Can We Skip Intraoperative Evaluation of Sentinel Lymph Nodes? Nomogram Predicting Involvement of Three or More Axillary Lymph Nodes before Breast Cancer Surgery

Individualized prediction of non-sentinel lymph node metastasis in Chinese breast cancer patients with ≥ 3 positive sentinel lymph nodes based on machine-learning algorithms

BACKGROUND

Axillary lymph node dissection (ALND) is a standard procedure for early-stage breast cancer (BC) patients with three or more positive sentinel lymph nodes (SLNs). However, ALND can lead to significant postoperative complications without always providing additional clinical benefits. This study aims to develop machine-learning (ML) models to predict non-sentinel lymph node (non-SLN) metastasis in Chinese BC patients with three or more positive SLNs, potentially allowing the omission of ALND.

METHODS

Data from 2217 BC patients who underwent SLN biopsy at Shantou University Medical College were analyzed, with 634 having positive SLNs. Patients were categorized into those with ≤ 2 positive SLNs and those with ≥ 3 positive SLNs. We applied nine ML algorithms to predict non-SLN metastasis. Model performance was evaluated using ROC curves, precision-recall curves, and calibration curves. Decision Curve Analysis (DCA) assessed the clinical utility of the models.

RESULTS

The RF model showed superior predictive performance, achieving an AUC of 0.987 in the training set and 0.828 in the validation set. Key predictive features included size of positive SLNs, tumor size, number of SLNs, and ER status. In external validation, the RF model achieved an AUC of 0.870, demonstrating robust predictive capabilities.

CONCLUSION

The developed RF model accurately predicts non-SLN metastasis in BC patients with ≥ 3 positive SLNs, suggesting that ALND might be avoided in selected patients by applying additional axillary radiotherapy. This approach could reduce the incidence of postoperative complications and improve patient quality of life. Further validation in prospective clinical trials is warranted.

Predicting three or more metastatic nodes using contrast-enhanced lymphatic US findings in early breast cancer

OBJECTIVES

To develop and validate a nomogram for predicting ≥ 3 metastatic axillary lymph nodes (ALNs) in early breast cancer with no palpable axillary adenopathy by clinicopathologic data, contrast-enhanced (CE) lymphatic ultrasound (US), and grayscale findings of sentinel lymph nodes (SLNs).

MATERIALS AND METHODS

Women with T1-2N0 invasive breast cancer were consecutively recruited for the CE lymphatic US. Patients from Center 1 were grouped into development and internal validation cohorts at a ratio of 2:1. The external validation cohort was constructed from Center 2. The clinicopathologic data and US findings of SLNs were analyzed. A nomogram was developed to predict women with ≥ 3 metastatic ALNs. Nomogram performance was assessed with the area under the receiver operating characteristic curve (AUC) and calibration curve analysis.

RESULTS

One hundred seventy-nine from Center 1 were considered the development cohorts. The remaining 90 participants from Center 1 were internal cohorts and 197 participants from Center 2 were external validation cohorts. The US findings of no enhancement (odds ratio (OR), 15.3; p = 0.01), diffuse (OR, 19.1; p = 0.01) or focal eccentric (OR, 27.7; p = 0.003) cortical thickening, and absent hilum (OR, 169.7; p < 0.001) were independently associated with ≥ 3 metastatic ALNs. Compared to grayscale US or CE lymphatic US alone, the nomogram showed the highest AUC of 0.88 (0.85, 0.91). The nomogram showed a calibration slope of 1.0 (p = 0.80-0.81; Brier = 0.066-0.067) in validation cohorts in predicting ≥ 3 metastatic ALNs.

CONCLUSION

Patients likely to have ≥ 3 metastatic ALNs were identified by combining the lymphatic and grayscale US findings of SLNs. Our nomogram could aid in multidisciplinary treatment decision-making.

TRIAL REGISTRATION

This trial is registered on www.chictr.org.cn : ChiCTR2000031231. Registered March 25, 2020.

CRITICAL RELEVANCE STATEMENT

A nomogram combining lymphatic CEUS and grayscale US findings of SLNs could identify early breast cancer patients with low or high axillary tumor burden preoperatively, which is more applicable to the Z0011 era. Our nomogram could be useful in aiding multidisciplinary treatment decision-making for patients with early breast cancer.

