Triple-negative breast cancer (TNBC) is the most aggressive breast cancer subtype and is associated with high recurrence rates, a high incidence of distant metastases and poor overall survival. The aim of this study was to investigate the role of PD-L1, EGFR and AR expression in TNBC promotion and progression. To that end, we analyzed the immunohistochemical expression of these genes in 125 TNBC patients and their relation to clinicopathological parameters and survival. An elevated expression of PD-L1 was significantly correlated with higher tumor and nuclear grade, while a low expression was correlated with loco-regional recurrence without any influence on survival. Contrary to this, the expression of AR showed a positive impact on the DFI and a negative association with tumor grade. Furthermore, PD-L1 and AR demonstrated simultaneous expression, and further co-expression analysis revealed that a positive expression of PD-L1/AR notably correlates with tumor and nuclear grade and has a significant impact on a longer DFI and OS, while a negative PD-L1/AR expression is significantly associated with metastases. Therefore, our results suggest that positive PD-L1/AR expression is beneficial for TNBC patients. In addition, an elevated expression of EGFR contributes to metastases and a worse DFI and OS. In conclusion, we think that low PD-L1/low AR/high EGFR expression followed by high Ki67 expression constitutes a ‘high risk’ profile of TNBC.

Papillary thyroid carcinoma (PTC) is generally considered an indolent cancer. However, patients with cervical lymph node metastasis (LNM) have a higher risk of local recurrence. This study evaluated and compared four machine learning (ML)-based classifiers to predict the presence of cervical LNM in clinically node-negative (cN0) T1 and T2 PTC patients. The algorithm was developed using clinicopathological data from 288 patients who underwent total thyroidectomy and prophylactic central neck dissection, with sentinel lymph node biopsy performed to identify lateral LNM. The final ML classifier was selected based on the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the models evaluated, the k-Nearest Neighbor (k-NN) classifier was found to be the best fit, with an area under the receiver operating characteristic curve of 0.72, and sensitivity, specificity, positive and negative predictive values, F1 and F2 scores of 98%, 27%, 56%, 93%, 72%, and 85%, respectively. A web application based on a sensitivity-optimized kNN classifier was also created to predict the potential of cervical LNM, allowing users to explore and potentially build upon the model. These findings suggest that ML can improve the prediction of LNM in cN0 T1 and T2 PTC patients, thereby aiding in individual treatment planning.

The presence of ectopic breast tissue in axillary lymph nodes (ALN) is a benign condition that must be differentiated from primary or metastatic carcinoma. Here we report a patient who underwent excision of enlarged ALN 10 years after she had received surgical treatment of ipsilateral breast for an intracystic intraductal papilloma (IDP). Histological examination of the removed ALN revealed that the proliferative lesion consisted of papillary and tubular structures lined by luminal cuboidal cells and a distinct outer layer of myoepithelial cells resembling IDP of the breast. Immunostaining with a set of immunohistochemical markers including AE/AE3, alpha-smooth muscle actin and p63 in combination with estrogen and progesterone receptors confirmed the diagnosis of ectopic IDP. This case shows that even though benign proliferative change in ectopic breast tissue is an extremely rare phenomenon, this possibility should be taken into account for correct diagnosis.