Realistic Noise Synthesis Improves Machine Learning Accuracy in Diffusion MRI Tissue Analysis
Researchers have developed a Realistic Noise Synthesis (RNS) framework to address systematic bias in supervised machine learning models used to estimate tissue microstructure from diffusion MRI data. The problem arises from a mismatch between the noise characteristics of simulated training data and real acquired signals — a form of covariate shift — which causes SNR-dependent errors, particularly at low signal-to-noise ratios. The findings suggest that accurate noise modelling in training data is essential for reliable, unbiased microstructure estimation in clinical and research diffusion MRI applications.
Diffusion MRI is widely used to non-invasively probe tissue microstructure, but supervised machine learning models trained on simulated data can suffer from systematic parameter bias when the noise properties of simulated signals differ from those of real acquired data. The study, posted to arXiv by Jallais and colleagues, introduces a Realistic Noise Synthesis (RNS) framework that incorporates both the Rician signal expectation — modelled using noise standard deviation estimated via MPPCA — and the effective post-processing noise variance derived from spherical harmonic residuals. The framework was evaluated using two biophysical models, the cylinder-zeppelin and SANDI models, across multiple SNR levels on both simulated and in vivo diffusion datasets with repeated acquisitions. Results showed that ignoring magnitude-induced noise effects during training produced systematic, SNR-dependent bias, while incorporating the Rician expectation reduced bias to levels comparable with noise-aware nonlinear least-squares fitting; additionally modelling the effective standard deviation further improved precision. Performance gains were largely consistent across different regression architectures, though the method proved sensitive to accurate noise estimation. The authors conclude that realistic noise modelling is critical for unbiased supervised microstructure estimation, especially in challenging low-SNR regimes typical of high b-value or high spatial resolution acquisitions.
What's missing
As a preprint, this work has not yet undergone formal peer review, so findings should be interpreted with appropriate caution. The study does not report extensive validation across diverse scanner platforms, field strengths, or clinical populations, which limits generalisability.
What different sources said
- arXiv physicsCenter
Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning
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.