KEY POINTS

• CEUS can help identify and diagnose SLN in early breast cancer preoperatively. • Combining lymphatic and grayscale US findings can predict axillary tumor burden. • The nomogram showed a high diagnostic value in validation cohorts.

Nomogram based on multiparametric analysis of early-stage breast cancer: Prediction of high burden metastatic axillary lymph nodes

BACKGROUND

The Z0011 and AMAROS trials found that axillary lymph node dissection (ALND) was no longer mandatory for early-stage breast cancer patients who had one or two metastatic axillary lymph nodes (mALNs). The aim of our study was to establish a nomogram which could be used to quantitatively predict the individual likelihood of high burden mALN (≥3 mALN).

METHODS

We retrospectively analyzed 564 women with early breast cancer who had all undergone both ultrasound (US) and magnetic resonance imaging (MRI) to examine axillary lymph nodes before radical surgery. All the patients were divided into training (n = 452) and validation (n = 112) cohorts by computer-generated random numbers. Their clinicopathological features and preoperative imaging associated with high burden mALNs were evaluated by logistic regression analysis to develop a nomogram for predicting the probability of high burden mALNs.

RESULTS

Multivariate analysis showed that high burden mALNs were significantly associated with replaced hilum and the shortest diameter >10 mm on MRI, with cortex thickness >3 mm on US (p < 0.05 each). These imaging criteria plus higher grade (grades II and III) and quadrant of breast tumor were used to develop a nomogram calculating the probability of high burden mALNs. The AUC of the nomogram was 0.853 (95% CI: 0.790-0.908) for the training set and 0.783 (95% CI: 0.638-0.929) for the validation set. Both internal and external validation evaluated the accuracy of nomogram to be good.

CONCLUSION

A well-discriminated nomogram was developed to predict the high burden mALN in early-stage breast patients, which may assist the breast surgeon in choosing the appropriate surgical approach.

Predictive nomogram based on serum tumor markers and clinicopathological features for stratifying lymph node metastasis in breast cancer

BACKGROUND

This study was aimed to establish the nomogram to predict patients' axillary node status by using patients' clinicopathological and tumor characteristic factors.

METHODS

A total of 705 patients with breast cancer were enrolled in this study. All patients were randomly divided into a training group and a validation group. Univariate and multivariate ordered logistic regression were used to determine the predictive ability of each variable. A nomogram was performed based on the factors selected from logistic regression results. Receiver operating characteristic curve (ROC) analysis, calibration plots and decision curve analysis (DCA) were used to evaluate the discriminative ability and accuracy of the models.

RESULTS

Logistic regression analysis demonstrated that CEA, CA125, CA153, tumor size, vascular-invasion, calcification, and tumor grade were independent prognostic factors for positive ALNs. Integrating all the predictive factors, a nomogram was successfully developed and validated. The C-indexes of the nomogram for prediction of no ALN metastasis, positive ALN, and four and more ALN metastasis were 0.826, 0.706, and 0.855 in training group and 0.836, 0.731, and 0.897 in validation group. Furthermore, calibration plots and DCA demonstrated a satisfactory performance of our nomogram.

CONCLUSION

We successfully construct and validate the nomogram to predict patients' axillary node status by using patients' clinicopathological and tumor characteristic factors.

Is Routine Intraoperative Frozen Section Analysis of Sentinel Lymph Nodes Necessary in Every Early-Stage Breast Cancer?

Purpose

Clinical application of the ACOSOG Z0011 trial results allows clinically node-negative breast cancer patients who meet criteria to avoid axillary dissection even when 1–2 sentinel lymph nodes (SLNs) are positive for metastatic disease. Intraoperative frozen section (iFS) analyses of SLNs were thought to reduce re-operation rates despite variable reported sensitivity and possibility of a false negative result. This study evaluated the rate of re-operations prevented by SLN iFS in a tertiary care hospital in Bangkok, Thailand, over a 6-year time-frame.

