Micrometastases in axillary lymph nodes in breast cancer, post-neoadjuvant systemic therapy.

INTRODUCTION: The significance of minimal residual axillary disease, specifically micrometastases, following neoadjuvant systemic therapy (NST) remains largely unexplored. Our study aimed to elucidate the prognostic implications of micrometastases in axillary and sentinel lymph nodes following NST. METHODS: This retrospective study analyzed primary breast cancer patients who underwent surgery after NST from September 2006 through February 2018. All patients received axillary lymph node dissection (ALND), either with or without sentinel lymph node biopsy. Recurrence-free survival (RFS)-associated variables were identified using a multivariate Cox proportional hazard model. RESULTS: Of the 978 patients examined, 438 (44.8%) exhibited no pathologic lymph node involvement (ypN0) after NST, while 89 (9.1%) had micrometastases (ypN1mi) and 451 (46.7%) had macrometastases (ypN+). Notably, 51.1% of the patients with sentinel lymph node micrometastases (SLNmi) had additional metastases, nearly triple that of SLN-negative patients (P < 0.001), and 29.8% of SLNmi patients were upstaged with the ALND. Although ypN1mi was not associated with RFS in patients post-NST (HR, 1.02; 95% CI, 0.42-2.49; P = 0.958), SLNmi patients experienced significantly worse RFS compared to SLN-negative patients (hazard ratio [HR], 2.23; 95% confidence intervals [CI], 1.12-4.46; P = 0.023). Additional metastases in SLNmi were more prevalent in patients with larger residual breast disease greater than 20 mm, HR-positive/HER2-negative subtype, and low Ki-67 LI (< 14%). CONCLUSIONS: SLNmi is a negative prognostic factor significantly associated with additional non-SLN metastases, while ypN1mi does not influence the prognosis compared to ypN0. Hence, additional ALND may be warranted to confirm axillary nodal status in patients with SLNmi.

Should patients with hormone receptor-positive, HER2-negative breast cancer and one or two positive sentinel nodes undergo axillary dissection to determine candidacy for adjuvant abemaciclib?

BACKGROUND: The monarchE trial demonstrated improved outcomes with the use of adjuvant abemaciclib in patients with high-risk hormone receptor-positive, HER2-negative (HR+/HER2-) breast cancer defined as ≥4 positive lymph nodes (+LNs) or one to three +LNs with one or more additional high-risk features (HRFs). The proportion of patients with one or two positive sentinel lymph nodes (+SLNs) without HRFs who had ≥4 +LNs at the time of completion axillary lymph node dissection (cALND), and who therefore qualified for receipt of abemaciclib, was investigated. METHODS: Females with pathologically node-positive nonmetastatic HR+/HER2- breast cancer stratified by the number of +SLNs and +LNs and the presence of one or more HRFs were identified from the National Cancer Database (2018-2019). The proportion of patients meeting the criteria for abemaciclib both before and after ALND was assessed. RESULTS: Of the 22,048 patients identified, 1578 patients underwent upfront surgery, had one or two +SLNs without HRFs, and went on to cALND. Only 213 (13%) of these patients had ≥4 +LNs; thus, cALND performed solely to determine abemaciclib candidacy would have constituted surgical overtreatment in 1365 patients (87%). When stratified by the number of +SLNs, only 10% of those with one +SLN and 24% of those with two +SLNs had ≥4 +LNs after cALND, which meets the criteria for abemaciclib. CONCLUSIONS: Patients with one +SLN without HRFs are unlikely to have ≥4 +LNs and should not be subjected to the morbidity of ALND in order to inform candidacy for abemaciclib. An individualized multidisciplinary discussion should be undertaken about the risk:benefit ratio of ALND and abemaciclib for those with two +SLNs.

Nonsentinel lymph node metastases in cases of micrometastasis detected by sentinel lymph node biopsy after neoadjuvant chemotherapy.

