AI-Assisted Ultrasound Nomogram Predicts Axillary Lymph Node Metastasis in Breast Cancer

An AI-assisted ultrasound nomogram predicted axillary lymph node metastasis in breast cancer with AUC 0.81, sensitivity 77%, specificity 82% (internal validation), outperforming radiologist assessment. Retrospective, single-center, not externally validated.

• Retrospective study of 148 women (training n=118, validation n=30) with invasive breast cancer; AI features extracted via S-Detect (Samsung Medison).
• Nomogram combined AI features with tumor/IARN size, Ki-67 >20%, and radiologist assessment; AUC 0.855 (training), 0.810 (validation). No 95% CIs reported.
• Key limitation: small single-center internal validation only, retrospective design, commercial AI software, limiting generalizability.

RadPigeon summaries are original and for information only. They are not clinical advice.