AI Tool Launches to Help Radiologists Read Breast MRI
The CE- and UKCA-marked software automatically highlights suspicious lesions and generates structured findings for screening and diagnostic exams.
The CE- and UKCA-marked software automatically highlights suspicious lesions and generates structured findings for screening and diagnostic exams.
AI replacing radiologists is a growing concern. New research examines how these tools are actually used in practice.
The U.S. FDA has released draft guidance on AI-enabled devices, addressing design, risk management, and monitoring, and is seeking public feedback before finalizing the proposals.
RSNA’s 2024 AI challenge used the largest open-source lumbar spine MRI dataset to develop AI models for detecting and classifying degenerative spine conditions, with participation from 1,874 teams worldwide.
Read MoreA study in Radiology found that while AI assistance improves diagnostic accuracy and efficiency in radiology, over-reliance on AI, especially with localized guidance, poses risks of automation bias and diagnostic errors.
Read MoreA Hong Kong-based team has developed the Co-Plane Attention across MRI Sequences deep learning model to classify 12 knee abnormalities from multi-sequence MRI, improving diagnostic accuracy, efficiency, and aligning with clinical standards while bridging expertise gaps in radiology.
Read MoreThe American College of Radiology (ACR) has launched Assess-AI, the first AI quality registry to monitor and analyze the real-world performance of imaging AI algorithms, providing radiology facilities with performance insights, national benchmarks, and tools to ensure safe, effective, and transparent AI integration in clinical practice.
Read MoreIn this exclusive interview, Avez Rizvi, MD, CEO of RADPAIR, shares insights into the future of AI in radiology and the role RADPAIR aims to play in creating an AI-driven, patient-focused healthcare environment.
Read More