Patients and Methods

From April 2016 to April 2022, 1284 sentinel lymph node biopsy (SLNB) procedures were performed. Of these, 214 cases were breast-conserving surgery in accordance with the ACOSOG criteria with concomitant usage of iFS. Clinicopathological features of these cases were collected and analyzed. Re-operation rates prevented by the additional intervention were reported.

Results

Only five additional operations were prevented with the usage of 214 iFS. The discordance rate between frozen and permanent sections in terms of presence of metastatic disease and number of total lymph nodes was around 15%. Tumor staging, node staging, Nottingham histologic grading and lymphovascular invasion are significant predictors of SLN metastasis.

Conclusion

iFS results in a very low prevention rate for follow-up ALND in patients with preoperative clinically negative axillary nodes and is associated with a non-negligible discordance rate with permanent sections. Our study suggests iFS may be avoided in most cases of early-stage clinically and radiographically node-negative breast cancer patients. Doing so may reduce surgical costs and total operative time without a significant impact on the overall quality of treatment and standard of care.

Accurate Evaluation of Feature Contributions for Sentinel Lymph Node Status Classification in Breast Cancer

The current guidelines recommend the sentinel lymph node biopsy to evaluate the lymph node involvement for breast cancer patients with clinically negative lymph nodes on clinical or radiological examination. Machine learning (ML) models have significantly improved the prediction of lymph nodes status based on clinical features, thus avoiding expensive, time-consuming and invasive procedures. However, the classification of sentinel lymph node status represents a typical example of an unbalanced classification problem. In this work, we developed a ML framework to explore the effects of unbalanced populations on the performance and stability of feature ranking for sentinel lymph node status classification in breast cancer. Our results indicate state-of-the-art AUC (Area under the Receiver Operating Characteristic curve) values on a hold-out set (67%) while providing particularly stable features related to tumor size, histological subtype and estrogen receptor expression, which should therefore be considered as potential biomarkers.

A nomogram for predicting three or more axillary lymph node involvement before breast cancer surgery

Based on the American College of Surgeons Oncology Group (ACOSOG)-Z0011, a useful nomogram has been constructed to identify patients who do not require intraoperative frozen sections to evaluate sentinel lymph nodes in the previous study. This study investigated the developed nomogram by ultrasonography (US) and positron emission tomography (PET)/computed tomography (CT) as a modality. In the training set, 89/1030 (8.6%) patients had three or more positive nodes. Larger tumor size, higher grade ultrasonographic ALN classification, and findings suspicious of positive ALN on PET/CT were associated in multivariate analysis. The areas under the receiver operating characteristic curve (AUC) of the nomogram were 0.856 [95% CI 0.815-0.897] in the training set. The AUC in the validation set was 0.866 [95% CI 0.799-0.934]. Application of the nomogram to 1067 patients who met the inclusion criteria of ACOSOG-Z0011 showed that 90 (8.4%) patients had scores above the cut-off and a false-negative result was 37 (3.8%) patients. And the specificity was 93.8%, and the negative predictive value was 96.4%. The upgraded nomogram improved the predictive accuracy, using only US and PET/CT. This nomogram is useful for identifying patients who do not require intraoperative analysis of sentinel lymph nodes and considering candidates for identifying neoadjuvant chemotherapy. The patients consisted of clinical T1-2 and node-negative invasive breast cancer. The training and validation set consisted of 1030 and 781 patients, respectively. A nomogram was constructed by analyzing factors related to three or more axillary lymph node metastases. The patients who matched the ACOSOG-Z0011 criteria were selected and applied to the new nomogram.

Gail model and fifth edition of ultrasound BI-RADS help predict axillary lymph node metastasis in breast cancer-A multicenter prospective study

RATIONALE AND OBJECTIVES

We aim to assess the performance of the Gail model and the fifth edition of ultrasound BI-RADS (Breast Imaging Reporting and Data System) in breast cancer for predicting axillary lymph node metastasis (ALNM).

MATERIALS AND METHODS

We prospectively studied 958 female patients with breast cancer between 2018 and 2019 from 35 hospitals in China. Based on B-mode, color Doppler, and elastography, radiologists classified the degree of suspicion based on the fifth edition of BI-RADS. Individual breast cancer risk was assessed with the Gail model. The association between the US BI-RADS category and the Gail model in terms of ALNM was analyzed.

