Lightweight AI Tool Classifies Stroke Types from Brain CT Scans
A lightweight AI pipeline combining wavelet and texture features classified hemorrhagic stroke, ischemic stroke and normal tissue on brain CT ...
A lightweight AI pipeline combining wavelet and texture features classified hemorrhagic stroke, ischemic stroke and normal tissue on brain CT ...
A knowledge-distilled convolutional network reached 92.64 percent accuracy on an independent breast ultrasound dataset, outperforming chief physicians in a retrospective ...
A new lightweight three-branch neural network called FLIFuse classifies bacterial pneumonia, viral pneumonia, and normal chest X-rays with 91.4 percent ...
A Japanese research team built a deep learning framework called MMMID that tracks beating heart muscle motion from 4D cardiac ...
A new hybrid convolution-Mamba network uses dual-domain masked image modeling to diagnose developmental dysplasia of the hip from B-mode ultrasound ...
A hybrid machine learning framework fusing autoencoder-learned representations with handcrafted texture features achieved approximately 99.85% test accuracy for cervical cancer ...
Researchers at the Vellore Institute of Technology developed three hybrid deep learning models combining convolutional networks, transformers, and clinical metadata ...
A new stochastic fractal search-based framework pairs nature-inspired optimization with a lightweight k-nearest neighbor classifier to classify mammographic lesions with ...
A new deep learning model combines diffusion-style state propagation with Mamba-based sequence modeling and window attention to grade ulcerative colitis ...
A Stanford team shows a transparent web-based staging tool cuts Ann Arbor staging time and errors in pediatric Hodgkin lymphoma, ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine