Breast Cancer Detection Based on Deep Learning Technique
Authors:
- 1 August 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 89-92
Abstract
Breast cancer is the most common cancer among Malaysian women and roughly one in 19 women at risk of breast cancer in Malaysia. The number of breast cancer cases is steadily growing especially with increasing number of ageing population. The screening practice using mammography needs to be better and potentially efficient. There is always room for advancement when it comes to medical imaging. Early detection of cancer can reduce the risk of deaths for cancer patients. The objective of this paper is to compare the breast cancer detection with two model networks of deep learning technique. The overall process involves image preprocessing, classification and performance evaluation. In this paper, we evaluate the performance of deep learning model network which are VGG16 and ResNet50 to classify between normal tumor and abnormal tumor using IRMA dataset. The result show that VGG16 produces the better result with 94% compared to ResNet50 with 91.7% in term of accuracy.Keywords
This publication has 8 references indexed in Scilit:
- An image-based segmentation recommender using crowdsourcing and transfer learning for skin lesion extractionExpert Systems with Applications, 2019
- Density-wise two stage mammogram classification using texture exploiting descriptorsExpert Systems with Applications, 2018
- Artificial intelligence for breast cancer screening: Opportunity or hype?The Breast, 2017
- Breast cancer epidemic in the early twenty-first century: evaluation of risk factors, cumulative questionnaires and recommendations for preventive measuresTumor Biology, 2016
- Breast mass classification in digital mammography based on extreme learning machineNeurocomputing, 2016
- Automated Mass Detection in Mammograms Using Cascaded Deep Learning and Random Forests2015
- A new ensemble of features for breast cancer diagnosis2015
- Breast Cancer Detected with Screening US: Reasons for Nondetection at MammographyRadiology, 2014