A UCLA-led review analyzes current evidence for AI tools in screening mammography, focusing on their capability to detect interval cancers.
Key Details
- 1UCLA researchers conducted a review of commercially available AI for mammography screening.
- 2The review highlights a need for prospective, real-world data on AI effectiveness and safety.
- 3Interval cancers—cancers developing shortly after a negative screen—are a key focus for AI improvement.
- 4AI retrospectively identified 5% to 78% of technically visible but previously missed cancers, indicating variable sensitivity.
- 5The article calls for more robust data to clarify how these tools should be used in clinical practice.
Why It Matters
Robust, prospective data is crucial before widespread adoption of AI for breast cancer screening. Understanding AI's true sensitivity and potential to reduce missed cancers will directly impact clinical standards in radiology.
Source
Radiology Business
Related News
•Radiology Business
New AI Flags Uncertainty in Breast Cancer Imaging Predictions
University of Pittsburgh researchers developed an AI model that quantifies uncertainty in breast cancer diagnostic predictions to enhance trustworthiness.
•AuntMinnie
LLMs Rarely Recommend Unnecessary Imaging, Except for Thyroid Ultrasound
Large language models seldom over-recommend imaging, but thyroid ultrasound guidance shows substantial discrepancies.
•Radiology Business
UC Irvine Implements AI to Find Lung Cancer Screening Candidates
UC Irvine's radiology department developed an NLP tool to identify patients eligible for lung cancer screening from EHR notes.