Preoperative Nomogram for Predicting Sentinel Lymph Node Metastasis Risk in Breast Cancer: A Potential Application on Omitting Sentinel Lymph Node Biopsy

Deep learning radiomics based prediction of axillary lymph node metastasis in breast cancer

This study aimed to develop and validate a deep learning radiomics nomogram (DLRN) for the preoperative evaluation of axillary lymph node (ALN) metastasis status in patients with a newly diagnosed unifocal breast cancer. A total of 883 eligible patients with breast cancer who underwent preoperative breast and axillary ultrasound were retrospectively enrolled between April 1, 2016, and June 30, 2022. The training cohort comprised 621 patients from Hospital I; the external validation cohorts comprised 112, 87, and 63 patients from Hospitals II, III, and IV, respectively. A DLR signature was created based on the deep learning and handcrafted features, and the DLRN was then developed based on the signature and four independent clinical parameters. The DLRN exhibited good performance, yielding areas under the receiver operating characteristic curve (AUC) of 0.914, 0.929, and 0.952 in the three external validation cohorts, respectively. Decision curve and calibration curve analyses demonstrated the favorable clinical value and calibration of the nomogram. In addition, the DLRN outperformed five experienced radiologists in all cohorts. This has the potential to guide appropriate management of the axilla in patients with breast cancer, including avoiding overtreatment.

Prediction of sentinel lymph node metastasis in breast cancer patients based on preoperative features: a deep machine learning approach

Sentinel lymph node (SLN) biopsy is the standard surgical approach to detect lymph node metastasis in breast cancer. Machine learning is a novel tool that provides better accuracy for predicting positive SLN involvement in breast cancer patients. This study obtained data from 2890 surgical cases of breast cancer patients from two referral hospitals in Iran from 2000 to 2021. Patients whose SLN involvement status was identified were included in our study. The dataset consisted of preoperative features, including patient features, gestational factors, laboratory data, and tumoral features. In this study, TabNet, an end-to-end deep learning model, was proposed to predict SLN involvement in breast cancer patients. We compared the accuracy of our model with results from logistic regression analysis. A total of 1832 patients with an average age of 51 ± 12 years were included in our study, of which 697 (25.5%) had SLN involvement. On average, the TabNet model achieved an accuracy of 75%, precision of 81%, specificity of 70%, sensitivity of 87%, and AUC of 0.74, while the logistic model demonstrated an accuracy of 70%, precision of 73%, specificity of 65%, sensitivity of 79%, F1 score of 73%, and AUC of 0.70 in predicting the SLN involvement in patients. Vascular invasion, tumor size, core needle biopsy pathology, age, and FH had the most contributions to the TabNet model. The TabNet model outperformed the logistic regression model in all metrics, indicating that it is more effective in predicting SLN involvement in breast cancer patients based on preoperative data.

Cryoablation Allows the Ultimate De-escalation of Surgical Therapy for Select Breast Cancer Patients

BACKGROUND

Widespread use of screening mammography has allowed breast cancer to be detected at earlier stages. This allows for increased customization of treatment and less aggressive management. De-escalation of therapy plays an important role in decreasing treatment burden and improving patient quality of life. This report examines cryoablation as the next step in the surgical de-escalation of breast cancer.

METHODS

Women with a diagnosis of clinically node-negative, estrogen receptor-positive (ER +), progesterone receptor-positive (PR +), human epidermal growth factor receptor 2-negative (HER2 -) infiltrating ductal carcinomas 1.5 cm or smaller underwent ultrasound-guided cryoablation. Either the Visica 2 treatment system (before 2020) or the ProSense treatment system (since 2020) was used to perform the cryoablation. Patients received mammograms and ultrasounds at a 6 months follow-up visit, and magnetic resonance images at baseline, then at 1 year follow-up intervals. Adjuvant therapy decisions and disease status were recorded.

RESULTS

This study enrolled 32 patients who underwent 33 cryoablation procedures (1 patient had bilateral cancer). One patient had a sentinel node biopsy in addition to clinical staging of the axilla. For all the patients, adjuvant endocrine therapy was recommended, and six patients (18.75%) received adjuvant radiation. Of the 32 patients, 20 (60.6%) have been followed up for 2 years or longer, with no residual or recurrent disease at the site of ablation.