BACKGROUND: There is a clinical need to omit axillary lymph node dissection (ALND) when residual disease in sentinel lymph nodes (SLNs) is low after neoadjuvant chemotherapy (NAC). This study aimed to clarify the relationship between micrometastasis in SLNs after NAC and additional non-SLN metastases by analyzing SLN biopsy results followed by ALND. METHODS: This retrospective study reviewed clinical records of patients who underwent breast cancer surgery between January 2010 and June 2022 after NAC at Samsung Medical Center. Of 3944 patients, 806 underwent SLN biopsy followed by ALND. Intraoperative frozen SLN biopsy results were examined, including the number and size of metastases in SLNs, and further investigated the number of additional non-SLN metastases. RESULTS: Among the 806 patients, 95 (11.8%) had micrometastasis on SLNs in frozen sections, of which 89 (93.7%) had clinically node-positive (cN1-3) breast cancer before NAC. Twenty-three patients (24.2%) exhibited positive additional non-SLNs after ALND. The presence of lymphovascular invasion (vs. absence; odds ratio [OR] = 4.02, p = .0151) and having two or more SLNs with micrometastasis (vs. a positive SLN; OR = 3.65, p = .0301) were significantly associated with additional non-SLN metastases. Tumor subtypes and breast pathological complete response after NAC showed no correlation with the additional non-SLN metastases. CONCLUSION: The study identified a 24.2% possibility of additional non-SLN metastasis if micrometastases was detected in the SLN after NAC. This rate is significant, indicating that ALND cannot be omitted if low volume residual disease, such as micrometastasis, is identified in the SLN after NAC.

Long-term outcome in patients with nodal-positive breast cancer treated with sentinel lymph node biopsy alone after neoadjuvant chemotherapy.

PURPOSE: Sentinel lymph node biopsy (SLNB) has yet to be accepted as the standard staging procedure in node positive (cN1) breast cancer patients who had clinical complete response in the axilla (cN0) following neoadjuvant chemotherapy (NAC), due to the presumed high false negative rate associated with SLNB in such scenario. This study aimed to determine whether there is a significant difference in the axillary recurrence rate (ARR) and long-term survival in this group of patients, receiving SLNB alone versus axillary lymph node dissection (ALND). METHODS: A retrospective cohort of cN1 patients who were rendered cN0 by NAC from January 2014 to December 2018 were identified from the Asan Medical Center database. Patients' characteristics and outcomes were collected and analyzed. RESULTS: 902 cN1 patients treated with NAC and turned cN0 were identified. 477 (52.9%) patients achieved complete pathological response in the axilla (ypN0). At a median follow up of 65 months, ARR was 3.2% in the SLNB only group and 1.8% in the ALND group (p = 0.398). DFS and OS were significantly worse in patients with ALND as compared to patients with SLNB only (p = 0.011 and 0.047, respectively). We noted more patients in the ALND group had T3-4 tumor. In the subgroup analysis, we showed that in the T1-2 subgroup (n = 377), there was no statistically significant difference in DFS and OS (p = 0.242 and 0.671, respectively) between SLNB only and ALND group. CONCLUSION: Our findings suggest that cN1 patients who were converted to ypN0 following NAC may be safely treated with SLNB only.

Sentinel lymph node biopsy before and after neoadjuvant chemotherapy in cN0 breast cancer patients: impact on axillary morbidity and survival-a propensity score cohort study.

PURPOSE: In patients with clinically lymph node-negative (cN0) breast cancer, performing sentinel lymph node biopsy (SLNB) after neoadjuvant chemotherapy (NACT) has been preferentially embraced in comparison to before NACT. However, survival outcomes associated with both strategies remain understudied. We aimed to compare the axillary lymphadenectomy (ALND) rate, disease-free survival (DFS), and overall survival (OS), between two strategies. METHODS: We included 310 patients in a retrospective observational study. SNLB was performed before NACT from December 2006 to April 2014 (107 cases) and after NACT from May 2014 to May 2020 (203 patients). An inverse probability of treatment weighting (IPTW) method was applied to homogenize both groups. Hazard ratios (HR) and odd ratios (OR) are reported with 95% confidence intervals (95%CI). RESULTS: The lymphadenectomy rate was 29.9% before NACT and 7.4% after NACT (p < 0.001), with an OR of 5.35 95%CI (2.7-10.4); p = .002. After 4 years of follow-up, SLNB after NACT was associated with lower risk for DFS, HR 0.42 95%CI (0.17-1.06); p = 0.066 and better OS, HR 0.21 CI 95% (0.07-0.67); p = 0.009 than SLNB before NACT. After multivariate analysis, independent adverse prognostic factors for OS included SLNB before NACT, HR 3.095 95%CI (2.323-4.123), clinical nonresponse to NACT, HR 1.702 95% CI (1.012-2.861), and small tumors (cT1) with high proliferation index, HR 1.889 95% (1.195-2.985). CONCLUSION: Performing SLNB before NACT results in more ALND and has no benefit for patient survival. These findings support discontinuing the practice of SLNB before NACT in patients with cN0 breast cancer.