RESULTS

We found that US BI-RADS category was significantly and independently associated with ALNM (P < 0.001). The sensitivity, specificity, and accuracy of BI-RADS category 5 for predicting ALNM were 63.6%, 71.6%, and 68.6%, respectively. Combining the Gail model with the BI-RADS category showed a significantly higher sensitivity than using the BI-RADS category alone (67.8% vs. 63.6%, P < 0.001). The diagnostic accuracy of the BI-RADS category combined with the Gail model was better than that of the Gail model alone (area under the curve: 0.71 vs. 0.50, P < 0.001).

CONCLUSION

Based on the conventional ultrasound and elastography, the fifth edition of ultrasound BI-RADS category could be used to predict the ALNM of breast cancer. ALNM was likely to occur in patients with BI-RADS category 5. The Gail model could improve the diagnostic sensitivity of the US BI-RADS category for predicting ALNM in breast cancer.

ACR Appropriateness Criteria® Imaging of the Axilla

This publication reviews the current evidence supporting the imaging approach of the axilla in various scenarios with broad differential diagnosis ranging from inflammatory to malignant etiologies. Controversies on the management of axillary adenopathy results in disagreement on the appropriate axillary imaging tests. Ultrasound is often the appropriate initial imaging test in several clinical scenarios. Clinical information (such as age, physical examinations, risk factors) and concurrent complete breast evaluation with mammogram, tomosynthesis, or MRI impact the type of initial imaging test for the axilla. Several impactful clinical trials demonstrated that selected patient's population can received sentinel lymph node biopsy instead of axillary lymph node dissection with similar overall survival, and axillary lymph node dissection is a safe alternative as the nodal staging procedure for clinically node negative patients or even for some node positive patients with limited nodal tumor burden. This approach is not universally accepted, which adversely affect the type of imaging tests considered appropriate for axilla. This document is focused on the initial imaging of the axilla in various scenarios, with the understanding that concurrent or subsequent additional tests may also be performed for the breast. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Stratification of axillary lymph node metastasis risk with breast magnetic resonance imaging in breast cancer

Aims: To develop a model based on breast MRI to stratify axillary lymph node metastasis (ALNM) in breast cancer. Patients & methods: A total of 134 eligible patients were used to build a predicting model, which was validated with an independent group of 57 patients and evaluated for accuracy and sensitivity. Results: A model based on breast MRI was developed and yielded total accuracy of 82.5% and sensitivities of 94.3, 64.3 and 62.5% to predict patients with no, low and heavy ALNM burden, respectively, in the validation group. Conclusion: A noninvasive model based on breast MRI was developed to preoperatively stratify ALNM in breast cancer; its performance needs to be validated and improved in future research.

Avoiding unnecessary intraoperative sentinel lymph node frozen section biopsy of patients with early breast cancer

Purpose

After the publication of the ACOSOG (American College of Surgeons Oncology Group) Z0011 trial, the rate of axillary lymph node dissection has reduced. Thus, the need for intraoperative frozen section biopsy of sentinel lymph nodes (SLNs) has become controversial. We identified patients for whom intraoperative SLN frozen section biopsy could be omitted and found that frozen section biopsy rate can be reduced.

Methods

We reviewed the records of patients with tumors ≤5 cm in diameter who underwent breast-conserving surgery between January 2013 and December 2019 at Seoul St. Mary’s Hospital. Clinicopathological and imaging characteristics were compared according to number of positive SLNs (0–2 SLNs positive vs. ≥3 SLNs positive).

Results

A total of 1,983 patients were included in this study. Thirty-two patients (1.6%) had at least 3 positive SLNs. Patients with ≥3 positive SLNs had significantly larger tumors and were more frequently high-grade tumors (P < 0.001 and P = 0.002, respectively). Identification of suspicious lymph nodes on imaging studies was also associated with the presence of ≥3 positive SLNs (hazard ratio, 11.54; 95% confidence interval, 4.42–30.10). All patients with none or only 1 suspicious lymph node on any imaging modality (n = 647, 32.6%) had 0–2 positive SLNs. Also, among patients with clinical T1-stage tumors and at least 2 suspicious lymph nodes on only 1 imaging modality (n = 514, 25.9%), only 2 cases had ≥3 positive SLNs.

