Dense breast tissue is a significant factor that increases the risk of breast cancer. Current mammographic density classification approaches are unable to provide enough classification accuracy. However, it remains a difficult problem to classify breast density. This paper proposes TwoViewDensityNet, an end-to-end deep learning-based method for mammographic breast density classification. The craniocaudal (CC) and mediolateral oblique (MLO) views of screening mammography provide two different views of each breast. As the two views are complementary, and dual-view-based methods have proven efficient, we use two views for breast classification. The loss function plays a key role in training a deep model; we employ the focal loss function because it focuses on learning hard cases. The method was thoroughly evaluated on two public datasets using 5-fold cross-validation, and it achieved an overall performance (F-score of 98.63%, AUC of 99.51%, accuracy of 95.83%) on DDSM and (F-score of 97.14%, AUC of 97.44%, accuracy of 96%) on the INbreast. The comparison shows that the TwoViewDensityNet outperforms the state-of-the-art methods for classifying breast density into BI-RADS class. It aids healthcare providers in providing patients with more accurate information and will help improve the diagnostic accuracy and reliability of mammographic breast density evaluation in clinical care.
Background/Objectives: Breast cancer is the most commonly diagnosed cancer among women in Saudi Arabia, yet evidence on younger women remains limited. This study aimed to characterize the clinicopathological, molecular, and treatment features of women diagnosed at age ≤ 40 years and to explore differences between women aged ≤ 35 and 36–40 years. Methods: We conducted a retrospective study of 135 women aged 22–40 years diagnosed with breast cancer at King Saud University Medical City, Riyadh. Variable-specific available-case denominators were used without imputation. Characteristics were summarized descriptively, and age groups were compared using Pearson’s chi-square or exact tests, as appropriate. Results: A breast mass was the most frequent presentation (79.3%), and invasive ductal carcinoma was the predominant diagnosis (80.7%). Tumors > 2 to ≤5 cm accounted for 48.9% of cases; axillary involvement was documented in 47.4%, distant metastasis in 16.7%, and grade 3 disease in 68.2% of patients with documented grade. Luminal B (31.5%) and triple-negative (29.2%) were the most frequently documented molecular subtypes. No statistically significant differences were detected between the age groups in clinical presentation, tumor-size category, axillary involvement, distant metastasis, histological grade, documented molecular subtype, or treatment characteristics. Conclusions: Symptomatic presentation and potentially unfavorable pathological features were common in this tertiary-center cohort. The absence of statistically significant clinicopathological, molecular, or treatment differences between age groups does not establish clinical equivalence and should be interpreted cautiously given the exploratory design and modest sample size. The findings highlight the need for standardized staging, hereditary-risk assessment, and multicenter longitudinal data to inform care for younger women with breast cancer.