Ghost in the Axilla: Luminal-Type Breast Cancer and Occult Sentinel Node Metastasis After Neoadjuvant Chemotherapy

<b>Background</b>: Sentinel lymph node biopsy (SLNB) is the standard axillary staging procedure in clinically node-negative breast cancer but remains invasive, non-therapeutic and increasingly questioned in contemporary de-escalation algorithms. After neoadjuvant chemotherapy (NACT), however, the safety of omitting SLNB solely on the basis of a negative axillary ultrasound (AUS) is uncertain, particularly across molecular subtypes with heterogeneous chemosensitivity. This study evaluated the diagnostic performance of preoperative AUS after NACT and explored clinicopathological and biological factors associated with SLNB positivity in ultrasound-negative axillae. <b>Methods</b>: In this single-centre retrospective cohort, 135 women with invasive breast cancer who received NACT followed by surgery (2022-2024) were analysed. To avoid spectrum bias, 77 patients with clipped, cytologically or histologically proven node-positive disease at baseline were excluded from the main analysis. All patients underwent preoperative AUS and definitive axillary staging. Ninety-six women with ultrasound-negative axillae who proceeded to SLNB constituted the primary study population. Oestrogen receptor (ER), progesterone receptor (PR), HER2, Ki-67 and immunohistochemistry-based molecular subtype were recorded. Receiver operating characteristic (ROC) analysis and uni/multivariable logistic regression were used as exploratory tools to identify factors associated with SLNB positivity. <b>Results</b>: In the overall cohort, AUS sensitivity, specificity, negative predictive value and false-negative rate for axillary metastasis were 47.8%, 90.9%, 62.5% and 52.2%, respectively. Among ultrasound-negative axillae, SLNB was positive in 37.5%. Compared with SLNB-negative patients, those with SLNB metastases more frequently harboured an intratumoural ductal carcinoma in situ (DCIS) component, showed higher ER/PR expression and lower Ki-67, and were predominantly luminal A or luminal B/HER2-, whereas AUS performance appeared more favourable in HER2-enriched and triple-negative tumours. ROC-derived cut-offs for ER (82.5%), PR (25.0%) and Ki-67 (17.5%) provided only moderate discrimination (area under the curve 0.68-0.70). In multivariable analysis, absence of a DCIS component and low PR expression were independently associated with reduced odds of SLNB positivity, suggesting that DCIS and high PR may act as indicators of residual nodal risk in ultrasound-negative axillae. All estimates are limited by sample size and wide confidence intervals and should be interpreted as hypothesis-generating. <b>Conclusions</b>: Preoperative AUS alone cannot reliably exclude sentinel lymph node metastasis after NACT, particularly in luminal A and luminal B/HER2- tumours with strong hormone receptor expression and a low proliferative index. Until prospective, biology-stratified trials confirm the safety of omission, SLNB should not be withheld solely on the basis of a negative AUS in these subtypes. Axillary management after NACT should systematically integrate both imaging findings and tumour biology when considering further de-escalation of surgery.