BI-RADS
PulseAugur coverage of BI-RADS — every cluster mentioning BI-RADS across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
AI models advance ultrasound segmentation with new learning frameworks
Researchers have developed novel multi-task learning frameworks for medical image segmentation, focusing on breast and thyroid ultrasound data. The first approach, using BI-RADS-consistent morphological priors, improves…
-
New AI framework BUSTR generates breast ultrasound reports from limited data
Researchers have developed BUSTR, a novel framework for generating breast ultrasound (BUS) reports using vision-language learning. This system is designed to overcome the scarcity of paired image and radiologist-written…
-
New framework enhances breast cancer classification using dual-view mammography fusion
Researchers have developed a novel token-centric framework for improving breast cancer classification from mammography images by effectively fusing information from craniocaudal (CC) and mediolateral oblique (MLO) views…
-
New AEGIS architecture enhances mammography analysis with Vision Transformers
Researchers have developed AEGIS, a novel joint-embedding predictive architecture for mammography that utilizes Vision Transformer variants. Trained on a large dataset from multiple clinical sites, AEGIS demonstrates st…
-
New AI framework enhances breast cancer diagnosis with structured reasoning
Researchers have developed Latent-CURE, a new diagnostic framework for breast cancer detection using multimodal large models. This framework employs an asymmetric weighted chain-of-thought methodology to ensure structur…
-
New AI framework MammoRG improves mammography report generation
Researchers have developed MammoRG, a new framework for generating mammography reports that integrates prior clinical knowledge and simulates the diagnostic workflow. Unlike previous methods that focused solely on visua…
-
AI models show strong breast density prediction from ultrasounds, generalize well
Researchers externally validated three deep learning models—DenseNet121, ViT-B/32, and ResNet50—for predicting breast density from ultrasound images. The models demonstrated strong performance, particularly in extremely…