Self-Supervised Vision Transformers Achieve High Accuracy in Detecting Temporomandibular Joint Osteoarthritis on CBCT Scans
Researchers tested self-supervised vision transformer models (DINO family) for detecting temporomandibular joint osteoarthritis on cone-beam CT scans, finding that partial unfreezing of transformer blocks achieved 0.902 AUC. The study addresses a clinical challenge where osseous changes in TMJ osteoarthritis are subtle and difficult to detect automatically. The findings provide practical guidance for adapting foundation models to low-data medical imaging applications.
A new study evaluated how well self-supervised vision transformers from the DINO family transfer to medical imaging tasks, specifically detecting temporomandibular joint osteoarthritis (TMJ OA) on cone-beam CT (CBCT) scans. The researchers developed a slice-based pipeline using Vision Transformer backbones with attention-based multiple instance learning for patient-level classification. Through systematic ablation studies on a multi-source CBCT dataset, they found that partial unfreezing of the final two transformer blocks was the critical factor, improving performance from 0.671 AUC (fully frozen DINOv2) to 0.902 AUC. This outperformed other variants including DINOv1 (0.867), DINOv2 with regularization (0.774), and a supervised ImageNet baseline (0.843). The work demonstrates that adaptation strategy is more important than backbone choice alone for medical imaging applications with limited training data.
What's missing
The study does not report sensitivity, specificity, or other clinical performance metrics beyond AUC; clinical validation or comparison with radiologist performance is not mentioned; generalization to other joint imaging modalities or populations is not discussed; computational requirements and inference time are not provided.
What different sources said
- arXiv cs.AICenter
Self-Supervised Vision Transformers for CBCT-Based Detection of Temporomandibular Joint Osteoarthritis
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.