Correlation between mammograghic findings and clinical/ pathologic features in women with small invasive breast carcinomas

A machine learning model based on ultrasound image features to assess the risk of sentinel lymph node metastasis in breast cancer patients: Applications of scikit-learn and SHAP

Background

This study aimed to determine an optimal machine learning (ML) model for evaluating the preoperative diagnostic value of ultrasound signs of breast cancer lesions for sentinel lymph node (SLN) status.

Method

This study retrospectively analyzed the ultrasound images and postoperative pathological findings of lesions in 952 breast cancer patients. Firstly, the univariate analysis of the relationship between the ultrasonographic features of breast cancer morphological features and SLN metastasis. Then, based on the ultrasound signs of breast cancer lesions, we screened ten ML models: support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), linear discriminant analysis (LDA), logistic regression (LR), naive bayesian model (NB), k-nearest neighbors (KNN), multilayer perceptron (MLP), long short-term memory (LSTM), and convolutional neural network (CNN). The diagnostic performance of the model was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC), Kappa value, accuracy, F1-score, sensitivity, and specificity. Then we constructed a clinical prediction model which was based on the ML algorithm with the best diagnostic performance. Finally, we used SHapley Additive exPlanation (SHAP) to visualize and analyze the diagnostic process of the ML model.

Results

Of 952 patients with breast cancer, 394 (41.4%) had SLN metastasis, and 558 (58.6%) had no metastasis. Univariate analysis found that the shape, orientation, margin, posterior features, calculations, architectural distortion, duct changes and suspicious lymph node of breast cancer lesions in ultrasound signs were associated with SLN metastasis. Among the 10 ML algorithms, XGBoost had the best comprehensive diagnostic performance for SLN metastasis, with Average-AUC of 0.952, Average-Kappa of 0.763, and Average-Accuracy of 0.891. The AUC of the XGBoost model in the validation cohort was 0.916, the accuracy was 0.846, the sensitivity was 0.870, the specificity was 0.862, and the F1-score was 0.826. The diagnostic performance of the XGBoost model was significantly higher than that of experienced radiologists in some cases (P<0.001). Using SHAP to visualize the interpretation of the ML model screen, it was found that the ultrasonic detection of suspicious lymph nodes, microcalcifications in the primary tumor, burrs on the edge of the primary tumor, and distortion of the tissue structure around the lesion contributed greatly to the diagnostic performance of the XGBoost model.

Conclusions

The XGBoost model based on the ultrasound signs of the primary breast tumor and its surrounding tissues and lymph nodes has a high diagnostic performance for predicting SLN metastasis. Visual explanation using SHAP made it an effective tool for guiding clinical courses preoperatively.

Sonographic Features of Pure Mucinous Brelast Carcinoma With Micropapillary Pattern

Objective

Previous studies have mostly discussed the clinical manifestations and prognosis of mucinous breast carcinoma with a micropapillary pattern. The purposes of this study were to investigate the sonographic features of pure mucinous breast carcinoma with micropapillary pattern (MUMPC) and to identify the role of ultrasound in the differential diagnosis between MUMPC and conventional pure mucinous breast carcinoma (cPMBC).

Materials and Methods

We obtained written informed consent from all patients, and the Ethics Committee of West China Hospital approved this retrospective study. The study was conducted between May and August 2020. We enrolled 133 patients with 133 breast lesions confirmed as mucinous breast carcinoma (MBC) histopathologically between January 2014 and January 2020.We retrospectively assessed sonographic features (margin, shape, internal echogenicity, calcification, posterior acoustic feature, invasive growth, blood flow grade, and rate of missed diagnosis) and clinical characteristics (age, tumor size, tumor texture, initial symptom, and lymph node metastasis). Bivariable analyses were performed using SPSS version 19.0.