CONCLUSION

Cryoablation of the primary tumor foregoing sentinel node biopsy offers an oncologically safe and feasible minimally invasive office-based procedure option in lieu of surgery for patients with early-stage, low-risk breast cancer.

The value of whole-lesion histogram analysis based on field‑of‑view optimized and constrained undistorted single shot (FOCUS) DWI for predicting axillary lymph node status in early-stage breast cancer

Background

This study aims to estimate the amount of axillary lymph node (ALN) involvement in early-stage breast cancer utilizing a field of view (FOV) optimized and constrained undistorted single-shot (FOCUS) diffusion-weighted imaging (DWI) approach, as well as a whole-lesion histogram analysis.

Methods

This retrospective analysis involved 81 individuals with invasive breast cancer. The patients were divided into three groups: N0 (negative ALN metastasis), N1–2 (low metastatic burden with 1–2 ALNs), and N≥3 (heavy metastatic burden with ≥ 3 ALNs) based on their sentinel lymph node biopsy (SLNB) or axillary lymph node dissection (ALND). Histogram parameters of apparent diffusion coefficient (ADC) depending basically on FOCUS DWI were performed using 3D-Slicer software for whole lesions. The typical histogram characteristics for N0, N1–2, and N≥ 3 were compared to identify the significantly different parameters. To determine the diagnostic efficacy of significantly different factors, the area under their receiver operating characteristic (ROC) curves was examined.

Results

There were significant differences in the energy, maximum, 90 percentile, range, and lesion size among N0, N1–2, and N≥ 3 groups (P < 0.05). The energy differed significantly between N0 and N1–2 groups (P < 0.05), and some certain ADC histogram parameters and lesion sizes differed significantly between N0 and N≥3, or N1–2 and N≥3 groups. For ROC analysis, the energy yielded the best diagnostic performance in distinguishing N0 and N1–2 groups from N≥3 group with an AUC value of0.853. All parameters revealed excellent inter-observer agreement with inter-reader consistencies data ranging from0.919 to 0.982.

Conclusion

By employing FOCUS DWI method, the analysis of whole-lesion ADC histogram quantitatively provides a non-invasive way to evaluate the degree of ALN metastatic spread in early-stage breast cancer.

Nomogram models for stratified prediction of axillary lymph node metastasis in breast cancer patients (cN0)

Objectives

To determine the predictors of axillary lymph node metastasis (ALNM), two nomogram models were constructed to accurately predict the status of axillary lymph nodes (ALNs), mainly high nodal tumour burden (HNTB, > 2 positive lymph nodes), low nodal tumour burden (LNTB, 1-2 positive lymph nodes) and negative ALNM (N0). Accordingly, more appropriate treatment strategies for breast cancer patients without clinical ALNM (cN0) could be selected.

Methods

From 2010 to 2015, a total of 6314 patients with invasive breast cancer (cN0) were diagnosed in the Surveillance, Epidemiology, and End Results (SEER) database and randomly assigned to the training and internal validation groups at a ratio of 3:1. As the external validation group, data from 503 breast cancer patients (cN0) who underwent axillary lymph node dissection (ALND) at the Second Affiliated Hospital of Chongqing Medical University between January 2011 and December 2020 were collected. The predictive factors determined by univariate and multivariate logistic regression analyses were used to construct the nomograms. Receiver operating characteristic (ROC) curves and calibration plots were used to assess the prediction models' discrimination and calibration.

Results

Univariate analysis and multivariate logistic regression analyses showed that tumour size, primary site, molecular subtype and grade were independent predictors of both ALNM and HNTB. Moreover, histologic type and age were independent predictors of ALNM and HNTB, respectively. Integrating these independent predictors, two nomograms were successfully developed to accurately predict the status of ALN. For nomogram 1 (prediction of ALNM), the areas under the receiver operating characteristic (ROC) curve in the training, internal validation and external validation groups were 0.715, 0.688 and 0.876, respectively. For nomogram 2 (prediction of HNTB), the areas under the ROC curve in the training, internal validation and external validation groups were 0.842, 0.823 and 0.862. The above results showed a satisfactory performance.

