Experience-Guided Self-Adaptive Cascaded Agents for Breast Cancer Screening and Diagnosis with Reduced Biopsy Referrals

Researchers developed BUSD-Agent, an AI framework for breast cancer screening that uses cascaded agents and experience-guided decision-making to reduce unnecessary biopsies. The system achieved a 22% reduction in biopsy referrals while improving diagnostic accuracy through retrieval-based learning from past cases.

• →BUSD-Agent framework reduced diagnostic escalation from 84.95% to 58.72% and biopsy referrals from 59.50% to 37.08%.
• →The system uses a two-stage approach with screening and diagnostic agents that make selective decisions based on risk assessment.
• →Experience-guided learning stores past pathology outcomes to inform future decisions without parameter updates.
• →Average screening specificity improved by 68.48% and diagnostic specificity by 6.33% across 10 breast ultrasound datasets.
• →The framework demonstrates practical AI application in healthcare with measurable patient outcome improvements.