Tumor-infiltrating lymphocytes as a predictor of axillary and primary tumor pathological response after neoadjuvant chemotherapy in patients with breast cancer: a retrospective cohort study.

PURPOSE: Tumor-infiltrating lymphocytes (TILs) can predict complete pathological response (pCR) of tumor in the breast but not so well-defined in the axilla after neoadjuvant chemotherapy. Since axillary surgery is being increasingly de-escalated after NACT, we aimed to investigate the relationship between TILs and pCR in the axilla and breast, as well as survival amongst NACT patients. METHODS: Clinicopathological data on patients who underwent NACT between 2013 and 2020 were retrospectively examined. Specifically, pre-TILs (before NACT), post-TILs (after NACT) and ΔTIL (changes in TILs) were assessed. Primary endpoint was pCR and secondary endpoints were breast cancer-free interval (BCFI) and overall survival (OS). RESULTS: Two hundred and twenty patients with nodal metastases were included. Overall axillary and breast pCR rates were 42.7% (94/220) and 39.1% (86/220), respectively, whereas the combined pCR rate was 32.7% (72/220). High pre-TILs (OR 2.03, 95% CI 1.02-4.05; p = 0.04) predicted axillary pCR whereas, high post-TILs (OR 0.33, 95% CI 0.14-0.76; p = 0.009) and increased ΔTILs (OR 0.25, 95% CI 0.08-0.79; p = 0.02) predicted non-axillary pCR. TILs were not a significant predictor for BCFI and OS. CONCLUSIONS: This study supports the potential use of pre-TILs to select initially node-positive patients for axillary surgical de-escalation after NACT.

Omission of axillary lymph node dissection for breast cancer patients with three or more positive sentinel lymph nodes.

PURPOSE: The ACOSOG Z0011 (Z11) trial assessed the benefit of axillary dissection (ALND) for breast cancer patients with sentinel lymph node (SLN) metastases; however, Z11 excluded patients with ≥ 3 positive SLNs. We analyzed trends in ALND omission in patients with ≥ 3 positive SLNs. METHODS: Women with ≥ 3 positive SLNs who underwent breast-conserving surgery (BCS) or mastectomy between 2018 and 2020 in the National Cancer Database were included using SLN codes initiated in 2018. Patients with stage IV disease, recurrent breast cancer, and who underwent neoadjuvant chemotherapy were excluded. A multivariable logistic regression model was utilized to determine the proportion who received ALND and factors associated with ALND omission. A subgroup analysis was performed among patients who met the remainder of the Z11 inclusion criteria (BCS, T1/T2 breast cancer). RESULTS: We identified 3654 patients with ≥ 3 positive SLNs. ALND was omitted in 37% of patients, and omission significantly increased from 2018 to 2020 (29% vs. 41%, p < 0.0001). Older age, lower grade tumors, no radiation, non-academic facility, BCS, more SLNs examined and fewer positive SLNs were significantly associated with ALND omission. 942 patients with ≥ 3 positive SLNs met the remainder of the Z11 inclusion criteria. ALND was omitted in 49% of these patients, and omission increased from 2018 to 2020 (44% vs. 49%, p = 0.22). CONCLUSION: Approximately one-third of patients with ≥ 3 positive SLNs do not undergo ALND; omission of ALND increased from 2018 to 2020. Studies assessing oncologic outcomes of patients with ≥ 3 positive SLNs who do and do not receive ALND are required.

Characteristics and risk factors of axillary lymph node metastasis of microinvasive breast cancer.