Conclusion

We found that intraoperative SLN frozen biopsy could be omitted in patients using tumor size and axillary lymph node status on imaging modality.

The new perspective of PET/CT for axillary nodal staging in early breast cancer patients according to ACOSOG Z0011 trial PET/CT axillary staging according to Z0011

OBJECTIVE

Post Z0011 trial, axillary lymph node dissections (ALNDs) can be performed in patients with ≥3 positive axillary lymph nodes (ALNs). We investigated the diagnostic performance of 18F-fluorodeoxyglucose PET/computed tomography (FDG PET/CT) to predict ≥3 metastasis [high nodal burden (HNB)].

METHODS

We retrospectively analyzed preoperative FDG PET/CT from January 2010 to June 2012. Patients had clinical T1-2N0 primary invasive breast cancer and underwent breast-conserving surgery with sentinel lymph node biopsy ± ALND. All suspicious ALNs were counted considering FDG-avidity with morphologic changes. Images were considered positive if the axillary basin took up more FDG than the surrounding tissue. On CT, abnormal ALNs were round/ovoid or had cortical thickening with contrast enhancement. PET/CT results were compared with the histology and follow-up findings.

RESULTS

In total, 221 females with 224 axillae were enrolled; 161 had negative, 53 had 1-2 metastasis [low nodal burden (LNB)] and 10 had HNB. The sensitivity, specificity, negative predictive value and positive predictive value of PET/CT for HNB were 70, 100, 98.6 and 100%, respectively. There was a correlation between the number of suspicious ALNs on PET/CT and the metastatic nodes on final histology. There were no significant differences in age, tumor size and FDG-avidity between patients with negative or LNB and HNB. During follow-up, 25 patients had a recurrence. The three false-negative patients did not show recurrence.

CONCLUSION

Preoperative PET/CT predicts HNB with high accuracy and is useful for evaluating clinical T1-2N0 invasive breast cancer.

Sentinel Lymph Node Metastasis on Clinically Negative Patients: Preliminary Results of a Machine Learning Model Based on Histopathological Features

The reported incidence of node metastasis at sentinel lymph node biopsy is generally low, so that the majority of women underwent unnecessary invasive axilla surgery. Although the sentinel lymph node biopsy is time consuming and expensive, it is still the intra-operative exam with the highest performance, but sometimes surgery is achieved without a clear diagnosis and also with possible serious complications. In this work, we developed a machine learning model to predict the sentinel lymph nodes positivity in clinically negative patients. Breast cancer clinical and immunohistochemical features of 907 patients characterized by a clinically negative lymph node status were collected. We trained different machine learning algorithms on the retrospective collected data and selected an optimal subset of features through a sequential forward procedure. We found comparable performances for different classification algorithms: on a hold-out training set, the logistics regression classifier with seven features, i.e., tumor diameter, age, histologic type, grading, multiplicity, in situ component and Her2-neu status reached an AUC value of 71.5% and showed a better trade-off between sensitivity and specificity (69.4 and 66.9%, respectively) compared to other two classifiers. On the hold-out test set, the performance dropped by five percentage points in terms of accuracy. Overall, the histological characteristics alone did not allow us to develop a support tool suitable for actual clinical application, but it showed the maximum informative power contained in the same for the resolution of the clinical problem. The proposed study represents a starting point for future development of predictive models to obtain the probability for lymph node metastases by using histopathological features combined with other features of a different nature.

Establishing a prediction model of axillary nodal burden based on the combination of CT and ultrasound findings and the clinicopathological features in patients with early-stage breast cancer

Background

Axillary lymph node (ALN) management in early-stage breast cancer (ESBC) patients has become less invasive during the past decades. Here, we tried to explore whether high nodal burden (HNB) in ESBC patients could be predicted preoperatively, so as to avoid unnecessary sentinel lymph node biopsy (SLNB).

