New Machine Learning Framework Combines fMRI Amplitude and Phase Data to Improve Brain Disorder Detection
Researchers have proposed a multi-scale fusion learning framework (MSFL) that integrates both amplitude and phase information from fMRI signals to classify brain disorders such as autism spectrum disorder (ASD) and major depressive disorder (MDD). Traditional dynamic functional connectivity methods rely only on amplitude-based correlations, while the new approach adds phase synchronization as a complementary feature. The study reports that MSFL significantly outperforms existing models, suggesting that combining these two signal properties could improve neuroimaging-based diagnosis.
A team of researchers has introduced MSFL (Multi-Scale Fusion Learning), a deep learning framework designed to improve the detection of brain disorders from resting-state fMRI data. Conventional approaches to dynamic functional connectivity (dFC) typically use sliding window correlation (SWC), which captures how amplitude correlations between brain regions change over time, but ignore phase information. MSFL incorporates both SWC-derived amplitude correlations and phase synchronization (PS), which measures the coherence of signal phases between brain regions, treating them as complementary features. The framework was evaluated on two publicly available datasets—ABIDE I for autism spectrum disorder and REST-meta-MDD for major depressive disorder—and reportedly outperformed existing comparative models on both. Explainability analysis using the SHAP framework confirmed that both feature types contribute meaningfully to disorder detection, lending interpretability to the model's decisions. The preprint was first submitted in March 2026 and revised in June 2026, and has not yet undergone formal peer review.
What's missing
As a preprint, this work has not yet been peer-reviewed, which is a key caveat. The study does not report specific performance metrics (e.g., accuracy, AUC) in the abstract, making it difficult to assess the magnitude of improvement over baseline models. It is also unclear whether the framework was tested on held-out external datasets beyond the two used, limiting assessment of generalizability. Class imbalance, site effects across multi-site datasets like ABIDE I and REST-meta-MDD, and potential confounds (age, sex, medication status) are common limitations in neuroimaging classification studies that are not addressed in the available abstract.
What different sources said
- arXiv cs.AICenter
Fusion Learning from Dynamic Functional Connectivity: Combining the Amplitude and Phase of fMRI Signals to Identify Brain Disorders
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.