Application of Deep Learning Method in Facilitating the Detection of Breast Cancer

• Published in: IOP conference series. Materials Science and Engineering 2020-05, Vol.864 (1), p.12079
• Main Authors: Samah, Azurah A, Nasien, Dewi, Hashim, Haslina, Sahar, Julia, Abdul Majid, Hairudin, Yusoff, Yusliza, Ali Shah, Zuraini
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial neural networks; Breast cancer; Classification; Datasets; Deep learning; Machine learning; Neural networks
• ISSN: 1757-8981; 1757-899X
• DOI: 10.1088/1757-899X/864/1/012079

Breast cancer is a type of tumour that could be treated if the disease is identified at an earlier stage. Early diagnosis is crucial when it comes to reducing the mortality rate. In this study, deep neural network method is applied to facilitate the detection of breast cancer. The aim of this study is to implement deep neural network in breast cancer classification models that can produce high classification accuracy. Deep Neural Network (DNN) with multiple hidden layers was applied to learn deep features of the breast cancer data. Dataset used in this study was obtained from the UCI Machine Learning Repository which consists of Wisconsin Breast Cancer Dataset (WBCD) and used for the original and diagnostic dataset. The performance of the proposed DNN method was compared against previous machine learning classifier in terms of accuracy. From the results, the accuracy obtained for the original dataset was 97.14% and 97.66% for the diagnostic dataset, which is better than previous SVM method.