Fine-tuned Transformer Models for Breast Cancer Detection and Classification

TL;DR

The paper investigates transformer-based vision models for breast cancer detection in mammography, evaluating Swin Tiny, DeiT, BEiT, ViT, and YOLOv8 on a dataset augmented to enhance robustness. ViT achieves the best performance with an accuracy around 99.3%, indicating strong capability to capture global patterns and subtle features in breast images, while DeiT also performs well and YOLOv8 underperforms due to optimization challenges. The study acknowledges limitations related to dataset diversity and computational demands, and proposes future work on multi-modal data, lightweight models, and clinical validation. Overall, the work demonstrates the crystal potential of vision transformers to improve AI-assisted breast cancer detection and informs directions for practical adoption and further research.

Abstract

Breast cancer is still the second top cause of cancer deaths worldwide and this emphasizes the importance of necessary steps for early detection. Traditional diagnostic methods, such as mammography, ultrasound, and thermography, which have limitations when it comes to catching subtle patterns and reducing false positives. New technologies like artificial intelligence (AI) and deep learning have brought about the revolution in medical imaging analysis. Nevertheless, typical architectures such as Convolutional Neural Networks (CNNs) often have problems with modeling long-range dependencies. It explores the application of visual transformer models (here: Swin Tiny, DeiT, BEiT, ViT, and YOLOv8) for breast cancer detection through a collection of mammographic image sets. The ViT model reached the highest accuracy of 99.32% which showed its superiority in detecting global patterns as well as subtle image features. Data augmenting approaches, such as resizing croppings, flippings, and normalization, were further applied to the model for achieving higher performance. Although there were interesting results, the issues of dataset diversity and model optimization which present new avenues of research are also still present. Through this study, the crystal potential of transformer-based AI models in changing the detecting process of breast cancer and, thus, to patients health, is suggested.

Figures (4)

• Figure 1: Architecture of the proposed system design.
• Figure 2: After analyzing images from both cancerous and non-cancerous cases
• Figure 3: Comparison of Training and Validation Loss with Accuracy Across Different Models.
• Figure 4: Confusion Matrix for Breast Cancer Detection Using ViT.