A commercial AI system can identify up to 33% of interval breast cancers missed by radiologists on digital breast tomosynthesis exams.
Key Details
- 1Study published in Radiology tested AI on digital breast tomosynthesis (DBT) exams preceding confirmed interval cancer diagnoses.
- 2The AI algorithm (Lunit INSIGHT DBT v1.1) flagged up to one-third of interval cancers missed by radiologists.
- 3Interval breast cancers are often more aggressive and have worse prognoses than screen-detected cancers.
- 4Nearly 12 years of retrospective DBT data (Feb 2011–Jun 2023) were analyzed.
- 5Algorithm scored lesions; those over 10 marked as positive, and radiologist review correlated AI findings with actual cancer sites.
Why It Matters
Interval cancers are frequently aggressive and linked with higher morbidity and mortality due to later detection. AI's ability to identify a significant portion of these previously missed cancers suggests potential for earlier intervention and improved patient outcomes in breast imaging.
Source
Health Imaging
Related News
•Radiology Business
Experts Urge Development of Generalist Radiology AI to Cut Costs and Improve Care
Leading scientists advocate for broader, generalist radiology AI models to overcome limitations of narrow, single-task solutions.
•AuntMinnie
General LLMs Show Promise in Detecting Critical Findings in Radiology Reports
Stanford and Mayo Clinic Arizona researchers demonstrated that LLMs like GPT-4 can categorize critical findings in radiology reports using few-shot prompting.
•AuntMinnie
Experts Outline Framework and Benefits for Generalist Radiology AI
Researchers propose key features and benefits for implementing generalist radiology AI (GRAI) frameworks over narrow AI tools.