PURPOSE: To select patients who would benefit most from sentinel lymph node biopsy (SLNB) by investigating the characteristics and risk factors of axillary lymph node metastasis (ALNM) in microinvasive breast cancer (MIBC). METHODS: This retrospective study included 1688 patients with MIBC who underwent breast surgery with axillary staging at the Asan Medical Center from 1995 to 2020. RESULTS: Most patients underwent SLNB alone (83.5%). Seventy (4.1%) patients were node-positive, and the majority had positive lymph nodes < 10 mm, with micro-metastases occurring frequently (n = 37; 55%). Node-positive patients underwent total mastectomy and axillary lymph node dissection (ALND) more than breast-conserving surgery (BCS) and SLNB compared with node-negative patients (p < 0.001). In the multivariate analysis, independent predictors of ALNM included young age [odds ratio (OR) 0.959; 95% confidence interval (CI) 0.927-0.993; p = 0.019], ALND (OR 11.486; 95% CI 5.767-22.877; p < 0.001), number of lymph nodes harvested (≥ 5) (OR 3.184; 95% CI 1.555-6.522; p < 0.001), lymphovascular invasion (OR 6.831; 95% CI 2.386-19.557; p < 0.001), presence of multiple microinvasion foci (OR 2.771; 95% CI 1.329-5.779; p = 0.007), prominent lymph nodes in preoperative imaging (OR 2.675; 95% CI 1.362-5.253; p = 0.004), and hormone receptor positivity (OR 2.491; 95% CI 1.230-5.046; p = 0.011). CONCLUSION: Low ALNM rate (4.1%) suggests that routine SLNB for patients with MIBC is unnecessary but can be valuable for patients with specific risk factors. Ongoing trials for omitting SLNB in early breast cancer, and further subanalyses focusing on rare populations with MIBC are necessary.

MRI radiomics and biological correlations for predicting axillary lymph node burden in early-stage breast cancer.

BACKGROUND AND AIMS: Preoperative prediction of axillary lymph node (ALN) burden in patients with early-stage breast cancer is pivotal for individualised treatment. This study aimed to develop a MRI radiomics model for evaluating the ALN burden in early-stage breast cancer and to provide biological interpretability to predictions by integrating radiogenomic data. METHODS: This study retrospectively analyzed 1211 patients with early-stage breast cancer from four centers, supplemented by data from The Cancer Imaging Archive (TCIA) and Duke University (DUKE). MRI radiomic features were extracted from dynamic contrast-enhanced MRI images and an ALN burden-related radscore was constructed by the backpropagation neural network algorithm. Clinical and combined models were developed, integrating ALN-related clinical variables and radscore. The Kaplan-Meier curve and log-rank test were used to assess the prognostic differences between the predicted high- and low-ALN burden groups in both Center I and DUKE cohorts. Gene set enrichment and immune infiltration analyses based on transcriptomic TCIA and TCIA Breast Cancer dataset were used to investigate the biological significance of the ALN-related radscore. RESULTS: The MRI radiomics model demonstrated an area under the curve of 0.781-0.809 in three validation cohorts. The predicted high-risk population demonstrated a poorer prognosis (log-rank P < .05 in both cohorts). Radiogenomic analysis revealed migration pathway upregulation and cell differentiation pathway downregulation in the high radscore groups. Immune infiltration analysis confirmed the ability of radiological features to reflect the heterogeneity of the tumor microenvironment. CONCLUSIONS: The MRI radiomics model effectively predicted the ALN burden and prognosis of early-stage breast cancer. Moreover, radiogenomic analysis revealed key cellular and immune patterns associated with the radscore.

Prevention of Seroma Formation and Its Sequelae After Axillary Lymph Node Dissection: An Up-to-Date Systematic Review and Guideline for Surgeons.

INTRODUCTION: Seroma formation after axillary lymph node dissection (ALND) remains a troublesome complication with significant morbidity. Numerous studies have tried to identify techniques to prevent seroma formation. The aim of this systematic review and network meta-analysis is to use available literature to identify the best intervention for prevention of seroma after standalone ALND. METHODS: A literature search was performed for all comparative articles regarding seroma formation in patients undergoing a standalone ALND or ALND with breast-conserving surgery in the last 25 years. Data regarding seroma formation, clinically significant seroma (CSS), surgical site infections (SSI), and hematomas were collected. The network meta-analysis was performed using a random effects model and the level of inconsistency was evaluated using the Bucher method. RESULTS: A total of 19 articles with 1962 patients were included. Ten different techniques to prevent seroma formation were described. When combining direct and indirect comparisons, axillary drainage until output is less than 50 ml per 24 h for two consecutive days results in significantly less CSS. The use of energy sealing devices, padding, tissue glue, or patches did not significantly reduce the incidence of CSS. When comparing the different techniques with regard to SSIs, no statistically significant differences were seen. CONCLUSIONS: To prevent CSS after ALND, axillary drainage is the most valuable and scientifically proven measure. On the basis of the results of this systematic review with network meta-analysis, removing the drain when output is < 50 ml per 24 h for two consecutive days irrespective of duration seems best. Since drainage policies vary widely, an evidence-based guideline is needed.

