Computerized evaluation scheme to detect metastasis in sentinel lymph nodes using contrast-enhanced computed tomography before breast cancer surgery

Application of Machine Learning Algorithm in Predicting Axillary Lymph Node Metastasis from Breast Cancer on Preoperative Chest CT

Axillary lymph node (ALN) status is one of the most critical prognostic factors in patients with breast cancer. However, ALN evaluation with contrast-enhanced CT (CECT) has been challenging. Machine learning (ML) is known to show excellent performance in image recognition tasks. The purpose of our study was to evaluate the performance of the ML algorithm for predicting ALN metastasis by combining preoperative CECT features of both ALN and primary tumor. This was a retrospective single-institutional study of a total of 266 patients with breast cancer who underwent preoperative chest CECT. Random forest (RF), extreme gradient boosting (XGBoost), and neural network (NN) algorithms were used. Statistical analysis and recursive feature elimination (RFE) were adopted as feature selection for ML. The best ML-based ALN prediction model for breast cancer was NN with RFE, which achieved an AUROC of 0.76 ± 0.11 and an accuracy of 0.74 ± 0.12. By comparing NN with RFE model performance with and without ALN features from CECT, NN with RFE model with ALN features showed better performance at all performance evaluations, which indicated the effect of ALN features. Through our study, we were able to demonstrate that the ML algorithm could effectively predict the final diagnosis of ALN metastases from CECT images of the primary tumor and ALN. This suggests that ML has the potential to differentiate between benign and malignant ALNs.

Comparative observation of common tracers in sentinel lymph node biopsy of breast cancer and a study on simplifying its surgical procedure

Background

Many breast cancer patients have avoided axillary lymph node dissection after sentinel lymph node biopsy (SLNB). During the SLNB operation, the color of lymphatic vessels is sometimes poor and so finding them is difficult. This study observed the tracing effects of three tracer combinations and also reported our experience in simplifying the SLNB program.

Methods

In total, 123 breast cancer patients whose TNM stage was cT1-2N0M0 were retrospectively studied. According to the tracer used, the patients were divided into the carbon nanoparticle (CNP) group (38 cases), CNP combined with methylene blue (CNP + MB) group (41 cases), and indocyanine green combined with MB (ICG + MB) group (44 cases). All 123 breast cancer cases were also classified into the non-tracking group (53 cases) and tracking group (70 cases) according to the SLNB operation process. The non-tracking group looked for the stained sentinel lymph nodes directly, while the tracking group looked for the stained lymph nodes along the lymphatic vessels.

Results

The SLN identification rates in the CNP, CNP + MB, and ICG + MB groups were 97.4%, 97.6%, and 95.5% respectively (P > 0.05). The average number of SLNs detected was 4.92 ± 2.06, 5.12 ± 2.18, and 4.57 ± 1.90, respectively (P > 0.05). The ideal display rates of lymphatic vessels in the three groups were 86.8%, 87.8%, and 93.2%, respectively (P > 0.05). The SLN identification rates in the non-tracking and tracking groups were 96.2% and 97.1%, respectively (P > 0.05). The average number of SLNs detected were 5.73 ± 1.76 and 5.70 ± 1.93, respectively (P > 0.05), and the average operation time was 16.47 ± 5.78 and 27.53 ± 7.75 min, respectively (P < 0.05).

Conclusion

This is the first study to observe the application effect of CNP combined with MB and ICG combined with MB tracers in SLNB of breast cancer patients. No significant difference was observed among the patients in SLN identification and lymphatic vessel display. Omitting the step of searching for lymphatic vessels in SLNB surgery does not reduce the surgical effect, but the reduced operating steps can reduce the surgical time and theoretically reduce postoperative complications.

Study on Sentinel Lymph Node and Its Lymphatic Drainage Pattern of Breast Cancer by Contrast-Enhanced Ultrasound

OBJECTIVES

Sentinel lymph node (SLN) and its lymphatic drainage pattern (LDP) of breast cancer were studied by contrast-enhanced ultrasound (CEUS).

METHODS

From July 2017 to December 2019, patients with SLN localization of breast cancer in Sichuan Academy of Medical Sciences·Sichuan Provincial People's Hospital were selected. The sentinel lymph system of breast cancer was observed by CEUS before both operation and blue staining in the surgery. The location, number, and route of sentinel lymphatic channel (SLC) were recorded, along with the number, size, and the depth from skin of SLN. LDPs were summarized according to these basic characteristics of SLC and SLN.