Methods

The clinicopathological and imaging data of patients with early invasive breast cancer (cT_1-2N₀M₀) were analyzed retrospectively. Univariate and multivariate analyses were performed for the risk factors of axillary HNB in ESBC patients, and a risk prediction model of HNB was established.

Results

HNB was identified in 105 (8.0%) of 1,300 ESBC patients. Multivariate analysis showed that estrogen receptors (ER) status, human epidermal growth factor receptor 2 (HER2) status, number of abnormal lymph nodes (LNs) on computed tomography (CT), and axillary score on ultrasound (US) were the risk factors of HNB (all P<0.05). The area under the receiver operating characteristic (ROC) curve in the prediction model was 0.914, with the sensitivity being 85.7% and the specificity being 82.4%. The calibration curve showed that the prediction model had good performance.

Conclusions

As a valuable tool for predicting HNB in ESBC patients, this newly established model helps clinicians to make reasonable axillary surgery decisions and thus avoid unnecessary SLNB.

Predicting of Sentinel Lymph Node Status in Breast Cancer Patients with Clinically Negative Nodes: A Validation Study

Simple Summary

Sentinel lymph node biopsy procedure is time consuming and expensive, but it is still the intra-operative exam capable of the best performance. However, sometimes, surgery is achieved without a clear diagnosis, so clinical decision support systems developed with artificial intelligence techniques are essential to assist current diagnostic procedures. In this work, we evaluated the usefulness of a CancerMath tool in the sentinel lymph nodes positivity prediction for clinically negative patients. We tested it on 993 patients referred to our institute characterized by sentinel lymph node status, tumor size, age, histologic type, grading, expression of estrogen receptor, progesterone receptor, HER2, and Ki-67. By training the CancerMath (CM) model on our dataset, we reached a sensitivity value of 72%, whereas the online one was 46%, despite a specificity reduction. It was found the addiction of the prognostic factors Her2 and Ki67 could help improve performances on the classification of particular types of patients.

Abstract

In the absence of lymph node abnormalities detectable on clinical examination or imaging, the guidelines provide for the dissection of the first axillary draining lymph nodes during surgery. It is not always possible to arrive at surgery without diagnostic doubts, and machine learning algorithms can support clinical decisions. The web calculator CancerMath (CM) allows you to estimate the probability of having positive lymph nodes valued on the basis of tumor size, age, histologic type, grading, expression of estrogen receptor, and progesterone receptor. We collected 993 patients referred to our institute with clinically negative results characterized by sentinel lymph node status, prognostic factors defined by CM, and also human epidermal growth factor receptor 2 (HER2) and Ki-67. Area Under the Curve (AUC) values obtained by the online CM application were comparable with those obtained after training its algorithm on our database. Nevertheless, by training the CM model on our dataset and using the same feature, we reached a sensitivity median value of 72%, whereas the online one was equal to 46%, despite a specificity reduction. We found that the addition of the prognostic factors Her2 and Ki67 could help improve performances on the classification of particular types of patients with the aim of reducing as much as possible the false positives that lead to axillary dissection. As showed by our experimental results, it is not particularly suitable for use as a support instrument for the prediction of metastatic lymph nodes on clinically negative patients.

Prediction of axillary nodal burden in patients with invasive lobular carcinoma using MRI

PURPOSE

To investigate clinical and imaging features associated with a high nodal burden (≥ 3 metastatic lymph nodes [LNs]) and compare diagnostic performance of US and MRI in patients with invasive lobular carcinoma (ILC) and invasive ductal carcinoma (IDC).

METHODS

Retrospective search revealed 239 patients with ILC and 999 with IDC who underwent preoperative US and MRI between January 2016 and June 2019. Patients with ILC were propensity-score-matched with patients with IDC. Univariate and multivariate logistic regression analyses were performed to determine factors associated with ≥ 3 metastatic LNs.

