Tag: medical image analysis

A three-dimensional deep learning pipeline automates total kidney volume measurement and Mayo risk classification from noncontrast CT scans in autosomal ...

A deep learning framework combining DINOv2 representations with Monte Carlo Dropout and temperature scaling successfully quantifies diagnostic uncertainty and calibrates ...

Spanish researchers found that artificial intelligence models achieved moderate accuracy when detecting stroke lesions in non-contrast brain magnetic resonance imaging ...

Researchers have developed bmri-ai-prep, an open-source modular preprocessing pipeline and standardized data structure that preserves three-dimensional volumetric relationships while isolating ...

A novel explainable Vision Transformer framework integrating paired mammographic views achieved high diagnostic classification accuracy and superior explanation faithfulness across ...

Researchers have introduced ClinFusion-Net, a hybrid deep learning model combining convolutional networks and vision transformers for explainable gastrointestinal disease classification.

Computer scientists have developed AV-MapNet, an end-to-end deep learning framework that combines multi-scale feature extraction, sequential residual refinement, and geodesic ...

Researchers evaluated black-box adversarial attacks and inference-time defenses on a deep learning model for thyroid nodule segmentation in ultrasound images.

Researchers developed MSDR-Net, a deep learning model that differentiates benign and malignant spinal tumors on T2-weighted fat-suppressed MRI scans with ...

A compact residual network called MSERNet removes JPEG compression artifacts from ovarian and carotid ultrasound images while preserving tissue textures ...