Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of early deaths. The data presented in this article reviews the medical images of breast cancer using ultrasound scan. Breast Ultrasound Dataset is categorized into three classes: normal, benign, and malignant images. Breast ultrasound images can produce great results in classification, detection, and segmentation of breast cancer when combined with machine learning.

Breast classification and detection using ultrasound imaging is considered a significant step in computer-aided diagnosis systems. Over the previous decades, researchers have proved the opportunities to automate the initial tumor classification and detection. The shortage of popular datasets of ultrasound images of breast cancer prevents researchers from obtaining a good performance of the classification algorithms. Traditional augmentation approaches are firmly limited, especially in tasks where the images follow strict standards, as in the case of medical datasets. Therefore besides the traditional augmentation, we use a new methodology for data augmentation using Generative Adversarial Network (GAN). We achieved higher accuracies by integrating traditional with GAN-based augmentation. This paper uses two breast ultrasound image datasets obtained from two various ultrasound systems. The first dataset is our dataset which was collected from Baheya Hospital for Early Detection and Treatment of Women's Cancer, Cairo (Egypt), we name it (BUSI) referring to Breast Ultrasound Images (BUSI) dataset. It contains 780 images (133 normal, 437 benign and 210 malignant). While the Dataset (B) is obtained from related work and it has 163 images (110 benign and 53 malignant). To overcome the shortage of public datasets in this field, BUSI dataset will be publicly available for researchers. Moreover, in this paper, deep learning approaches are proposed to be used for breast ultrasound classification. We examine two different methods: a Convolutional Neural Network (CNN) approach and a Transfer Learning (TL) approach and we compare their performance with and without augmentation. The results confirm an overall enhancement using augmentation methods with deep learning classification methods (especially transfer learning) when evaluated on the two datasets.

No abstract

Objective: To evaluate the clinical performance of contrast-enhanced spectral mammography (CESM) on asymmetries detected on a mammogram (MG). Methods: This study was approved by the Scientific Research Review Board of the Radiology Department, and waiver of informed consent was applied for the uses of data of the included cases. The study included 125 female patients,33 (26.4%) who presented for screening and 92 (73.6%) who presented for a diagnostic MG. All had breast asymmetries on MG. Ultrasound examination and CESM using dual-energy acquisitions were performed for all patients. Results: In all, 88/125 (70.4%) females had focal asymmetry (seen in two views and occupying less than a quadrant), 26/125 (20.8%) had global asymmetry (occupying more than one quadrant), 10/125 (8%) had asymmetry (seen in a single view and occupying less than a quadrant), and 1/125 had developing asymmetry (0.8%) (not present in the previous MG). Malignant lesions represented 91 cases, benign lesions represented 30 cases, and 4 cases were high-risk lesions. CESM sensitivity was 100% (v s 97.8 % for sono-mammography), specificity was 55.88% (v s 81.8% for sono-mammography), and the positive- and negative-predictive values were 85.85 and 100% (v s 93.7 and 93% for sono-mammography respectively) . Conclusion: In our study, we conclude that focal and global asymmetries with other suspicious mammographic findings were statistically significant for malignancy and CESM played an important role in delineating tumor size and extension. Any non-enhancing asymmetrical density correlated with a benign pathology, if not associated with other suspicious imaging findings. Advances in knowledge:  Our study is the first to explore the added value of CESM to asymmetries detected in screening and diagnostic mammography.

No abstract