METHODS: Breast cancer MRI images were classified into BA, BF, BPT, BTA, MDC, MLC, MMC, and MPC using a proposed Deep Learning model with additional 5 fine-tuned Deep learning models consisting of Xception, InceptionV3, VGG16, MobileNet and ResNet50 trained on ImageNet database. The dataset was collected from Kaggle depository for breast cancer detection and classification. That Dataset was boosted using GAN technique. The images in the dataset have 4 magnifications (40X, 100X, 200X, 400X, and Complete Dataset). Thus we evaluated the proposed Deep Learning model and 5 pre-trained models using each dataset individually. That means we carried out a total of 30 experiments. The measurement that was used in the evaluation of all models includes: F1-score, recall, precision, accuracy.
RESULTS: The classification F1-score accuracies of Xception, InceptionV3, ResNet50, VGG16, MobileNet, and Proposed Model (BCCNN) were 97.54%, 95.33%, 98.14%, 97.67%, 93.98%, and 98.28%, respectively.
CONCLUSION: Dataset Boosting, preprocessing and balancing played a good role in enhancing the detection and classification of breast cancer of the proposed model (BCCNN) and the fine-tuned pre-trained models' accuracies greatly. The best accuracies were attained when the 400X magnification of the MRI images due to their high images resolution.
METHODS: mRNA was extracted from 44 fibroadenomas and 36 giant fibroadenomas, and transcriptomic profiling was performed to identify up- and down-regulated genes in the giant fibroadenomas as compared to the fibroadenomas.
RESULTS: A total of 40 genes were significantly up-regulated and 18 genes were significantly down-regulated in the giant fibroadenomas as compared to the fibroadenomas of the breast. The top 5 up-regulated genes were FN1, IL3, CDC6, FGF8 and BMP8A. The top 5 down-regulated genes were TNR, CDKN2A, COL5A1, THBS4 and BMPR1B. The differentially expressed genes (DEGs) were found to be associated with 5 major canonical pathways involved in cell growth (PI3K-AKT, cell cycle regulation, WNT, and RAS signalling) and immune response (JAK-STAT signalling). Further analyses using 3 supervised learning algorithms identified an 8-gene signature (FN1, CDC6, IL23A, CCNA1, MCM4, FLT1, FGF22 and COL5A1) that could distinguish giant fibroadenomas from fibroadenomas with high predictive accuracy.
CONCLUSION: Our findings demonstrated that the giant fibroadenomas are biologically distinct to fibroadenomas of the breast with overexpression of genes involved in the regulation of cell growth and immune response.
PRESENTATION OF CASE: A 19-year-old lady presented with a bleeding, fungating breast mass worsened with topical herbal concoction. Examination revealed a 10 × 15 cm fungating breast mass that obliterated her nipple- areolar complex (NAC). Computed Tomography (CT) scan reported a huge heterogeneously enhancing mass 10.6 × 14.5 × 15.1 cm with loss of normal fat plane with the overlying skin but a clear fat plane with the pectoralis muscle posteriorly.
DISCUSSION: Giant breast masses that fungate and ulcerate usually indicate a sinister pathology. Traditional remedies have been reported to exacerbate growth. In cases where most of the breast parenchyma and NAC has been destroyed, it is no longer possible to proceed with breast conserving techniques. Breast reconstruction is crucial in adolescents and should be tailored to the patient's existing breast size as well as body habitus.
CONCLUSION: In juvenile giant fibroadenomas where breast parenchyma and NAC has been destroyed, breast reconstruction is the goal. The lack of consensus in both diagnosis and management further compounds the difficulty in dealing with this sensitive population. Awareness needs to be raised regarding negative effects related to traditional medicine.