Management and results of treatment of breast cancer patients having sentinel lymph node micrometastases

Analysis of false reasons based on the artificial intelligence RRCART model to identify frozen sections of lymph nodes in breast cancer

BACKGROUND

Breast cancer is the most common malignant tumor in the world. Intraoperative frozen section of sentinel lymph nodes is an important basis for determining whether axillary lymph node dissection is required for breast cancer surgery. We propose an RRCART model based on a deep-learning network to identify metastases in 2362 frozen sections and count the wrongly identified sections and the associated reasons. The purpose is to summarize the factors that affect the accuracy of the artificial intelligence model and propose corresponding solutions.

METHODS

We took the pathological diagnosis of senior pathologists as the gold standard and identified errors. The pathologists and artificial intelligence engineers jointly read the images and heatmaps to determine the locations of the identified errors on sections, and the pathologists found the reasons (false reasons) for the errors. Through NVivo 12 Plus, qualitative analysis of word frequency analysis and nodal analysis was performed on the error reasons, and the top-down error reason framework of "artificial intelligence RRCART model to identify frozen sections of breast cancer lymph nodes" was constructed based on the importance of false reasons.

RESULTS

There were 101 incorrectly identified sections in 2362 slides, including 42 false negatives and 59 false positives. Through NVivo 12 Plus software, the error causes were node-coded, and finally, 2 parent nodes (high-frequency error, low-frequency error) and 5 child nodes (section quality, normal lymph node structure, secondary reaction of lymph nodes, micrometastasis, and special growth pattern of tumor) were obtained; among them, the error of highest frequency was that caused by normal lymph node structure, with a total of 45 cases (44.55%), followed by micrometastasis, which occurred in 30 cases (29.70%).

CONCLUSIONS

The causes of identification errors in examination of sentinel lymph node frozen sections by artificial intelligence are, in descending order of influence, normal lymph node structure, micrometastases, section quality, special tumor growth patterns and secondary lymph node reactions. In this study, by constructing an artificial intelligence model to identify the error causes of frozen sections of lymph nodes in breast cancer and by analyzing the model in detail, we found that poor quality of slices was the preproblem of many identification errors, which can lead to other errors, such as unclear recognition of lymph node structure by computer. Therefore, we believe that the process of artificial intelligence pathological diagnosis should be optimized, and the quality control of the pathological sections included in the artificial intelligence reading should be carried out first to exclude the influence of poor section quality on the computer model. For cases of micrometastasis, we suggest that by differentiating slices into high- and low-confidence groups, low-confidence micrometastatic slices can be separated for manual identification. The normal lymph node structure can be improved by adding samples and training the model in a targeted manner.

Clinical relevance of a degree of extracapsular extension in a sentinel lymph node in breast cancer patients: a single-centre study

In some breast cancer (BC) patients, an examination of lymph nodes dissected during sentinel lymph node biopsy (SLNB) demonstrates a presence of metastatic lesions and extracapsular extension (ECE) in a SLN. This study aimed to evaluate clinical relevance of ECE in BC patients. This is a retrospective analysis of 891 patients with cancer metastases to SLN, referred to supplementary axillary lymph node dissection (ALND), hospitalized between Jan 2007 and Dec 2017. Clinical and epidemiological data was evaluated. Long-term treatment outcomes were analysed. In 433 (48.6%) patients, cancer metastases were limited to the SLN (group I), in 61 (6.8%) patients the SLN capsule was exceeded focally (≤ 1 mm—group II). In 397 (44.6%) patients, a more extensive ECE was found (> 1 mm—group III). Metastases to non-sentinel lymph nodes (nSLNs) were diagnosed in 27.0% patients from group I, 44.3% patients from group II and in 49.6% patients from group III. No statistically significant differences were observed in long-term treatment outcomes for compared groups. The presence of ECE is accompanied by a higher stage of metastatic lesions in the lymphatic system. The differences in this respect were statistically significant, when compared to the group of ECE(−) patients. ECE, regardless of its extent, did not impact the long-term treatment results. ECE remains an indication for supplementary ALND and for other equivalent cancer treatment procedures, regardless of ECE size.

Does the presence of sentinel lymph node macrometastases in breast cancer patients require axillary lymph node dissection?-Single-center analysis

According to the current guidelines on treatment of breast cancer patients, identification of metastases in the sentinel lymph node (SLN (+)) is not an absolute indication for necessary axillary lymph node dissection (ALND). In our study, we present long-term outcomes of treatment among SLN(+) patients referred for conservative treatment, for example, no further ALND. A total of 3145 breast cancer patients subjected to sentinel lymph node biopsy (SLNB) between November 2008 and June 2015. SLN metastases were identified in 719 patients (22.9%). Locoregional recurrences and distant metastases as endpoints were distinquished. The mean follow-up time for patients after ALND was 36.2 months (6-74 months); 18.8 months (6-38 months) for patients with SLN macrometastases without ALND; and 34.0 months (6-74 months) for patients with micrometastases. Adjuvant ALND was performed in 626 of SLN(+) patients. Conservative treatment was applied in the remaining 93 cases. Among SLN(+) patients without adjuvant ALND, there was one case of recurrence (1.07%). In the group of patients without SLN, metastases recurrence was noted in 32 patients (1.32%). Among SLN(+) patients diagnosed with macrometastases, recurrence concerned 2.01% of analyzed cases (all subjected to ALND). Lack of radical surgical treatment in SLN(+) breast cancer patients did not lead to worsening long-term outcomes. In the occurrence of macrometastases to the sentinel lymph node, abandoning completion axillary lymph node dissection might be a reasonable option. However, it would require continuation of current research, preferably involving a clinical trial.

Application of artificial neural networks for predicting presence of non-sentinel lymph node metastases in breast cancer patients with positive sentinel lymph node biopsies

INTRODUCTION

The aim of this study was to present a new predictive tool for non-sentinel lymph node (nSLN) metastases.

MATERIAL AND METHODS

One thousand five hundred eighty-three patients with early-stage breast cancer were subjected to sentinel lymph node biopsy (SLNB) between 2004 and 2012. Metastatic SLNs were found in 348 patients - the retrospective group. Selective axillary lymph node dissection (ALND) was performed in 94% of cases. Involvement of the nSLNs was identified in 32.1% of patients following ALND. The correlation between nSLN involvement and selected epidemiological data, primary tumor features and details of the diagnostic and therapeutic management was examined in metastatic SLN group. Multivariate analysis was performed using an artificial neural network to create a new nomogram. The new test was validated using the overall study population consisting of the prospective group (365 patients - SLNB between 01-07.2013).

RESULTS

Accuracy of the new test was calculated using area under the receiver operating characteristics curve (AUC). We obtained AUC coefficient equal to 0.87 (95% confidence interval: 0.81-0.92). Sensitivity amounted to 69%, specificity to 86%, accuracy - 80% (retrospective group) and 77%, 46%, 66% (validation group), respectively. The Memorial Sloan-Kettering Cancer Center (MSKCC) nomogram the calculated AUC value was 0.71, for Stanford - 0.68, for Tenon - 0.67.

CONCLUSIONS

In the analyzed group only the MSKCC nomogram and the new model showed AUC values exceeding the expected level of 0.70. Our nomogram performs well in prospective validation on patient series. The overall assessment of clinical usefulness of this test will be possible after testing it on different patient populations.