RESULTS

A total of 368 cases were included; 465 SLCs and 423 SLNs were detected. Most of the SLCs were originated from the outer upper quadrant of areola. Eleven LDPs were found, including 31 subtypes of LDPs. There were 6 cases of type A (1.63%), 15 cases of type B (4.08%), 223 cases of type C (57.88%), 38 cases of type D (10.33%), 2 cases of type E (0.54%), 3 cases of type F (0.82%), 50 cases of type G (13.59%), 30 cases of type H (8.15%), 2 cases of type I (0.54%), 6 cases of type J (1.63%), and 3 cases of type K (0.82%).

CONCLUSIONS

The most common LDP of breast cancer was one SLC originated from the upper quadrant of areola with one SLN. CEUS can identify the LDP before surgery to reduce the false negative rate of SLN biopsy.

Advanced diagnostic imaging of sentinel lymph node in early stage breast cancer

Sentinel lymph node biopsy has been regarded as the standard procedure for early staging breast cancer. One of the key steps is to locate the sentinel lymph node (SLN). The recommended method is the joint use of blue dye and radioisotope. However, due to radionuclide radiation and high cost, it is urgent to develop more convenient and sensitive imaging methods to accurately locate SLN. This article discusses the advancement of accurately locating SLN by isotope tracer imaging, magnetic tracer method, computed tomographic lymphography, and trans-lymphatic contrast-enhanced ultrasound, as well as proposing new propose for clinical diagnosis.

Imaging features of sentinel lymph node mapped by multidetector-row computed tomography lymphography in predicting axillary lymph node metastasis

INTRODUCTION

Accurately assessing axillary lymph node (ALN) status in breast cancer is vital for clinical decision making and prognosis. The purpose of this study was to evaluate the predictive value of sentinel lymph node (SLN) mapped by multidetector-row computed tomography lymphography (MDCT-LG) for ALN metastasis in breast cancer patients.

METHODS

112 patients with breast cancer who underwent preoperative MDCT-LG examination were included in the study. Long-axis diameter, short-axis diameter, ratio of long-/short-axis and cortical thickness were measured. Logistic regression analysis was performed to evaluate independent predictors associated with ALN metastasis. The prediction of ALN metastasis was determined with related variables of SLN using receiver operating characteristic (ROC) curve analysis.

RESULTS

Among the 112 cases, 35 (30.8%) cases had ALN metastasis. The cortical thickness in metastatic ALN group was significantly thicker than that in non-metastatic ALN group (4.0 ± 1.2 mm vs. 2.4 ± 0.7 mm, P < 0.001). Multi-logistic regression analysis indicated that cortical thickness of > 3.3 mm (OR 24.53, 95% CI 6.58-91.48, P < 0.001) had higher risk for ALN metastasis. The best sensitivity, specificity, negative predictive value(NPV) and AUC of MDCT-LG for ALN metastasis prediction based on the single variable of cortical thickness were 76.2%, 88.5%, 90.2% and 0.872 (95% CI 0.773-0.939, P < 0.001), respectively.

CONCLUSION

ALN status can be predicted using the imaging features of SLN which was mapped on MDCT-LG in breast cancer patients. Besides, it may be helpful to select true negative lymph nodes in patients with early breast cancer, and SLN biopsy can be avoided in clinically and radiographically negative axilla.

Prediction of Metastasis in the Axillary Lymph Nodes of Patients With Breast Cancer: A Radiomics Method Based on Contrast-Enhanced Computed Tomography

Background

The use of traditional techniques to evaluate breast cancer is restricted by the subjective nature of assessment, variation across radiologists, and limited data. Radiomics may predict axillary lymph node metastasis (ALNM) of breast cancer more accurately.

Purpose

The aim was to evaluate the diagnostic performance of a radiomics model based on ALNs themselves that used contrast-enhanced computed tomography (CECT) to detect ALNM of breast cancer.

Methods

We retrospectively enrolled 402 patients with breast cancer confirmed by pathology from January 2016 to October 2019. Three hundred and ninety-six features were extracted for all patients from axial CECT images of 825 ALNs using Artificial Intelligent Kit software (GE Medical Systems, Version V3.1.0.R). Next, the radiomics model was trained, validated, and tested for predicting ALNM in breast cancer by using a support vector machine algorithm. Finally, the performance of the radiomics model was evaluated in terms of its classification accuracy and the value of the area under the curve (AUC).

