Vision Transformers-Based Transfer Learning for Breast Mass Classification From Multiple Diagnostic Modalities

被引:1
作者
Ayana, Gelan [1 ,2 ]
Choe, Se-woon [1 ,3 ]
机构
[1] Kumoh Natl Inst Technol, Dept Med IT Convergence Engn, Gumi 39253, South Korea
[2] Jimma Univ, Sch Biomed Engn, Jimma 378, Ethiopia
[3] Kumoh Natl Inst Technol, Dept IT Convergence Engn, Gumi 39253, South Korea
基金
新加坡国家研究基金会;
关键词
Vision Transformer; Transfer Learning; Breast Mass; Ultrasound; Mammography; CANCER; MAMMOGRAMS;
D O I
10.1007/s42835-024-01904-w
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
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.
引用
收藏
页码:3391 / 3410
页数:20
相关论文
共 46 条
[1]   Deep Learning to Distinguish Recalled but Benign Mammography Images in Breast Cancer Screening [J].
Aboutalib, Sarah S. ;
Mohamed, Aly A. ;
Berg, Wendie A. ;
Zuley, Margarita L. ;
Sumkin, Jules H. ;
Wu, Shandong .
CLINICAL CANCER RESEARCH, 2018, 24 (23) :5902-5909
[2]   Classification of Mammogram Images Using Multiscale all Convolutional Neural Network (MA-CNN) [J].
Agnes, S. