Tag: Medical Imaging

New research from IIT Kharagpur shows that federated learning drives models toward flatter loss minima that suppress memorization, and introduces ...

For millions of people living with gout, the painful reality of the disease is written in lumps of crystallized uric ...

Researchers combined a deep autoencoder with K-Means clustering to group brain tumor MRI scans into latent imaging-pattern clusters without any ...

A Chinese research team has developed DeepFusion-HSK, a multimodal deep learning system that distinguishes epithelial from non-epithelial herpes simplex keratitis ...

Every year, millions of women undergo breast imaging that reveals a finding of uncertain significance—a shadow on a mammogram, a ...

Researchers at Xinjiang University developed BGAFS-UNet, a boundary-aware deep learning architecture that improves retinal vessel segmentation fidelity while openly documenting ...

Researchers have built a modular AI framework that improves automated chest X-ray report generation by retrieving similar past cases at ...

Researchers at the Vellore Institute of Technology developed three hybrid deep learning models combining convolutional networks, transformers, and clinical metadata ...

A machine learning model applied to routine CT urography scans can non-invasively predict HER2 status in bladder cancer, potentially guiding ...

Researchers in India report a hybrid dual-attention pyramidal deep learning model that detects liver tumors on CT scans with 96.52 ...

A multicenter study shows a 2.5D Transformer-based AI framework combining clinical data, MRI radiomics and deep learning can reliably distinguish ...

A new study finds that higher waist-to-hip ratio is associated with lower radiation dose in coronary CT angiography, driven primarily ...

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 explainable transformer that combines frequency-domain analysis and topology-aware structural modeling achieves 97.86 percent accuracy in classifying eight retinal ...

A CT-based study of 62 patients found that coronary blood flow measurements decline after transcatheter aortic valve replacement even though ...

Researchers in China have built an explainable deep learning model that analyzes contrast-enhanced CT scans to predict whether non-muscle-invasive bladder ...

A new study evaluates a hybrid quantum algorithm for ECG arrhythmia classification, finding it competitive at moderate resolutions but lacking ...

Researchers have developed a one-click, rule-based pipeline that automatically divides pelvic and proximal femoral CT scans into 81 clinically relevant ...

A retrospective study of 116 patients shows that quantitative CT parameters, especially the maximum enhanced CT value, can reliably distinguish ...

A new meta-analysis of 18 studies finds that deep learning applied to dynamic contrast-enhanced breast MRI achieves 90 percent sensitivity ...