Results

The radiomics model yielded the best classification accuracy of 89.1% and the highest AUC of 0.92 (95% CI: 0.91-0.93, p=0.002) for discriminating ALNM in breast cancer in the validation cohorts. In the testing cohorts, the model also demonstrated better performance, with an accuracy of 88.5% and an AUC of 0.94 (95% CI: 0.93-0.95, p=0.005) for predicting ALNM in breast cancer.

Conclusion

The radiomics model based on CECT images can be used to predict ALNM in breast cancer and has significant potential in clinical noninvasive diagnosis and in the prediction of breast cancer metastasis.

Application of preoperative computed tomographic lymphography for precise sentinel lymph node biopsy in breast cancer patients

Background

In light of the extensive application of sentinel lymph node biopsy (SLNB) in clinically node-negative breast cancer patients and the recently investigated failure of SLNB after lumpectomy, it has become important to explore methods for preoperative mapping of sentinel lymph nodes (SLNs) and their lymphatics to direct precise SLNB and improve the identification rate of SLNs.

Methods

Twenty-seven patients with suspected breast cancer based on the results of the clinical examination and imaging were enrolled in the study. Computed tomographic lymphography (CTLG) followed by CT three-dimensional reconstruction was performed to determine the localization of SLNs and lymphatics on the body surface preoperatively. Intraoperatively combined staining with methylene blue and indocyanine green was used to evaluate the accuracy and feasibility of CTLG.

Results

SLNs and lymphatics from the breast were identified using CTLG in all patients, and preoperative SLNs and lymphatics localization on the body surface showed a significant role in the selection of operative incision and injection points. The accuracy rate of SLN and lymphatic detection by CTLG was 92.6% compared with intraoperatively combined staining. Moreover, preoperative CTLG performed well in SLN number detection, and the accuracy rate was 95.2%.

Conclusion

We evaluate the procedure and application of preoperative CTLG in the superficial localization of SLNs and lymphatics, which may lead to a decreased incidence of cutting off the lymphatics of SLNs and consequently more rapid and accurate SLN detection. This method promotes personalized SLN mapping, providing detailed information about the number and anatomical location of SLNs and lymphatics for adequate surgical planning for breast cancer patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12893-021-01190-7.

Combined 68Ga-NOTA-Evans Blue Lymphoscintigraphy and 68Ga-NOTA-RM26 PET/CT Evaluation of Sentinel Lymph Node Metastasis in Breast Cancer Patients

In this study, we applied a new strategy to identify sentinel lymph node (SLN) metastasis by combining ⁶⁸Ga-NOTA-Evans Blue (⁶⁸Ga-NEB) for SLN mapping and ⁶⁸Ga-NOTA-RM26 for LN metastasis detection in breast cancer patients. A total of 24 female patients with breast cancer diagnosed by core biopsy or suspected by mammography or ultrasonography were recruited and provided informed consent. All patients underwent ⁶⁸Ga-NEB and ⁶⁸Ga-NOTA-RM26 PET/CT imaging. Visual analysis of ⁶⁸Ga-NEB PET/CT images was used to determine SLNs, and then compared with the ⁶⁸Ga-NOTA-RM26 results and histopathological findings. SLNs were visualized in 24 of 24 patients (100.0%) within 4.0-10.0 (5.6 ± 1.4) min. All patients were pathologically diagnosed with breast cancer, and 12 patients had ipsilateral lymph node metastasis. By combining ⁶⁸Ga-NEB and ⁶⁸Ga-NOTA-RM26 images, 7/12 (58.3%) patients showed mild to intense uptake of ⁶⁸Ga-NOTA-RM26 in SLNs, 1/12 patient (8.3%) had moderate uptake of ⁶⁸Ga-NOTA-RM26 in the non-SLNs rather than SLN, indicating possible bypass lymphatic drainage, partially accounting for the false negatives in SLN biopsy during surgery. No false positives were found. The SUV_max of ⁶⁸Ga-NOTA-RM26 activity in metastatic SLNs was significantly higher than that in non-metastatic SLNs (2.2 ± 2.3 vs 0.7 ± 0.1, P = 0.047). This study manifests the value of combination of ⁶⁸Ga-NEB and ⁶⁸Ga-NOTA-RM26 dual tracer PET/CT in preoperative evaluation of SLN metastasis in breast cancer patients, especially in those patients with lymphatic obstruction and bypass drainage. In general, positive ⁶⁸Ga-NOTA-RM26 uptake in either SLN or other lymph nodes can apply lymph node dissection rather than intraoperative SLN biopsy.