Biology-Aware Harmonization Improves Machine Learning Models for Early Lung Cancer Detection in CT Scans
Researchers developed improved machine learning methods to predict lung cancer in early-stage pulmonary nodules using CT radiomics by combining training data from nodules at different developmental stages. The key innovation was using biology-aware harmonization to correct for variations across different CT imaging protocols, which outperformed standard harmonization approaches. This methodological advance could help detect lung cancer earlier than current standard diagnostic methods, though the study was conducted on a small single-center dataset.
A new study published on arXiv demonstrates that combining radiomic features (quantitative imaging characteristics) from pulmonary nodules at different developmental stages requires careful biological consideration when harmonizing data across multiple CT imaging protocols. Researchers trained machine learning classifiers on 106 early-development nodules and augmented the training set with 225 later-development nodules, comparing three harmonization approaches. Models using biology-aware harmonization—either by incorporating a covariate distinguishing nodule development stages or by harmonizing each dataset separately—achieved significantly higher performance (ROC-AUC 0.74 and 0.71 respectively) compared to biology-unaware harmonization. The findings suggest that standard harmonization techniques may not adequately account for biological differences between nodule populations, potentially degrading model performance. This proof-of-principle methodological study indicates that accounting for biology during data harmonization is critical when augmenting training datasets with heterogeneous sources.
What's missing
The study acknowledges its own limitations: it is a proof-of-principle methodological study conducted on a small single-center dataset, which limits generalizability. The authors do not report external validation on independent multi-center datasets, clinical implementation feasibility, or comparison with radiologist performance. The biological mechanisms underlying why biology-aware harmonization improves performance remain incompletely characterized.
What different sources said
- arXiv physicsCenter
Training Set Augmentation and Biology-Aware Harmonization Improve Radiomic Models for Lung Cancer Prediction in Indeterminate Nodules
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.