Omission of Axillary Lymph Node Dissection in Patients with Residual Nodal Disease After Neoadjuvant Chemotherapy.

BACKGROUND: Axillary management after neoadjuvant chemotherapy (NAC) is evolving but axillary lymph node dissection (ALND) remains the standard of care for patients with residual nodal disease. The results of the Alliance A011202 trial evaluating the oncologic safety of ALND omission in this cohort are pending but we hypothesize that ALND omission is already increasing. METHODS: The National Cancer Database was queried to identify patients diagnosed with cT1-3N1M0 breast cancer who underwent NAC and had residual nodal disease (ypN1mi-2) from 2012 to 2021. Temporal trends in omission of completion ALND were assessed annually. Multivariable logistic and Cox regression models were used to identify factors associated with ALND omission and overall survival (OS), respectively. RESULTS: A total of 6101 patients were included; the majority presented with cT2 disease (57%), with 69% HER2+, 23% triple-negative, and 8% hormone receptor-positive/HER2-. Overall, 34% underwent sentinel lymph node biopsy (SLNB) alone. Rates of ALND were the lowest in the last 4 years of observation. After adjustment, treatment at community centers (vs. academic) and lower pathologic nodal burden were associated with omission of ALND. ALND omission was associated with a higher unadjusted OS (5-year OS: 86% SLNB alone vs. 84% ALND; log-rank p = 0.03), however this association was not maintained after adjustment. CONCLUSIONS: Despite the impending release of the Alliance A011202 results, omission of ALND in patients with residual nodal disease after NAC is increasing. This practice appears more prominent in community centers and in patients with a lower burden of residual nodal disease. No association with OS was noted.

Oncological Safety of Skipping Axillary Lymph Node Dissection in Patients with Clinical N0, Sentinel Node-Positive Breast Cancer Undergoing Total Mastectomy.

OBJECTIVE: This study aimed to determine whether sentinel lymph node biopsy (SLNB) alone could afford oncological outcomes comparable with axillary lymph node dissection (ALND) in patients with early breast cancer without palpable lymphadenopathy who underwent total mastectomy (TM) and were SLN-positive. METHODS: This study analyzed clinical data of 6747 patients with breast cancer who underwent TM between 2014 and 2018 in two tertiary hospitals in Korea. Overall, 643 clinical stage T1-3 N0 patients who did not receive neoadjuvant therapy and had one to two metastatic SLNs at the time of surgery were included. Propensity score matching was performed between the SLNB alone and ALND groups, adjusting for clinical T stage and number of metastatic SLNs. In total, 237 patients were allocated to each group. RESULTS: Mean number of metastatic SLNs was 1.2 for the SLNB group and 1.6 for the ALND group. With a median follow-up of 65.0 months, 5 year disease-free survival was 90.8% for the SLNB group and 93.9% for the ALND group (hazard ratio [HR] 1.35, 95% confidence interval [CI] 0.70-2.58; p = 0.36). 5 year ipsilateral locoregional recurrence-free survival (LRRFS) was not significantly different between the two groups (95.1% and 98.3% for the SLNB and ALND groups, respectively) [HR 1.86, 95% CI 0.69-5.04; p = 0.21]. In the SLNB group, patients who received radiation therapy (RT) showed superior 5 year LRRFS than patients who did not receive RT (100% vs. 92.9%; p = 0.02). CONCLUSION: Collectively, our findings suggest that SLNB could afford comparable outcomes to ALND in patients with early breast cancer and one to two metastatic SLNs who underwent TM. Importantly, RT could decrease locoregional recurrence in patients who underwent SLNB alone.

Implementation of Choosing Wisely® Recommendations for Lymph Node Surgery in Male Breast Cancer.