Conclusion

We established two nomogram models to predict the status of ALNs (N0, 1-2 positive ALNs or >2 positive ALNs) for breast cancer patients (cN0). They were well verified in further internal and external groups. The nomograms can help doctors make more accurate treatment plans, and avoid unnecessary surgical trauma.

Photothermally responsive theranostic nanocomposites for near-infrared light triggered drug release and enhanced synergism of photothermo-chemotherapy for gastric cancer

Near-infrared (NIR) photothermal therapy plays a critical role in the cancer treatment and diagnosis as a promising carcinoma treatment modalities nowadays. However, development of clinical application has been greatly limited due to the inefficient drug release and low tumor accumulation. Herein, we designed a NIR-light triggered indocyanine green (ICG)-based PCL core/P(MEO₂MA-b-HMAM) shell nanocomposites (PPH@ICG) and evaluated their therapeutic effects in vitro and in vivo. The anticancer drug 5-fluorouracil (5Fu) and the photothermal agent ICG were loaded into a thermo-sensitive micelle (PPH@5Fu@ICG) by self-assembly. The nanoparticles formed were characterized using transmission electron microscopy, dynamic light scattering, and fluorescence spectra. The thermo-sensitive copolymer (PPH@5Fu@ICG) showed a great temperature-controlled drug release response with lower critical solution temperature. In vitro cellular uptake and TEM imaging proved that PPH@5Fu@ICG nanoparticles can home into the lysosomal compartments under NIR. Moreover, in gastric tumor-bearing nude mice, PPH@5Fu@ICG + NIR group exhibited excellent improvement in antitumor efficacy based on the NIR-triggered thermo-chemotherapy synergy, both in vitro and in vivo. In summary, the proposed strategy of synergistic photo-hyperthermia chemotherapy effectively reduced the 5Fu dose, toxic or side effect, which could serve as a secure and efficient approach for cancer theranostics.

Prevalence of Pathologic N2/N3 Disease in Postmenopausal Women with Clinical N0 ER+/HER2- Breast Cancer

BACKGROUND

The RxPONDER trial demonstrated that the 21-gene recurrence score can be used to guide adjuvant systemic therapy decisions in postmenopausal women with pN1 ER+/HER2- breast cancer. As such, a sentinel lymph node biopsy (SLNB) may not provide systemic treatment-altering information for many patients, and omission of SLNB in patients with low probability of pN2/N3 disease could be considered.

METHODS

Postmenopausal women (aged ≥ 50 years) diagnosed with cN0cM0, ER+/HER- breast cancer from 2013 to 2017 were identified in the National Cancer Database. The primary outcome was the prevalence of pN2/N3 disease.

RESULTS

Of 325,692 postmenopausal women with cN0 ER+/HER2- breast cancer, 7106 (2.2%) were pN2/N3. In total, 81.7% had cT1 tumors, 16.8% T2, 1.3% T3, and 0.2% T4. In patients with T1 tumors, the prevalence of pN2/N3 disease was 1.2% compared with 17.2% in patients with T3/T4 tumors. In multivariable models, cT stage was the strongest predictor of pN2/N3 disease (adjusted odds ratio [aOR] 14.9 [12.1-18.4]). Lobular histology (aOR 2.4 [2.3-2.6]), higher grade (aOR 2.9 [2.6-3.1]), and young age (aOR 1.5 [1.3-1.7]) were also associated with increased prevalence of pN2/N3. We created a model using histology, grade, and T stage that stratifies patients with low prevalence of pN2/3 disease (< 1%) and those at high risk (> 20%).

CONCLUSIONS

In postmenopausal women with cN0 ER+/HER2- breast cancer, the prevalence of pN2/N3 disease is low, indicating a potential opportunity to use the results of RxPONDER to extend criteria to omit SLNB. Prospective study is needed to determine safety, including risk of nodal recurrence, of omission of SLNB in carefully selected patients.

