Evaluating Deep Learning Models for Breast Cancer Classification: A Comparative Study

TL;DR

This paper compares eight deep learning models for breast cancer image classification, finding that Vision Transformer (ViT) outperforms CNNs with a 94% accuracy, highlighting the potential for improved clinical diagnosis.

Contribution

It provides a comprehensive comparison of multiple deep learning architectures, including transformers, for breast cancer histopathological image classification.

Findings

ViT achieved 94% validation accuracy.

Transformers outperform traditional CNNs in this task.

Deep learning models can enhance clinical breast cancer diagnosis.

Abstract

This study evaluates the effectiveness of deep learning models in classifying histopathological images for early and accurate detection of breast cancer. Eight advanced models, including ResNet-50, DenseNet-121, ResNeXt-50, Vision Transformer (ViT), GoogLeNet (Inception v3), EfficientNet, MobileNet, and SqueezeNet, were compared using a dataset of 277,524 image patches. The Vision Transformer (ViT) model, with its attention-based mechanisms, achieved the highest validation accuracy of 94%, outperforming conventional CNNs. The study demonstrates the potential of advanced machine learning methods to enhance precision and efficiency in breast cancer diagnosis in clinical settings.