Tag: medical imaging

This article delves into the critical role of Right Ventricle (RV) dysfunction in assessing the risk of Pulmonary Embolism (PE), highlighting how multimodal Artificial Intelligence (AI) is revolutionizing diagnostic accuracy and prognostic capabilities. It explores the challenges in traditional RV imaging and quantifies the advancements brought by AI in analyzing complex cardiac data.

A novel two-stage natural language processing pipeline, integrating BERT and a large language model (LLM), significantly enhances the classification of entities and mapping of relationships within radiology reports. This approach achieves notable accuracy in lesion-location mapping for chest CTs and diagnosis-episode mapping for brain MRIs, promising improved diagnostic insights and patient care.

This article introduces MIRAGE, a groundbreaking multimodal foundation model designed for comprehensive retinal OCT image analysis. It addresses the limitations of existing models by integrating multiple imaging modalities and establishing a new benchmark for evaluating AI in ophthalmology.

A novel AI method, MetaSeg, is revolutionizing medical image analysis by achieving high segmentation performance with significantly reduced computational resources, paving the way for more accessible and efficient diagnostic tools.