Quantifying the Mitigating Effects of Whole-Breast Radiotherapy and Systemic Treatments on Regional Recurrence Incidence Among Breast Cancer Patients

Predicting HER2 Status in Breast Cancer on Ultrasound Images Using Deep Learning Method

Purpose

The expression of human epidermal growth factor receptor 2 (HER2) in breast cancer is critical in the treatment with targeted therapy. A 3-block-DenseNet-based deep learning model was developed to predict the expression of HER2 in breast cancer by ultrasound images.

Methods

The data from 144 breast cancer patients with preoperative ultrasound images and clinical information were retrospectively collected from the Shandong Province Tumor Hospital. An end-to-end 3-block-DenseNet deep learning classifier was built to predict the expression of human epidermal growth factor receptor 2 by ultrasound images. The patients were randomly divided into a training (n = 108) and a validation set (n = 36).

Results

Our proposed deep learning model achieved an encouraging predictive performance in the training set (accuracy = 85.79%, AUC = 0.87) and the validation set (accuracy = 80.56%, AUC = 0.84). The effectiveness of our model significantly exceeded the clinical model and the radiomics model. The score of the proposed model showed significant differences between HER2-positive and -negative expression (p < 0.001).

Conclusions

These results demonstrate that ultrasound images are predictive of HER2 expression through a deep learning classifier. Our method provides a non-invasive, simple, and feasible method for the prediction of HER2 expression without the manual delineation of the regions of interest (ROI). The performance of our deep learning model significantly exceeded the traditional texture analysis based on the radiomics model.

Identifying Risk Factors for Regional Recurrence in Early-Stage Breast Cancer with pT1-2 and Negative Sentinel Lymph Node Biopsy

Background

Due to the low rate of regional recurrence (RR) in early-stage breast cancer with pT1-2 and negative sentinel lymph node biopsy (SLNB), no regional therapy is suggested for them. However, whether there is a subset of patients who were with high risk of regional failure and may benefit from regional treatment is still unknown. The current study was designed to identify the patients with high risk of RR, thereby providing clues for enhanced regional therapy.

Methods

We analyzed a total of 1124 breast cancer patients with pT1-2N0 from May 2004 to Dec 2014. All the patients were treated with breast-conservation surgery (BCS) and adjuvant whole-breast radiotherapy. The regional recurrence-free survival (RRFS), local regional recurrence-free survival (LRRFS), disease-free survival (DFS) and overall survival (OS) were assessed by using the Kaplan–Meier method. Cox proportional hazards regression was performed to detect factors in predicting the RRFS.

Results

In multivariable analysis, both T stage and molecular type were significant predictors of RRFS. Patients with T2 stage had a lower RRFS than those with T1stage. Triple-negative patients were more likely to suffer regional failure than the patients with other molecular types. The two predictors were then employed to divide all the patients into three groups based on the risk level of RR. Patients with both T2 and triple-negative molecular type had the lower RRFS, LRRFS, DFS and OS than the patients with one or no risk factor.

Conclusion

For early-stage breast cancer patients with negative SLNB, those who were with both T2 stage and triple-negative molecular type had a high rate of RR and enhance regional therapy may be needed for them.

mu-Opioid Receptor Polymorphisms and Breast Cancer Recurrence in Adult Korean Women Undergoing Breast Cancer Surgery: A Retrospective Study

Background: Genetic variations of mu-opioid receptors are well known to contribute to growth and progression of tumors. The most common single-nucleotide polymorphism (SNP) in the mu-opioid receptor 1 gene (OPRM1) is the A118G mutation. We examined the association between the recurrent breast cancer and genotypes of OPRM1 A118G SNP (AA vs. AG vs. GG) in Korean women population. Methods: We analysed medical records and genetic data of 200 patients aged more than 20 who underwent primary breast cancer surgery from June 2012 to June 2014 and diagnosed recurrent breast cancer from June 2012 to September 2019. Results: The incidence of recurrent breast cancer was 6.1%, 8.2%, and 4.8% in genotype AA, AG and GG, respectively (p=0.780). The incidence of recurrent breast cancer in volatile anaesthesia group was 7.0% and 7.1% in total intravenous anaesthesia (TIVA) group (RR = 0.984, 95% CI = 0.328 - 2.951; p = 0.978). Conclusion: OPRM1 A118G SNP had no influence on breast cancer recurrence in Korean women. Anaesthesia technique did not show significant effect on the incidence of recurrent breast cancer.