BACKGROUND: The Choosing Wisely® (CW) campaign recommended de-implementation of surgical management of axillary nodes in specified patients. This study aimed to assess trends in the application of CW guidelines for lymph node (LN) surgery in males with breast cancer. METHODS: The National Cancer Database was queried for males diagnosed with breast cancer from 2017 to 2020. Patients were categorized into two cohorts based on CW criteria. Cohort 1 included all T1-2, clinically node-negative patients who underwent breast-conserving therapy and with ≤ 2 positive nodes, and Cohort 2 included all T1-2, node-negative, hormone receptor-positive, human epidermal growth factor receptor 2 (HER2)-negative patients aged ≥ 70 years. In Cohort 1, patients who underwent sentinel LN biopsy (SLNB) alone were compared with axillary LN dissection (ALND) or no LN surgery, while in Cohort 2, patients who underwent LN surgery were compared with those with no LN surgery. RESULTS: Of 617 patients who met the criteria for Cohort 1, 73.1% underwent SLNB alone compared with ALND (11.8%) or no LN surgery (15.1%). Those who received SLNB alone were younger (65 vs. 68 vs. 73 years; p < 0.001). The annual proportion of males who underwent SLNB alone remained stable from 2017 to 2020. Overall, 1565 patients met the criteria for Cohort 2, and 84.9% received LN surgery. LN surgery was omitted in older patients (81 vs. 77; p < 0.001). The proportion of elderly males with early-stage breast cancer who underwent LN surgery increased from 2017 to 2020. CONCLUSION: This study demonstrates that CW recommendations are not being routinely applied to males. These findings reinforce the need for additional studies and subsequent recommendations for optimal application of axillary surgery de-implementation for males diagnosed with breast cancer.

Artificial intelligence assisted ultrasound for the non-invasive prediction of axillary lymph node metastasis in breast cancer.

PURPOSE: A practical noninvasive method is needed to identify lymph node (LN) status in breast cancer patients diagnosed with a suspicious axillary lymph node (ALN) at ultrasound but a negative clinical physical examination. To predict ALN metastasis effectively and noninvasively, we developed an artificial intelligence-assisted ultrasound system and validated it in a retrospective study. METHODS: A total of 266 patients treated with sentinel LN biopsy and ALN dissection at Peking Union Medical College & Hospital(PUMCH) between the year 2017 and 2019 were assigned to training, validation and test sets (8:1:1). A deep learning model architecture named DeepLabV3 + was used together with ResNet-101 as the backbone network to create an ultrasound image segmentation diagnosis model. Subsequently, the segmented images are classified by a Convolutional Neural Network to predict ALN metastasis. RESULTS: The area under the receiver operating characteristic curve of the model for identifying metastasis was 0.799 (95% CI: 0.514-1.000), with good end-to-end classification accuracy of 0.889 (95% CI: 0.741-1.000). Moreover, the specificity and positive predictive value of this model was 100%, providing high accuracy for clinical diagnosis. CONCLUSION: This model can be a direct and reliable tool for the evaluation of individual LN status. Our study focuses on predicting ALN metastasis by radiomic analysis, which can be used to guide further treatment planning in breast cancer.

The use of longitudinal CT-based radiomics and clinicopathological features predicts the pathological complete response of metastasized axillary lymph nodes in breast cancer.

BACKGROUND: Accurate assessment of axillary status after neoadjuvant therapy for breast cancer patients with axillary lymph node metastasis is important for the selection of appropriate subsequent axillary treatment decisions. Our objectives were to accurately predict whether the breast cancer patients with axillary lymph node metastases could achieve axillary pathological complete response (pCR). METHODS: We collected imaging data to extract longitudinal CT image features before and after neoadjuvant chemotherapy (NAC), analyzed the correlation between radiomics and clinicopathological features, and developed models to predict whether patients with axillary lymph node metastasis can achieve axillary pCR after NAC. The clinical utility of the models was determined via decision curve analysis (DCA). Subgroup analyses were also performed. Then, a nomogram was developed based on the model with the best predictive efficiency and clinical utility and was validated using the calibration plots. RESULTS: A total of 549 breast cancer patients with metastasized axillary lymph nodes were enrolled in this study. 42 independent radiomics features were selected from LASSO regression to construct a logistic regression model with clinicopathological features (LR radiomics-clinical combined model). The AUC of the LR radiomics-clinical combined model prediction performance was 0.861 in the training set and 0.891 in the testing set. For the HR + /HER2 - , HER2 + , and Triple negative subtype, the LR radiomics-clinical combined model yields the best prediction AUCs of 0.756, 0.812, and 0.928 in training sets, and AUCs of 0.757, 0.777 and 0.838 in testing sets, respectively. CONCLUSIONS: The combination of radiomics features and clinicopathological characteristics can effectively predict axillary pCR status in NAC breast cancer patients.

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.

Multitask Deep Learning-Based Whole-Process System for Automatic Diagnosis of Breast Lesions and Axillary Lymph Node Metastasis Discrimination from Dynamic Contrast-Enhanced-MRI: A Multicenter Study.

