Breast cancer diagnosis using machine learning model
T.S. Arthi, N. Partheeban, Bhoomika Singh, Aparajitha Singh, Nikhil Tripathi · Computational Methods in Science and Technology · 2024
Early and accurate detection of breast cancer, particularly Invasive Ductal Carcinoma (IDC), is critical for improving patient outcomes. Traditional diagnostic methods like histopathology and mammography have limitations in terms of time, cost, and potential subjectivity. This study proposes a lightweight Machine Learning (ML) model for IDC classification using digital whole-mount breast cancer slide images. The model aims to achieve high accuracy while being suitable for deployment in resource- constrained environments. We evaluate our model on a publicly available breast histopathology dataset and compare its performance with other Deep Learning (DL) models, focusing on both accuracy and computational efficiency. The results demonstrate that our model achieves a high classification accuracy (around 89.3 percent) with minimal processing power and memory requirements. Furthermore, successful deployment on a Raspberry Pi embedded system validates its potential for real-world application in resource-limited settings, potentially leading to improved breast cancer diagnosis accessibility. Index Terms—Bi-directional Long Short-Term Memory (BiLSTM), Convolutional Neural Network (CNN), Deep Learning (DL), Invasive Ductal Carcinoma (IDC), Multilayer Perceptron (MLP), Raspberry Pi, Tiny Machine Learning (TinyML).