Tag: radiology

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.

Australia's national science agency, CSIRO, has developed a groundbreaking multimodal AI that integrates diverse patient data with X-ray images to significantly enhance diagnostic accuracy and reporting efficiency, addressing the growing demand for radiologists.

This tutorial explores how Retrieval-Augmented Generation (RAG) significantly improves the quality and safety of local Large Language Models (LLMs) in radiology contrast media consultations. We delve into the methodology, performance improvements, and practical implications for healthcare institutions seeking privacy-preserving AI solutions.

Cortechs.ai, a leader in AI-driven neuroimaging software, has acquired intellectual property from ZepMed, including its patented CT imaging technologies and NeuroAlign CT™ software. This move significantly enhances Cortechs.ai's capabilities in radiological innovation and expands its suite of solutions for global clinicians.