Internal mammary lymph node metastasis in breast cancer patients based on anatomical imaging and functional imaging

Internal mammary lymph node (IMLN) metastasis forms part of the clinical node classification for primary breast cancer, which influences the treatment strategy. However, because of the IMLNs' complicated anatomical structures and relationships with adjacent structures, IMLN biopsy or resection is associated with a limited improvement in prognosis and a high complication rate. The positivity rate also varies broadly according to imaging modality, and there is a low rate of agreement between the imaging and pathological diagnoses, which creates imprecision in the preoperative staging. The IMLN positivity rate also varies remarkably, and there are no clear, accurate, and non-invasive modalities for diagnosing the pre-mastectomy IMLN status. Nevertheless, medical imaging modalities continue to evolve, with functional imaging and image-guided thoracoscopic biopsy of sentinel IMLNs being well established. Thus, personalized decision-making and treatment selection should be based on the modality-specific differences in the diagnosis of IMLN metastasis/recurrence and the patient's specific risk factors.

The NILS Study Protocol: A Retrospective Validation Study of an Artificial Neural Network Based Preoperative Decision-Making Tool for Noninvasive Lymph Node Staging in Women with Primary Breast Cancer (ISRCTN14341750)

Newly diagnosed breast cancer (BC) patients with clinical T1–T2 N0 disease undergo sentinel-lymph-node (SLN) biopsy, although most of them have a benign SLN. The pilot noninvasive lymph node staging (NILS) artificial neural network (ANN) model to predict nodal status was published in 2019, showing the potential to identify patients with a low risk of SLN metastasis. The aim of this study is to assess the performance measures of the model after a web-based implementation for the prediction of a healthy SLN in clinically N0 BC patients. This retrospective study was designed to validate the NILS prediction model for SLN status using preoperatively available clinicopathological and radiological data. The model results in an estimated probability of a healthy SLN for each study participant. Our primary endpoint is to report on the performance of the NILS prediction model to distinguish between healthy and metastatic SLNs (N0 vs. N+) and compare the observed and predicted event rates of benign SLNs. After validation, the prediction model may assist medical professionals and BC patients in shared decision making on omitting SLN biopsies in patients predicted to be node-negative by the NILS model. This study was prospectively registered in the ISRCTN registry (identification number: 14341750).

Low RUFY3 expression level is associated with lymph node metastasis in older women with invasive breast cancer

PURPOSE

Sentinel lymph node biopsy is omitted in older women (≥ 70 years old) with clinical lymph node (LN)-negative hormone receptor-positive breast cancer as it does not influence adjuvant treatment decision-making. However, older women are heterogeneous in frailty while the chance of recurrence increase with improving longevity. Therefore, a biomarker that identifies LN metastasis may facilitate treatment decision-making. RUFY3 is associated with cancer progression. We evaluated RUFY3 expression level as a biomarker for LN-positive breast cancer in older women.

METHODS

Clinical and transcriptomic data of breast cancer patients were obtained from the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC, n = 1903) and The Cancer Genome Atlas (TCGA, n = 1046) Pan-cancer study cohorts.

RESULTS

A total of 510 (METABRIC) and 211 (TCGA) older women were identified. LN-positive breast cancer, which represented 51.4% (METABRIC) and 48.4% (TCGA), demonstrated worse disease-free, disease-specific, and overall survival. RUFY3 levels were significantly lower in LN-positive tumors regardless of age. The area under the curve for the receiver operator characteristic (AUC-ROC) curves showed RUFY3-predicted LN metastasis. Low RUFY3 enriched oxidative phosphorylation, DNA repair, MYC targets, unfolded protein response, and mtorc1 signaling gene sets, was associated with T helper type 1 cell infiltration, and with intratumor heterogeneity and fraction altered. Low RUFY3 expression was associated with LN-positive breast cancer and with worse disease-specific survival among older women.

CONCLUSION

Older women with breast cancers who had low expression level of RUFY3 were more frequently diagnosed with LN-positive tumors, which translated into worse prognosis.