Computer Graphics Forum, EarlyView.We present an interactive visual analysis tool to study how patient‐specific tissue properties influence radiofrequency ablation outcomes. Using a deep‐learning surrogate model, we predict ablation volumes for unseen parameter settings with accuracy superior to interpolation, supporting improved treatment planning. Abstract Radiofrequency (RF) ablation
R. Sabbagh Gol +7 more
wiley +1 more source
Nuclei Detection and Segmentation of Histopathological Images Using a Feature Pyramidal Network Variant of a Mask R-CNN. [PDF]
Bioengineering (Basel)Ramakrishnan V +10 more
europepmc +1 more source
Textile and colour defect detection using deep learning methods
Coloration Technology, EarlyView.Abstract Recent advances in deep learning (DL) have significantly enhanced the detection of textile and colour defects. This review focuses specifically on the application of DL‐based methods for defect detection in textile and coloration processes, with an emphasis on object detection and related computer vision (CV) tasks.
Hao Cui +2 more
wiley +1 more source
Dilated Heterogeneous Convolution for Cell Detection and Segmentation Based on Mask R-CNN. [PDF]
Sensors (Basel)Hu F, Hu H, Xu H, Xu J, Chen Q.
europepmc +1 more source
Advances in Electrocardiogram‐Based Non‐Invasive Blood Glucose Monitoring Technology
Diabetes, Obesity and Metabolism, EarlyView.ABSTRACT Blood glucose monitoring is fundamental to diabetes management, yet traditional invasive methods are limited by patient discomfort and infection risks. In recent years, electrocardiogram (ECG), a conventional tool for cardiovascular assessment, has gained attention as a prospective method for non‐invasive blood glucose monitoring.
Qi Zeng +5 more
wiley +1 more source
Pig Weight Estimation Method Based on a Framework Combining Mask R-CNN and Ensemble Regression Model. [PDF]
Animals (Basel)Jiang S +5 more
europepmc +1 more source
Fish and Fisheries, EarlyView.ABSTRACT Monitoring recreational fisheries is difficult: anglers are widely dispersed, gear and practices vary, and many species are involved, which leads to fragmented and scarce data. To address these issues, we developed an Artificial Intelligence (AI) pipeline that turns angler‐reported photos into standardised records of catch composition and ...
Marco Signaroli +9 more
wiley +1 more source
Pipeline multi-type high consequence area identification based on mask R-CNN with fused attention mechanisms. [PDF]
Sci RepXiaojun D +4 more
europepmc +1 more source
International Endodontic Journal, EarlyView.ABSTRACT Aim This study evaluated the effect of a short, personalised training session on student performance in using an artificial intelligence (AI)‐based platform for pulp exposure prediction before caries excavation and determined the required sample size for a further randomised controlled trial (RCT).
Shaqayeq Ramezanzade +5 more
wiley +1 more source
Towards a More Reliable Identification of Non-Conformities in Railway Cars: Experiments with Mask R-CNN, U-NET, and Ensembles on Unbalanced and Balanced Datasets. [PDF]
Sensors (Basel)Carvalho E +6 more
europepmc +1 more source