ChatGPT-4 Vision Struggles with Radiologic Image Interpretation
ChatGPT-4 Vision shows strong performance on text-based radiology questions but struggles with image interpretation, highlighting limitations in its current application to radiology.
Category: Machine Learning & AI
Machine Learning & AI
Latest
Machine Learning & AI
Latest
AI in Imaging: Kids and Teens See Promise, Stress Need for Supervision
Children and young people are generally positive about AI in healthcare, especially in radiology, but emphasize the need for human supervision, according to a U.K.-based survey.
Machine Learning & AI
Latest
How Race and Age Impact AI Mammogram Results
A study of nearly 5,000 screening mammograms published in Radiology revealed that an FDA-approved AI algorithm's false positive results are influenced by patient race and age, highlighting the need for diverse training data and demographic considerations in AI software for mammography.
AI Boosts Breast Cancer Screening Accuracy
Combining AI with radiologists’ assessments may enhance breast cancer screening with an algorithm tailored to identify normal mammograms accurately, potentially reducing false positives and unnecessary follow-ups while maintaining cancer detection rates.
Read More
Researchers Develop Deep Learning Model to Predict Breast Cancer
Researchers have developed AsymMirai, an interpretable AI model using mammograms to predict breast cancer risk one to five years in advance by comparing differences in left and right breast tissue, showing similar performance to the complex Mirai model and suggesting bilateral dissimilarity as a potential marker for breast cancer risk.
Read More
How AI Tools Impact Radiologists Differently
Recent research suggests that while medical AI tools have the potential to enhance the interpretation of images like X-rays and CT scans for more accurate diagnoses, their effectiveness may differ among clinicians.
Read More
Researchers Look at Environmental Impacts of AI Tools
As artificial intelligence (AI) is increasingly used in radiology, researchers caution that it’s essential to consider the environmental impact of AI tools.
Read More
AI Tool Forecasts Psychosis from MRI Scans
A machine-learning tool accurately predicts psychosis onset by analyzing MRI scans, showing 85% accuracy in training and 73% accuracy in new data, potentially aiding early intervention in clinical settings, according to research led by the University of Tokyo and an international consortium.
Read More