FlexiBrain: New AI Framework Processes Brain Imaging Data Without Destructive Preprocessing
Researchers have proposed FlexiBrain, a machine learning framework that can process fMRI brain scan data directly in its native resolution without requiring lengthy preprocessing to standardize datasets. Most existing deep learning approaches for fMRI analysis force all data into a uniform format, which can destroy subject-specific anatomical detail and takes hours of computation per participant. FlexiBrain addresses this bottleneck and could accelerate the development of large-scale brain imaging AI models.
A preprint posted to arXiv introduces FlexiBrain, a resolution-agnostic voxel-level encoding framework designed to handle the heterogeneity inherent in fMRI data collected across different research sites and scanner configurations. Current deep learning pipelines typically require extensive preprocessing to normalize spatial and temporal resolution differences, a process that risks degrading individual anatomical information and imposes significant computational costs. FlexiBrain sidesteps this by defining patch sizes in real-world physical units and using dynamic patch resizing, allowing the model to ingest data in its native space. The framework is built on a Mamba-JEPA backbone, chosen for its efficiency in modeling high-dimensional 4D fMRI signals. Evaluated across five downstream neuroscience tasks, FlexiBrain outperformed recent state-of-the-art methods by up to 12 percentage points without relying on external data augmentation. The authors describe it as a plug-in module intended to reduce preprocessing overhead and support the development of generalizable fMRI foundation models. Code has been made publicly available.
What's missing
As a preprint, FlexiBrain has not yet undergone peer review. The paper does not report computational resource requirements for training the model itself, nor does it detail how performance scales with dataset size or scanner diversity. Generalizability to clinical fMRI populations and task domains beyond the five evaluated remains untested.
What different sources said
- arXiv cs.LGCenter
FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI
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.