Breast cancer: One-stage automated detection, segmentation, and classification of digital mammograms using UNet model based-semantic segmentation

Breast cancer is one of the most common cancers in women. It is known as asymptomatic cancer that presents no noticeable symptoms in its early stage. Thus, regular mammography screening helps detect breast cancer early before it spreads to nearby normal tissues or to other organs. Hence, an automated system for early detection of breast cancer in mammograms will assist radiologists in their diagnosis. The rapid advance of deep learning models has considerably arisen much interest in their application to medical imaging problems, particularly for breast cancer diagnosis. In this paper, we propose an end-to-end UNet model for the detection, segmentation, and classification of breast masses in one-stage. The proposed model is evaluated in terms of its performance in segmenting and classifying breast masses using the publicly available datasets, DDSM and INbreast. The mass segmentation and classification evaluation results give an intersection over union (IOU) score of 90.50% and an area under the curve of 99.88% for both DDSM and INbreast datasets. The proposed model scores a dice coefficient of 99.20% and 99.56% and a weighted F1-score of 99.19% and 99.65% for the DDSM and INbreast datasets, respectively. The results show that the proposed model outperforms the existing methodologies.