although the fNIRS community has been successful in disseminating open-source processing tools and a standard file format (SNIRF), reproducible research and sharing of fNIRS data amongst researchers has been hindered by a lack of standards and clarity over how study data should be organized and stored. This problem is not new in neuroimaging, and it became evident years ago with the proliferation of publicly available neuroimaging datasets.

View Article and Find Full Text PDF

The human visual system possesses a remarkable ability to detect and process faces across diverse contexts, including the phenomenon of face pareidolia--seeing faces in inanimate objects. Despite extensive research, it remains unclear why the visual system employs such broadly tuned face detection capabilities. We hypothesized that face pareidolia results from the visual system's optimization for recognizing both faces and objects.

View Article and Find Full Text PDF

Want 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!