Vision Transformers-Based Transfer Learning for Breast Mass Classification From Multiple Diagnostic Modalities
- Authors
- Ayana, Gelan; Choe, Se-woon
- Issue Date
- Jul-2024
- Publisher
- SPRINGER SINGAPORE PTE LTD
- Keywords
- Vision Transformer; Transfer Learning; Breast Mass; Ultrasound; Mammography
- Citation
- JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY, v.19, no.5, pp 3391 - 3410
- Pages
- 20
- Journal Title
- JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY
- Volume
- 19
- Number
- 5
- Start Page
- 3391
- End Page
- 3410
- URI
- https://scholarworks.bwise.kr/kumoh/handle/2020.sw.kumoh/28606
- DOI
- 10.1007/s42835-024-01904-w
- ISSN
- 1975-0102
2093-7423
- Abstract
- Breast mass evaluation is crucial for early breast cancer diagnosis via imaging. While Convolutional Neural Network (CNN)-based deep learning (DL) has enhanced this process, it suffers from computational complexity and limited spatial encoding. Vision Transformer (ViT)-based DL, more adept at encoding spatial information, presents a promising alternative. This study introduces a ViT-based transfer learning (TL) method for breast mass classification. Three ViT-based TL architectures pretrained on ImageNet were proposed and evaluated using ultrasound and mammogram datasets. Comparative analysis against ViT trained from scratch and CNN-based TL was conducted. Results showed the ViT-based TL method achieving the highest area under curve (AUC) of 1 +/- 0 for both datasets, outperforming ViT from scratch and yielding similar or better performance compared to CNN-based TL. Despite its computational cost, ViT-based TL demonstrates superior classification capabilities for breast mass images. This research provides a foundational framework for future studies exploring ViT-based TL in breast cancer diagnosis.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Department of Medical IT Convergence Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.