Results

The 133 lesions included 11 MUMPCs, 65 cPMBCs, and 57 mixed MBCs (MMBCs). There were significant differences in margin, shape, calcification, posterior acoustic feature, invasive growth, rate of missed diagnosis, average tumor size, and lymph node metastasis among the three groups (p < 0.05). The subsequent pairwise comparisons showed that there were significant differences in lymph node metastasis, margin, and invasive growth between MUMPC and cPMBC (p < 0.05). In patients aged >45 years, there was a significant difference in tumor size among the three groups (p = 0.045), and paired comparison showed that the average tumor size in the cPMBC group was larger than that in the MMBC group (p = 0.014).

Conclusion

MUMPC showed a non-circumscribed margin and invasive growth more frequently than cPMBC did. Lymphatic metastasis was more likely to occur in MUMPC than cPMBC. Ultrasound is helpful to distinguish MUMPC from cPMBC.

Imaging Predictors for Nonsentinel Lymph Node Metastases in Breast Cancer Patients

Background

The relationship between imaging features and nonsentinel lymph node (NSLN) metastasis is not clear.

Objectives

To determine whether imaging features could predict NSLN metastasis in sentinel lymph node (SLN)-positive breast cancer patients and to provide new clues for avoiding unnecessary axillary lymph node dissection.

Method

171 patients with clinically negative axillary lymph nodes and a pathologically positive SLN were recruited between January 2007 and January 2014. According to the Breast Imaging Reporting and Data System (BI-RADS), the effects of clinicopathological factors, especially imaging features, on NSLN metastases were assessed by univariate and multivariate statistical analyses.

Results

The average number of dissected SLNs was 2.11 (range, 1-6); 56 of the 171 (32.75%) patients exhibited NSLN metastases. In univariate analysis, tumor size, number of positive SLNs, ratio of positive SLNs, mammographic mass margins, ultrasonographic mass margins, and ultrasonographic vascularity were significantly correlated with NSLN involvement. Furthermore, through multivariate analysis, tumor size, number of positive SLNs, mammographic mass margins, and ultrasonographic vascularity were still independent predictors of NSLN involvement. Additionally, in SLN-positive patients, number of positive SLNs and ultrasonographic vascularity could also predict the tumor burden in NSLN.

Conclusions

In addition to tumor size and the number of positive SLNs, mammographic mass margins and ultrasonographic vascularity were also independent predictors of NSLN metastases in SLN-positive patients of breast cancer. The number of positive SLNs and ultrasonographic vascularity could also predict the tumor burden in NSLN.

BI-RADS 3-5 microcalcifications: prediction of lymph node metastasis of breast cancer

Purpose

To determine whether the clinicopathological parameters and Breast Imaging Reporting and Data System (BI-RADS) 3–5 microcalcifications differed between lymph node positive (LN (+)) and lymph node negative (LN (−)) invasive ductal carcinoma (IDC).

Results

For microcalcification-associated breast cancers, seven selected features (age, tumor size, Ki-67 status, lymphovascular invasion, calcification range, calcification diameter and calcification density) were significantly associated with LN status (all P < 0.05). Multivariate logistic regression analysis found that three risk factors (age: older vs. younger OR: 0.973 P = 0.006, tumor size: larger vs. smaller OR: 1.671, P < 0.001 and calcification density: calcifications > 20/cm² vs. calcifications ≤ 20/cm² OR: 1.698, P < 0.001) were significant independent predictors. This model had an area under the receiver operating characteristic curve (AUC) of 0.701. The nodal staging (N0 and N1 χ² = 5.701, P = 0.017; N0 and N2 χ² = 6.614, P = 0.013) was significantly positively associated with calcification density. The luminal B subtype had the highest risk of LN metastasis. Multivariate analysis demonstrated that calcification > 2 cm in range (OR: 2.209) and larger tumor size (OR: 1.882) were independently predictive of LN metastasis in the luminal B subtype (AUC = 0.667).

Materials and Methods

Mammographic images of 419 female breast cancer patients were included. Associations between the risk factors and LN status were evaluated using a Chi-square test, ANOVA and binary logistic regression analysis.

Conclusions

This study found that age, tumor size and calcifications density can be conveniently used to facilitate the preoperative prediction of LN metastasis. The luminal B subtype has the highest risk of LN metastasis among the microcalcification-associated breast cancers.