AI Learns to Simulate Abdominal Ultrasound Scans from Simple Anatomical Maps
Researchers in Argentina have built a two-stage AI pipeline that generates realistic abdominal ultrasound images from simple semantic label maps, ...
Tag: deep learning
AI on a Tiny Chip: Deep Learning Spots Treacher Collins Syndrome at the Edge
Researchers have built a deep learning framework that detects Treacher Collins syndrome from facial images on an NVIDIA Jetson Orin ...
New Loss Function Helps AI Learn From Flawed Labels
The practical significance of the RECE approach becomes clearer when viewed against the broader economics of dataset construction. Annotating large ...
Hybrid AI reads brain scans to stage Alzheimer’s disease in four steps
A hybrid CNN–BiLSTM network with additive attention classifies brain MRI into four Alzheimer's disease stages with 95.94% slice-level accuracy, while ...
New AI Model Sharpens Long-Range Traffic Forecasts by Rewiring Its Own Road Map
Researchers at Dalian Maritime University have developed ESTGCN, a graph neural network that dynamically rewires regional traffic relationships to deliver ...
AI Ensemble Reads Brain Scans With 98.5% Accuracy and Shows Its Work
Researchers in India have built a unified deep learning framework that classifies brain tumors in MRI scans with 98.52 percent ...
AI Grades Ultrasound Image Quality With 95% Accuracy in Breast Cancer Screening
A new deep learning network grades the gain quality of automated breast ultrasound images with 95.49 percent accuracy, outperforming standard ...
AI Learns to Measure Burn Damage From Simple Body Silhouettes
Researchers have developed BurnAreaNet, a deep learning system that estimates total body surface area burned from simple 2D masks with ...
The Grid Gets New Eyes: How AI and Waveform Sensors Are Rewiring Power Monitoring
A new review charts the transition of phasor measurement units from phasor-based reporting to high-fidelity point-on-wave sensing, with artificial intelligence ...
Transformer AI Reconstructs Sharp CT Scans From a Fraction of the Radiation Dose
A new Transformer-based dual-domain AI framework reconstructs high-quality CT images from sparse projection views, potentially reducing patient radiation exposure while ...
AI Learns to Play the Accordion by Encoding Music Theory into a Knowledge Graph
Researchers built a knowledge graph-guided Transformer that generates coherent accordion music with harmonic validity of 94.8 percent and robust thematic ...
How AI Is Quietly Becoming Public Health’s Newest Weapon Against Waste Dangers
A systematic review of 81 studies finds that artificial intelligence is reducing infectious, toxic, and occupational health risks across the ...
AI Learns to Read Brain-Wire Maps to Catch Seizures in Seconds
A new graph-based deep learning model reads the wiring structure of the EEG montage itself to detect every seizure in ...
Fractional Calculus Meets Deep Learning in New Palmprint Authentication Network
A new deep learning architecture called FrDPalmNet combines fractional calculus, dual attention, and densely connected blocks to push palmprint-based biometric ...
AI Reads Heart Rhythms Brilliantly in the Lab, but a Sweeping Review Finds the Clinic Is Still Waiting
A systematic review of 83 studies finds that while deep learning models excel at ECG-based cardiovascular disease prediction, weak external ...
Hidden Flaws in Public Thyroid AI Datasets Could Inflate Diagnostic Performance
A case-level audit of a public thyroid imaging archive finds contradictory labels, leak-prone data splits, and strong evidence that deep ...
Smartphones Could Hear Signs of Child Lung Disease, Deep Learning Study Finds
Researchers in South Korea developed a domain-adaptive deep learning framework that lets smartphones detect abnormal lung sounds in children despite ...
Self-Supervised Transformer Reads Resting-State EEG to Detect Alzheimer’s Disease With 96.42% Accuracy
Alzheimer's disease affects tens of millions of people worldwide, and the World Health Organization estimates that over 55 million people ...
Learnable Activation Head Pushes Alzheimer’s MRI Staging to 94.5 Percent Accuracy
A hybrid model pairing a ConvNeXt backbone with a Kolmogorov–Arnold Network head reaches 94.5 percent accuracy in four-way Alzheimer's staging ...
New AI Model Fuses Sequence and Structure Data to Sharpen Drug-Target Interaction Prediction
A new dual-modality deep learning framework called DHF-DTI combines sequence and graph data with cross-attention fusion and supervised contrastive learning ...
POPULAR NEWS
-
Case Report Explores Caplacizumab in Late-Diagnosed Congenital Thrombotic Thrombocytopenic Purpura
-
Multitask Cambrian Model Improves Protein Melting Temperature Prediction
-
Vasopressors Exert Divergent Immunomodulatory Effects Across a Spectrum in Septic Shock
-
Study Identifies Key Drivers Shaping Salmonid Gill Microbiomes in Aquaculture