Does ultrasound evaluation of the axilla increase the rate of axillary lymph node dissection in early stage clinically node negative breast cancer patients?

Machine Learning Model for Predicting Axillary Lymph Node Metastasis in Clinically Node Positive Breast Cancer Based on Peritumoral Ultrasound Radiomics and SHAP Feature Analysis

OBJECTIVE

This study seeks to construct a machine learning model that merges clinical characteristics with ultrasound radiomic analysis-encompassing both the intratumoral and peritumoral-to predict the status of axillary lymph nodes in patients with early-stage breast cancer.

METHODS

The study employed retrospective methods, collecting clinical information, ultrasound data, and postoperative pathological results from 321 breast cancer patients (including 224 in the training group and 97 in the validation group). Through correlation analysis, univariate analysis, and Lasso regression analysis, independent risk factors related to axillary lymph node metastasis in breast cancer were identified from conventional ultrasound and immunohistochemical indicators, and a clinical feature model was constructed. Additionally, features were extracted from ultrasound images of the intratumoral and its 1-5 mm peritumoral to establish a radiomics feature formula. Furthermore, by combining clinical features and ultrasound radiomics features, six machine learning models (Logistic Regression, Decision Tree, Support Vector Machine, Extreme Gradient Boosting, Random Forest, and K-Nearest Neighbors) were compared for diagnostic efficacy, and constructing a joint prediction model based on the optimal ML algorithm. The use of Shapley Additive Explanations (SHAP) enhanced the visualization and interpretability of the model during the diagnostic process.

RESULTS

Among the 321 breast cancer patients, 121 had axillary lymph node metastasis, and 200 did not. The clinical feature model had an AUC of 0.779 and 0.777 in the training and validation groups, respectively. Radiomics model analysis showed that the model including the Intratumor +3 mm peritumor area had the best diagnostic performance, with AUCs of 0.847 and 0.844 in the training and validation groups, respectively. The joint prediction model based on the XGBoost algorithm reached AUCs of 0.917 and 0.905 in the training and validation groups, respectively. SHAP analysis indicated that the Rad Score had the highest weight in the prediction model, playing a significant role in predicting axillary lymph node metastasis in breast cancer.

CONCLUSION

The predictive model, which integrates clinical features and radiomic characteristics using the XGBoost algorithm, demonstrates significant diagnostic value for axillary lymph node metastasis in breast cancer. This model can provide significant references for preoperative surgical strategy selection and prognosis evaluation for breast cancer patients, helping to reduce postoperative complications and improve long-term survival rates. Additionally, the utilization of SHAP enhancing the global and local interpretability of the model.

Axillary ultrasonography for early-stage invasive breast cancer

BACKGROUND

Among women with early invasive breast cancer and 1-2 positive sentinel nodes, sentinel lymph node biopsy (SLNB) is non-inferior to axillary lymph node dissection (ALND).1-3 However, preoperative axillary ultrasonography (AxUS) may not be sensitive enough to discriminate burden of nodal metastasis in these patients, potentially leading to overtreatment.4-6 This study compares axillary operation rates in patients who did and did not receive preoperative AxUS, assessing its utility and risks for overtreatment.

METHODS

This is a retrospective cohort study of patients with clinical T1/T2 breast tumors who were clinically node negative and underwent an axillary operation.

RESULTS

Patients who had preoperative AxUS received more ALND compared to patients who did not (5.6% vs. 1.4%, p ​< ​0.001). There was no significant difference in the number of additional axillary operations following SLNB (2.1% vs. 2.3%, p ​= ​0.77).

CONCLUSION

Eliminating preoperative AxUS is associated with fewer invasive ALND procedures, without increased rate of axillary reoperations.

Assessing Whether Morphological Changes in Axillary Lymph Node Have Already Occurred Prior to Metastasis in Breast Cancer Patients by Ultrasound

Background and Objectives: Whether the morphological changes in axillary lymph node (ALN) have occurred prior to metastasis remains unclear in breast cancer (BC) patients. The aim of this study is to investigate the influence of BC for the morphology of non-metastasis ALN (N−) and, further, to improve the performance of ultrasound (US) examination for metastasis ALN (N+). Materials and Methods: In this retrospective study, 653 patients with breast mass were enrolled and divided into normal group of 202 patients with benign breast tumor, N− group of 233 BC patients with negative ALN and N+ group of 218 BC patients with positive ALN. US features of ALN were evaluated and analyzed according to long (L) and short (S) diameter, the (L/S) axis ratio, cortical thickness, lymph node edge, replaced hilum and color Doppler flow imaging (CDFI). Results: ALN US features of short diameter, replaced hilum, cortical thickness and CDFI have significant statistical differences in N− group comparing with normal group and N+ group, respectively (p < 0.05). Conclusions: Therefore, BC can affect ALN and lead to US morphological changes whether lymph node metastasis is present, which reduces the sensitivity of axillary US. The combination of US and other examination methods should be applied to improve the diagnostic performance of N+.

Node Positivity Among Sonographically Suspicious but FNA-Negative Axillary Nodes

BACKGROUND

Fine needle aspiration (FNA) of sonographically suspicious axillary lymph nodes is helpful to clinically stage patients and guide consideration of neoadjuvant therapy in breast cancer. However, data are limited for suspicious nodes that are FNA negative. Our goal is to compare the frequency of node positivity between patients with negative axillary ultrasound (AUSneg) versus suspicious AUS with negative FNA (FNAneg).

METHODS

With IRB approval, we identified all clinically node-negative (cN0) patients with invasive breast cancer treated with upfront surgery at our tertiary care center between 2016 and 2021. AUS is routinely performed with FNA of suspicious lymph node(s). We compared clinicopathologic characteristics and nodal positivity rates between AUSneg and FNAneg groups.

RESULTS

A total of 1580 cN0 patients with invasive breast cancer were analyzed, including 1240 AUSneg and 340 FNAneg patients. The FNAneg group was younger (median age 59.7 years versus 63.5 years, p < 0.001) and had higher clinical T (cT) category (29.1% versus 21.7% with cT2-cT4 disease, p = 0.005). Final axillary pathologic node positivity did not differ significantly between the AUSneg and FNAneg groups (16.5% versus 19.1%, p = 0.25). Among FNAneg patients, 58/340 (17.1%) had a clip placed, with retrieval confirmed in 28/58 (48.3%). Of the 28 retrieved clipped nodes, 27 were sentinel nodes. Final pathologic nodal status (pN+%) did not differ between patients in whom retrieval of the clipped node was confirmed versus not confirmed (28.6% versus 16.7%, p = 0.28).

CONCLUSIONS

Both patients with sonographically suspicious node(s) and negative FNA and patients with negative AUS have a similarly low chance of positive nodes. Additionally, routine targeted excision of FNA-negative clipped nodes is not warranted.