Tag: convolutional neural networks

A new multi-task deep learning framework called ApexTransNet segments apical periodontitis lesions and grades radiographic severity on periapical radiographs with ...

CT Scans Teach Chest X-ray AI to Spot Lung Disease With Far Less Data

A new cross-modality knowledge distillation framework uses CT-derived feature supervision to boost chest X-ray classification of lung diseases by up ...

AI Finds Hidden Osteoporosis in Everyday CT Scans, Study Shows

A new study finds that AI software can extract reliable bone mineral density measurements from routine non-contrast CT scans, matching ...

AI Listens to the Body: New Deep Learning Framework Detects Heart and Lung Disease from Sound

Researchers at Saudi Electronic University have developed XCardioPulmoNet, an explainable deep learning framework that classifies heart and lung sounds with ...

New AI Detector Sees Traffic in High and Low Frequencies to Outsmart Cluttered Roads

Researchers have developed a lightweight frequency-based AI detector that achieves state-of-the-art accuracy and real-time speed on cluttered traffic scenes, running ...

Lightweight AI Network Reads Sign Language with Pyramid and Multimodal Boosts

A new lightweight deep learning framework called LCASP-MMANet achieves state-of-the-art sign language recognition accuracy while remaining efficient enough for real-world, ...

Ensemble of Three CNNs Reads Breast Cancer Slides With 97% Accuracy

Researchers in Algeria built a soft-voting ensemble of three convolutional neural networks that classifies breast cancer histopathology images with 97.12 ...

AI Learns to Spot 380-Million-Year-Old Fossil Spores on Microscope Slides

Researchers have built a two-step deep learning pipeline that detects and classifies biostratigraphically important Devonian miospores from Armenia with high ...

Lightweight Vision Transformer Tops CNNs in Sugarcane Disease Detection Test

A controlled benchmark from El Salvador found that the lightweight hybrid MobileViT-v2-100 model reached 96.45 percent accuracy in classifying sugarcane ...

AI Learns to Spot 33 Bacterial Species From Microscope Images in a Fraction of a Second

Researchers in India have built a lightweight, attention-guided deep learning model that classifies 33 bacterial species from Gram-stained microscope images ...

Head-to-Head Test Shows Deep Learning Beats Classic Models Only on Breast Cancer Images

An independent evaluation in PLOS Digital Health finds that deep learning models excel at breast cancer detection from medical images ...

AI Reads the Microscope: Deep Learning Powers Parasite Diagnosis, But Real-World Tests Lag Behind

A scoping review of 118 studies finds that deep learning models excel at detecting parasites in microscopy images under experimental ...

CNN or Transformer? AI Duel Reveals Best Way to Read X-ray Patterns

A controlled head-to-head study shows Vision Transformers beat convolutional networks on real X-ray diffraction data once fine-tuned, while CNNs remain ...

Deep Learning Teaches Satellites to Watch Soil Moisture Change Within a Single Day

A localized convolutional neural network trained on ASCAT satellite radar data outperforms the operational soil moisture product and, during heavy ...

AI Learns to Tell Living From Dead Microscopic Ocean Fossils

Researchers have trained convolutional neural networks on images from a modified 3D printer to automatically identify living, Rose Bengal-stained benthic ...

AI Learns to Diagnose Grapevine Diseases Like a Plant Pathologist

Researchers in Vietnam have built a hybrid vision-language AI that diagnoses grapevine diseases with 98.7 percent accuracy while explaining its ...

Banks Team Up to Catch Fraud Without Sharing Your Data