Breast Cancer Detection Using Convolutional Neural Networks: A Deep Learning-Based Approach

Abstract

Breast cancer remains one of the leading causes of mortality among women, particularly in low- and middle-income countries, where limited healthcare access and delayed diagnosis contribute to poor outcomes. Deep learning, especially convolutional neural networks (CNNs), has shown remarkable efficacy in breast cancer detection through automated image analysis, reducing reliance on manual interpretation. This study provides a comprehensive review of recent advancements in CNN-based breast cancer detection, evaluating deep learning architectures, feature extraction techniques, and optimization strategies. A comparative analysis of CNNs, recurrent neural networks (RNNs), and hybrid models highlights their strengths, limitations, and applicability in medical image classification. Using a dataset of 569 instances with 33 tumor morphology features, various deep learning architectures - including CNNs, long short-term memory networks (LSTMs), and multilayer perceptrons (MLPs) - were implemented, achieving classification accuracies between 89% and 98%. The study underscores the significance of data augmentation, transfer learning, and feature selection in improving model performance. Hybrid CNN-based models demonstrated superior predictive accuracy by capturing spatial and sequential dependencies within tumor feature sets. The findings support the potential of AI-driven breast cancer detection in clinical applications, reducing diagnostic errors and improving early detection rates. Future research should explore transformer-based models, federated learning, and explainable AI techniques to enhance interpretability, robustness, and generalization across diverse datasets.

Keywords: breast cancer detection; convolutional neural networks (cnns); data augmentation; deep learning; explainable ai (xai); federated learning; hybrid models; machine learning; medical image classification; transfer learning.

Figure 1. X-ray image of the breast and its cancer type

Source: Reference [32]

Figure 2. Dataset division across different classes

"M" denotes malignant tumors and "B" denotes benign tumors.

Figure 3. Heatmap showing feature correlations within the dataset

Figure 4. Representation of tumor morphology

Figure 5. Confusion matrix

Figure 6. Distribution of key features by diagnosis

Figure 7. Accuracy versus epochs graph

CNN: convolutional neural network; RNN: recurrent neural network; LSTM: long short-term memory network; MLP: multilayer perceptron

Figure 8. Comparison of model accuracy

CNN: convolutional neural network; RNN: recurrent neural network; LSTM: long short-term memory network; MLP: multilayer perceptron