BACKGROUND: Accurate diagnosis of breast lesions and discrimination of axillary lymph node (ALN) metastases largely depend on radiologist experience. PURPOSE: To develop a deep learning-based whole-process system (DLWPS) for segmentation and diagnosis of breast lesions and discrimination of ALN metastasis. STUDY TYPE: Retrospective. POPULATION: 1760 breast patients, who were divided into training and validation sets (1110 patients), internal (476 patients), and external (174 patients) test sets. FIELD STRENGTH/SEQUENCE: 3.0T/dynamic contrast-enhanced (DCE)-MRI sequence. ASSESSMENT: DLWPS was developed using segmentation and classification models. The DLWPS-based segmentation model was developed by the U-Net framework, which combined the attention module and the edge feature extraction module. The average score of the output scores of three networks was used as the result of the DLWPS-based classification model. Moreover, the radiologists' diagnosis without and with the DLWPS-assistance was explored. To reveal the underlying biological basis of DLWPS, genetic analysis was performed based on RNA-sequencing data. STATISTICAL TESTS: Dice similarity coefficient (DI), area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and kappa value. RESULTS: The segmentation model reached a DI of 0.828 and 0.813 in the internal and external test sets, respectively. Within the breast lesions diagnosis, the DLWPS achieved AUCs of 0.973 in internal test set and 0.936 in external test set. For ALN metastasis discrimination, the DLWPS achieved AUCs of 0.927 in internal test set and 0.917 in external test set. The agreement of radiologists improved with the DLWPS-assistance from 0.547 to 0.794, and from 0.848 to 0.892 in breast lesions diagnosis and ALN metastasis discrimination, respectively. Additionally, 10 breast cancers with ALN metastasis were associated with pathways of aerobic electron transport chain and cytoplasmic translation. DATA CONCLUSION: The performance of DLWPS indicates that it can promote radiologists in the judgment of breast lesions and ALN metastasis and nonmetastasis. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY STAGE: 3.

MRI-Based Kinetic Heterogeneity Evaluation in the Accurate Access of Axillary Lymph Node Status in Breast Cancer Using a Hybrid CNN-RNN Model.

BACKGROUND: Accurate evaluation of the axillary lymph node (ALN) status is needed for determining the treatment protocol for breast cancer (BC). The value of magnetic resonance imaging (MRI)-based tumor heterogeneity in assessing ALN metastasis in BC is unclear. PURPOSE: To assess the value of deep learning (DL)-derived kinetic heterogeneity parameters based on BC dynamic contrast-enhanced (DCE)-MRI to infer the ALN status. STUDY TYPE: Retrospective. SUBJECTS: 1256/539/153/115 patients in the training cohort, internal validation cohort, and external validation cohorts I and II, respectively. FIELD STRENGTH/SEQUENCE: 1.5 T/3.0 T, non-contrast T1-weighted spin-echo sequence imaging (T1WI), DCE-T1WI, and diffusion-weighted imaging. ASSESSMENT: Clinical pathological and MRI semantic features were obtained by reviewing histopathology and MRI reports. The segmentation of the tumor lesion on the first phase of T1WI DCE-MRI images was applied to other phases after registration. A DL architecture termed convolutional recurrent neural network (ConvRNN) was developed to generate the KHimage (kinetic heterogeneity of DCE-MRI image) score that indicated the ALN status in patients with BC. The model was trained and optimized on training and internal validation cohorts, tested on two external validation cohorts. We compared ConvRNN model with other 10 models and the subgroup analyses of tumor size, magnetic field strength, and molecular subtype were also evaluated. STATISTICAL TESTS: Chi-squared, Fisher's exact, Student's t, Mann-Whitney U tests, and receiver operating characteristics (ROC) analysis were performed. P < 0.05 was considered significant. RESULTS: The ConvRNN model achieved area under the curve (AUC) of 0.802 in the internal validation cohort and 0.785-0.806 in the external validation cohorts. The ConvRNN model could well evaluate the ALN status of the four molecular subtypes (AUC = 0.685-0.868). The patients with larger tumor sizes (>5 cm) were more susceptible to ALN metastasis with KHimage scores of 0.527-0.827. DATA CONCLUSION: A ConvRNN model outperformed traditional models for determining the ALN status in patients with BC. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Diagnostic performance of MRI for assessing axillary lymph node status after neoadjuvant chemotherapy in breast cancer: a systematic review and meta-analysis.