RESULTS

412 patients (206 ILC and 206 IDC) were evaluated. Of all patients with ILC, 27.2% (56/206) were node-positive and 7.8% (16/206) showed a high nodal burden. In multivariate analysis, the clinical N stage was the only independent factor associated with a high nodal burden in patients with IDC (odds ratio [OR] 6.24; 95% confidence interval [CI] 1.57-24.73; P = 0.009), but not in patients with ILC. Increased cortical thickness with loss of fatty hilum on US was associated with a high nodal burden in patients with ILC (OR 58.40; 95% CI 5.09-669.71; P = 0.001) and IDC (OR 24.14; 95% CI 3.52-165.37; P = 0.001), while suspicious LN findings at MRI were independently associated with a high nodal burden in ILC only (OR 13.94; 95% CI 2.61-74.39; P = 0.002).

CONCLUSION

In patients with ILC, MRI findings of suspicious LNs were helpful to predict a high nodal disease burden.

Can a machine-learning model improve the prediction of nodal stage after a positive sentinel lymph node biopsy in breast cancer?

Background: The current standard for evaluating axillary nodal burden in clinically node negative breast cancer is sentinel lymph node biopsy (SLNB). However, the accuracy of SLNB to detect nodal stage N2-3 remains debatable. Nomograms can help the decision-making process between axillary treatment options. The aim of this study was to create a new model to predict the nodal stage N2-3 after a positive SLNB using machine learning methods that are rarely seen in nomogram development.Material and methods: Primary breast cancer patients who underwent SLNB and axillary lymph node dissection (ALND) between 2012 and 2017 formed cohorts for nomogram development (training cohort, N = 460) and for nomogram validation (validation cohort, N = 70). A machine learning method known as the gradient boosted trees model (XGBoost) was used to determine the variables associated with nodal stage N2-3 and to create a predictive model. Multivariate logistic regression analysis was used for comparison.Results: The best combination of variables associated with nodal stage N2-3 in XGBoost modeling included tumor size, histological type, multifocality, lymphovascular invasion, percentage of ER positive cells, number of positive sentinel lymph nodes (SLN) and number of positive SLNs multiplied by tumor size. Indicating discrimination, AUC values for the training cohort and the validation cohort were 0.80 (95%CI 0.71-0.89) and 0.80 (95%CI 0.65-0.92) in the XGBoost model and 0.85 (95%CI 0.77-0.93) and 0.75 (95%CI 0.58-0.89) in the logistic regression model, respectively.Conclusions: This machine learning model was able to maintain its discrimination in the validation cohort better than the logistic regression model. This indicates advantages in employing modern artificial intelligence techniques into nomogram development. The nomogram could be used to help identify nodal stage N2-3 in early breast cancer and to select appropriate treatments for patients.

Axillary Nodal Evaluation in Breast Cancer: State of the Art

Axillary lymph node (LN) metastasis is the most important predictor of overall recurrence and survival in patients with breast cancer, and accurate assessment of axillary LN involvement is an essential component in staging breast cancer. Axillary management in patients with breast cancer has become much less invasive and individualized with the introduction of sentinel LN biopsy (SLNB). Emerging evidence indicates that axillary LN dissection may be avoided in selected patients with node-positive as well as node-negative cancer. Thus, assessment of nodal disease burden to guide multidisciplinary treatment decision making is now considered to be a critical role of axillary imaging and can be achieved with axillary US, MRI, and US-guided biopsy. For the node-positive patients treated with neoadjuvant chemotherapy, restaging of the axilla with US and MRI and targeted axillary dissection in addition to SLNB is highly recommended to minimize the false-negative rate of SLNB. Efforts continue to develop prediction models that incorporate imaging features to predict nodal disease burden and to select proper candidates for SLNB. As methods of axillary nodal evaluation evolve, breast radiologists and surgeons must work closely to maximize the potential role of imaging and to provide the most optimized treatment for patients.

External validation of a prognostic model based on total tumor load of sentinel lymph node for early breast cancer patients

Background

A prognostic model based on the results of molecular analysis of sentinel lymph nodes (SLN) is needed to replace the information that staging the entire axilla provided. The aim of the study is to conduct an external validation of a previously developed model for the prediction of 5-year DFS in a group of breast cancer patients that had undergone SLN biopsy assessed by the One Step Nucleic Acid Amplification (OSNA) method.

