
Research Article
PCA-DNN: A Novel Deep Neural Network Oriented System for Breast Cancer Classification
@ARTICLE{10.4108/eetpht.9.3533, author={Pooja Rani and Rajneesh Kumar and Anurag Jain and Rohit Lamba and Ravi Kumar Sachdeva and Tanupriya Choudhury}, title={PCA-DNN: A Novel Deep Neural Network Oriented System for Breast Cancer Classification}, journal={EAI Endorsed Transactions on Pervasive Health and Technology}, volume={9}, number={1}, publisher={EAI}, journal_a={PHAT}, year={2023}, month={10}, keywords={Breast Cancer, Principal Component Analysis, Support Vector Machine, Naive Bayes, Random Forest, Adaptive Boosting}, doi={10.4108/eetpht.9.3533} }
- Pooja Rani
Rajneesh Kumar
Anurag Jain
Rohit Lamba
Ravi Kumar Sachdeva
Tanupriya Choudhury
Year: 2023
PCA-DNN: A Novel Deep Neural Network Oriented System for Breast Cancer Classification
PHAT
EAI
DOI: 10.4108/eetpht.9.3533
Abstract
INTRODUCTION: The number of women diagnosed with breast cancer has risen rapidly in recent years all around the world, and this trend is anticipated to continue. After lung cancer, it is the second most common cause of death worldwide, and majority of women are diagnosed with it in their lives. In the healthcare sector, accurate breast cancer classification has become a challenging task. Breast cancer is a malignant tumor found in the breast tissue that occurs due to abnormal cell proliferation inside the breast. OBJECTIVES: This article proposes a principal component analysis deep neural network (PCA-DNN) for breast cancer classification. METHODS: PCA-DNN is developed by using features extracted through Principal component analysis (PCA) with deep neural network (DNN).In addition to PCA-DNN, conventional DNN and machine learning classifiers including support vector machine (SVM), naive bayes (NB), random forest (RF), and adaptive boosting (AdaBoost) are used to perform classification. Wisconsin Diagnostic Breast Cancer (WDBC) dataset available on the University of California, Irvine (UCI) is used to perform experiments. RESULTS: PCA-DNN provided 98.83% of accuracy and 10.36% of loss. The value of area under receiver operating characteristic curve (AUROC) is equal to 99.3%. CONCLUSION: Results provided by PCA-DNN are better than conventional DNN and traditional machine learning classifiers. Compared to conventional DNN, it offered accuracy improvements of 3.68% and loss reductions of 29.37%.
Copyright © 2023 P. Rani et al., licensed to EAI. This open-access article is distributed under the terms of the Creative Commons Attribution License, which permits unlimited use, distribution and reproduction in any medium as long as the original work is properly cited.