Multimodal Deep Learning Network Achieves 96% Accuracy in Brain Tumor Classification
Researchers developed a two-branch neural network that combines MRI images with 91 radiomic features to classify brain tumors into four categories, achieving 96.13% accuracy with gated fusion. The approach mimics how clinicians synthesize multiple data types rather than relying on imaging alone. This multimodal strategy could improve diagnostic accuracy and support clinical decision-making in neuro-oncology.
A new deep learning architecture combines raw MRI scans with extracted radiomic features—including intensity, texture, shape, and boundary descriptors—to classify brain tumors into glioma, meningioma, pituitary, and no-tumor categories. The model uses a two-stream design with a pre-trained CNN for image encoding and a dedicated MLP for radiomic feature encoding, with fusion achieved through concatenation, gating, or bidirectional cross-modal attention mechanisms. Tested across nine runs on a balanced dataset of 7,200 images, all multimodal configurations outperformed unimodal baselines, with gated fusion reaching the highest accuracy of 96.13%. The approach addresses a key limitation in existing deep learning models: most rely solely on imaging data and fail to replicate the multimodal reasoning clinicians use when integrating patient symptoms, medical history, and quantitative imaging data. This work demonstrates that incorporating radiomic features alongside raw images can enhance classification performance.
What's missing
The study does not report sensitivity, specificity, precision, recall, or F1-scores for individual tumor classes, limiting assessment of performance across different diagnostic categories. Generalization to external datasets and comparison with other multimodal fusion approaches are not discussed. The clinical validation status and whether the model has been tested on prospective patient data remain unclear.
What different sources said
- arXiv cs.LGCenter
Multimodal Brain Tumour Classification Using Feature Fusion
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.