Methods

We collected retrospective data of 889 patients with breast cancer, who had not received systemic treatment before surgery, and who underwent SLN biopsy and evaluation of all SLN by OSNA. The discrimination ability of the model was assessed by the area under the ROC curve (AUC ROC), and its calibration by comparing 5-years DFS Kaplan–Meier estimates in quartile groups of model predicted probabilities (MPP).

Results

The AUC ROC ranged from 0.78 (at 2 years) to 0.73 (at 5 years) in the training set, and from 0.78 to 0.71, respectively, in the validation set. The MPP allowed to distinguish four groups of patients with heterogeneous DFS (log-rank test p < 0.0001). In the highest risk group, the HR were 6.04 [95% CI 2.70, 13.48] in the training set and 4.79 [2.310, 9.93] in the validation set.

Conclusions

The model for the prediction of 5-year DFS was successfully validated using the most stringent form of validation, in centers different from those involved in the development of the model. The external validation of the model confirms its utility for the prediction of 5-year DFS and the usefulness of the TTL value as a prognostic variable.

Electronic supplementary material

The online version of this article (10.1007/s10549-020-05623-4) contains supplementary material, which is available to authorized users.

Can We Identify or Exclude Extensive Axillary Nodal Involvement in Breast Cancer Patients Preoperatively?

Background

Breast cancer treatment has rapidly changed in the last few years. Particularly, treatment of patients with axillary nodal involvement has evolved after publication of several randomized clinical trials. Omitting axillary lymph node dissection in selected early breast cancer patients with one or two positive sentinel nodes did not compromise overall survival nor regional disease control in these trials. Hence, either excluding or identifying extensive axillary nodal involvement becomes increasingly important.

Purpose

To evaluate whether the current diagnostic modalities can accurately identify or exclude extensive axillary nodal involvement. Evaluated modalities were axillary ultrasound, ultrasound-guided needle biopsy, MRI, and PET/CT.

Methods

A literature search was performed in the Cochrane Library, EMBASE, and PubMed databases up to June 2019. The search strategy included terms for breast cancer, lymph nodes, and the different imaging modalities. Only articles that reported pathological N-stage or the total number of positive axillary lymph nodes were considered for inclusion. Studies with patients undergoing neoadjuvant systemic therapy were excluded.

Conclusion

There is no evidence that any of the current preoperative axillary imaging modalities can accurately exclude or identify breast cancer patients with extensive nodal involvement. Both negative PET/CT and negative MRI scans (with gadolinium-based contrast agents) are promising in excluding extensive nodal involvement. Larger studies should be performed to strengthen this conclusion. False-negative rates of axillary ultrasound and ultrasound-guided needle biopsy are too high to rely on negative results of these modalities in excluding extensive nodal involvement.

Computer-aided prediction model for axillary lymph node metastasis in breast cancer using tumor morphological and textural features on ultrasound

BACKGROUND AND OBJECTIVES

Axillary lymph node (ALN) status is a key indicator in assessing and determining the treatment strategy for patients with newly diagnosed breast cancer. Previous studies suggest that sonographic features of a primary tumor have the potential to predict ALN status in the preoperative staging of breast cancer. In this study, a computer-aided prediction (CAP) model as well as the tumor features for ALN metastasis in breast cancers were developed using breast ultrasound (US) images.

METHODS

A total of 249 malignant tumors were acquired from 247 female patients (ages 20-84 years; mean 55 ± 11 years) to test the differences between the non-metastatic (130) and metastatic (119) groups based on various features. After applying semi-automatic tumor segmentation, 69 quantitative features were extracted. The features included morphology and texture of tumors inside a ROI of breast US image. By the backward feature selection and linear logistic regression, the prediction model was constructed and established to estimate the likelihood of ALN metastasis for each sample collected.

RESULTS

In the experiments, the texture features showed higher performance for predicting ALN metastasis compared to morphology (Az, 0.730 vs 0.667). The difference, however, was not statistically significant (p-values > 0.05). Combining the textural and morphological features, the accuracy, sensitivity, specificity, and Az value achieved 75.1% (187/249), 79.0% (94/119), 71.5% (93/130), and 0.757, respectively.

CONCLUSIONS

The proposed CAP model, which combines textural and morphological features of primary tumor, may be a useful method to determine the ALN status in patients with breast cancer.