A Combined PCA-MLP Network for Early Breast Cancer Detection

TL;DR

This paper proposes a combined PCA-MLP network for early breast cancer detection, achieving high accuracy and demonstrating the effectiveness of integrated machine learning techniques in improving diagnostic performance.

Contribution

The study introduces a novel 4-layer PCA-MLP network that outperforms other algorithms in early breast cancer detection, with superior accuracy on the BCCD dataset.

Findings

Achieved 100% accuracy on the BCCD dataset

Mean accuracy of 90.48% across multiple runs

Demonstrated the viability of PCA-MLP for early diagnosis

Abstract

Breast cancer is the second most responsible for all cancer types and has been the cause of numerous deaths over the years, especially among women. Any improvisation of the existing diagnosis system for the detection of cancer can contribute to minimizing the death ratio. Moreover, cancer detection at an early stage has recently been a prime research area in the scientific community to enhance the survival rate. Proper choice of machine learning tools can ensure early-stage prognosis with high accuracy. In this paper, we have studied different machine learning algorithms to detect whether a patient is likely to face breast cancer or not. Due to the implicit behavior of early-stage features, we have implemented a multilayer perception model with the integration of PCA and suggested it to be more viable than other detection algorithms. Our 4 layers MLP-PCA network has obtained the best accuracy of 100% with a mean of 90.48% accuracy on the BCCD dataset.