New AI Model Improves Nuclei Segmentation in Histopathology Images
Researchers have introduced AMN (Adaptive Multi-Scale Nuclei Network), a deep learning framework for classifying nuclei subtypes in histopathology images that outperforms eight existing baseline models. AMN combines a Swin Transformer and ResNet-50 encoder with a novel multi-objective loss function incorporating boundary-aware and uncertainty-modulated terms. Improved nuclei segmentation accuracy has direct implications for tumor grading, immune infiltrate quantification, and cancer prognosis prediction.
AMN is a dual-encoder segmentation architecture that simultaneously exploits fine-grained local texture features via ResNet-50 and long-range spatial context via a Swin Transformer, fusing the two streams through a learned per-channel gating mechanism that dynamically weights each encoder's contribution at every scale. The model is trained with a composite loss function combining class-weighted focal loss, a boundary-aware loss with positive-pixel emphasis, and a novel uncertainty-modulated classification term designed to suppress overconfident erroneous predictions. Evaluated on the CoNIC benchmark across seven nuclei classes, AMN achieves a mean Dice score of 0.82 and mean F1 of 0.68, including an F1 of 0.67 on the diagnostically challenging lymphocyte class. The framework outperforms eight baselines spanning pure-CNN architectures (U-Net, ResU-Net, DeepLabV3+, SegNet), a pure-transformer model (ViT-Small), and recent hybrid approaches (HmsU-Net, ConvFormer-UNet, BEFUnet). Cross-dataset evaluation on MoNuSeg demonstrated strong generalization without retraining, suggesting the learned representations are robust across different tissue domains.
What's missing
As a preprint, AMN has not yet undergone formal peer review. The study does not report statistical significance tests or confidence intervals for performance comparisons against baselines, making it difficult to assess whether improvements are meaningful. Computational cost, inference speed, and memory requirements relative to baselines are not discussed, which are relevant for clinical deployment. The generalization evaluation on MoNuSeg is described qualitatively without detailed per-class metrics, limiting assessment of where the model may still underperform.
What different sources said
- arXiv physicsCenter
Patient-Level Diagnosis of Acute Myeloid Leukemia via Deep Learning Analysis of Bone Marrow Smear
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.