OBJECTIVE: This systematic review examined the diagnostic performance of magnetic resonance imaging (MRI) for assessing axillary lymph node status (ALNS) after neoadjuvant chemotherapy (NAC) in breast cancer patients. METHODS: We searched PubMed, Embase, Cochrane Library, and Web of Science to identify relevant studies and used the QUADAS-2 tool to assess methodological quality of eligible studies. We used STATA version 12.0 to perform data pooling, heterogeneity testing, subgroup analysis, and sensitivity analysis. RESULTS: For the 21 enrolled studies, including 2875 patients, the pooled sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio were respectively 0.63 (95% CI: 0.53-0.72), 0.75 (95% CI: 0.68-0.81), 2.52 (95% CI: 1.98-3.19), 0.50 (95% CI: 0.39-0.63), and 5.08 (95% CI: 3.38-7.63). The AUC was 0.76 (95% CI: 0.72-0.79). I2 values of sensitivity (I2 = 94.41%) and specificity (I2 = 88.97%) were both > 50%. For the initial positive ALN patients, the pooled sensitivity and specificity were 0.64 (95% CI: 0.53-0.75) and 0.74 (95% CI: 0.64-0.82), respectively. Sensitivity analyses by focusing on studies with MRI performed post-NAC, studies using DCE-MRI, or studies with low risk of bias showed similar results to the primary analyses. CONCLUSION: MRI may have suboptimal diagnostic value in assessing ALNS after NAC for breast cancer patients. Due to the inconsistency of NAC regimens, the variability of axillary surgery, and the lack of time interval between MRI and surgery, further studies are needed to confirm our findings. CLINICAL RELEVANCE STATEMENT: Our study provided the diagnostic value of MRI in assessing axillary lymph node status after neoadjuvant chemotherapy for breast cancer patients. KEY POINTS: • MRI may have suboptimal diagnostic value in assessing axillary lymph node status after NAC for general breast cancer patients. • The initial axillary lymph node status has little impact on the diagnostic efficacy of MRI. • The substantial heterogeneity among studies highlights the need for further studies to provide more high-quality evidence in this field.

Multi-modality radiomics model predicts axillary lymph node metastasis of breast cancer using MRI and mammography.

OBJECTIVES: We aimed to develop a multi-modality model to predict axillary lymph node (ALN) metastasis by combining clinical predictors with radiomic features from magnetic resonance imaging (MRI) and mammography (MMG) in breast cancer. This model might potentially eliminate unnecessary axillary surgery in cases without ALN metastasis, thereby minimizing surgery-related complications. METHODS: We retrospectively enrolled 485 breast cancer patients from two hospitals and extracted radiomics features from tumor and lymph node regions on MRI and MMG images. After feature selection, three random forest models were built using the retained features, respectively. Significant clinical factors were integrated with these radiomics models to construct a multi-modality model. The multi-modality model was compared to radiologists' diagnoses on axillary ultrasound and MRI. It was also used to assist radiologists in making a secondary diagnosis on MRI. RESULTS: The multi-modality model showed superior performance with AUCs of 0.964 in the training cohort, 0.916 in the internal validation cohort, and 0.892 in the external validation cohort. It surpassed single-modality models and radiologists' ALN diagnosis on MRI and axillary ultrasound in all validation cohorts. Additionally, the multi-modality model improved radiologists' MRI-based ALN diagnostic ability, increasing the average accuracy from 70.70 to 78.16% for radiologist A and from 75.42 to 81.38% for radiologist B. CONCLUSION: The multi-modality model can predict ALN metastasis of breast cancer accurately. Moreover, the artificial intelligence (AI) model also assisted the radiologists to improve their diagnostic ability on MRI. CLINICAL RELEVANCE STATEMENT: The multi-modality model based on both MRI and mammography images allows preoperative prediction of axillary lymph node metastasis in breast cancer patients. With the assistance of the model, the diagnostic efficacy of radiologists can be further improved. KEY POINTS: • We developed a novel multi-modality model that combines MRI and mammography radiomics with clinical factors to accurately predict axillary lymph node (ALN) metastasis, which has not been previously reported. • Our multi-modality model outperformed both the radiologists' ALN diagnosis based on MRI and axillary ultrasound, as well as single-modality radiomics models based on MRI or mammography. • The multi-modality model can serve as a potential decision support tool to improve the radiologists' ALN diagnosis on MRI.