Changes in breast cancer staging trends among Egyptian women after COVID-19: A retrospective single-center study.

OBJECTIVES: Since being declared a global pandemic, the SARS-CoV-2 virus had a significant impact on the entire globe. The pandemic has placed a heavy burden on healthcare systems worldwide, and cancer patients are particularly prone. Despite the fact that initial international reports suggest delays in breast cancer (BC) diagnosis and screening programs, the Egyptian context requires additional research on this topic. To examine whether COVID-19 has changed the pattern of disease presentation before and after the pandemic, focusing on the tumor, node, and metastasis (TNM) staging of the disease at the initial presentation. METHODS: This single-center, retrospective study of female BC patients initially diagnosed at Baheya Foundation was conducted during the following time frames: from Jan 2019 to Jan 2020 (Pre COVID-19 cohort) and from Mar 2020 to Mar 2021 (post-COVID-19 cohort). We compared the two cohorts in terms of clinical characteristics, tumor characteristics, and the number of days from presentation to treatment. Our primary endpoint was the difference in the TNM stage of BC at the initial presentation. RESULTS: This analysis included 710 BC patients, 350 from the pre-COVID cohort and 360 from the post-COVID group. We detected a 27.9% increase in late-stage BC (stages III-IV) in the post-pandemic cohort compared to the pre-pandemic (60.1% vs. 47%, p < 0.001). The time from diagnosis to commencement of treatment was significantly longer (28.34 ± 18.845 vs 36.04 ± 23.641 days, p < 0.001) in the post-COVID cohort (mean difference = 7.702, 95% CI 4.54-10.85, p < 0.001). A higher percentage of patients in the post-pandemic cohort received systemic neoadjuvant therapy (p-value for Exact's test for all treatment options = 0.001). CONCLUSIONS: The number of patients requiring systemic neoadjuvant chemotherapy increased dramatically in the post-pandemic group with advanced stages of BC at presentation. This study highlights the need for proper management of cancer patients during any future pandemic.

Spatiotemporal Mammography-based Deep Learning Model for Improved Breast Cancer Risk Prediction.

Breast cancer is one of the most prevalent cancers among women. It is the second leading cause of death in cancer-related deaths. Early detection and personalized risk assessment can reduce the mortality rate and improve survival rates. Classical risk prediction models which rely on traditional risk factors produce inconsistent results among the different populations. Thus, they are not routinely used in screening programs. Deep learning was proven to improve the results of breast cancer risk prediction. CNNs can detect risk cues from screening mammograms. However, the deep learning models utilize the spatial information of each screening mammogram independently. This study aims to further improve the risk prediction models by exploiting the spatiotemporal information in multiple screening time points. We implemented a Siamese neural network for spatiotemporal risk prediction and compared the results against CNN trained using two different time points (T1 and T2) independently. We tested our results on 191 cases, 61 of which were diagnosed with cancer. The Siamese model showed a superior AUC of 0.81 against 0.75 and 0.77 at T1 and T2 respectively. The Siamese network also exhibited higher accuracy and F1-score with values of 0.78 and 0.61 while CNNs have the same accuracy of 0.76 with an F1-score of 0.54 at T1, and 0.59 at T2. The results suggest that spatiotemporal risk prediction can be a more reliable risk assessment tool.

Bilateral Analysis Boosts the Performance of Mammography-based Deep Learning Models in Breast Cancer Risk Prediction.

Breast cancer is one of the leading causes of death among women. Early prediction of breast cancer can significantly improve the survival rates. Breast density was proven as a reliable risk factor. Deep learning models can learn subtle cues in the mammogram images. CNN models were recently shown to improve the risk discrimination in full-field mammograms. This study aims to improve risk prediction models using bilateral analysis. Bilateral analysis is the process of comparing two breasts to verify presence of anomalies. We developed a Siamese neural network to leverage the bilateral information and asymmetries between the two mammograms of the same patient. We tested our model on 271 patients and compared the results of our Siamese model against the traditional unilateral CNN model. Our results showed AUCs of 0.75 and 0.70 respectively (p = 0.0056). The Siamese model also exhibits higher sensitivity, specificity, precision, and false positive rate with values of 0.68, 0.69, 0.71, 0.31 respectively. While the CNN values were 0.61, 0.66, 0.67, 0.34 respectively. We merged both models by two techniques using pre-trained weights and weighted voting ensemble. The merging technique boosted the AUC to 0.78. The results suggest that bilateral analysis can significantly improve the risk discrimination.

Body mass index, breast density, and the risk of breast cancer development in relation to the menopausal status; results from a population-based screening program in a native African-Arab country.

Background: Risk factors are traits or behaviors that have an influence on the development of breast cancer (BC). Awareness of the prevalent risk factors can guide in developing prevention interventions. Purpose: To evaluate the correlation between the breast density, body mass index, and the risk of breast cancer development in relation to the menopausal status in a native African-Arab population. Material and methods: The study included 30,443 screened females who were classified into cancer and non-cancer groups and each group was further sub-classified into pre- and postmenopausal groups. The breast density (BD) was reported and subjectively classified according to the 2013 ACR BI-RADS breast density classification. The weight and height were measured, and the body mass index (BMI) was calculated and classified according to the WHO BMI classification. Results: A statistically significant difference was calculated between the mean BMI in the cancer and non-cancer groups (p: .027) as well as between the pre- and postmenopausal groups (p < .001). A positive statistically insignificant correlation was calculated between the breast density and the risk of breast cancer in the premenopausal group (OR: 1.062, p: .919) and a negative highly significant correlation was calculated in the postmenopausal group (OR: 0.234, p < .001). Conclusion: BMI and BD are inversely associated with each other. The current studied population presented unique ethnic characteristics, where a decreased BD and an increased BMI were found to be independent risk factors for developing breast cancer.