Deep Learning Approaches for Data Augmentation and Classification of Breast Masses using Ultrasound Images
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2019, Vol 10, Issue 5
Abstract
Breast classification and detection using ultrasound imaging is considered a significant step in computer-aided diagno-sis 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.
Authors and Affiliations
Walid Al-Dhabyani, Mohammed Gomaa, Hussien Khaled, Aly Fahmy
Keywords
Related Articles
- EP ID EP579248
- DOI 10.14569/IJACSA.2019.0100579
- Views 114
- Downloads 0
Divide and Conquer Approach for Solving Security and Usability Conflict in User Authentication
Knowledge based authentication schemes are divided into textual password schemes and graphical password schemes. Textual password schemes are easy to use but have well known security issues, such as weak against online s...
An Efficient Scheme for MANET Domain Formation (ESMDF)
Mobile Ad hoc Network (MANET) has random topology as MANET devices leaving or joining to the network at anytime. The dynamic nature of MANETs makes achieving secrecy, connectivity and high performance, a big challenge an...
Data Synchronization Model for Heterogeneous Mobile Databases and Server-side Database
Mobile devices, because they can be used to access corporate information anytime anywhere, have recently received considerable attention, and several research efforts have been tailored towards addressing data synchroniz...
A High-Performing Similarity Measure for Categorical Dataset with SF-Tree Clustering Algorithm
Tasks such as clustering and classification assume the existence of a similarity measure to assess the similarity (or dissimilarity) of a pair of observations or clusters. The key difference between most clustering metho...
Estimating Evapotranspiration using Machine Learning Techniques
The measurement of evapotranspiration is the most important factor in irrigation scheduling. Evapotranspiration means loss of water from the surface of plant and soil. Evaporation parameters are being used in studying wa...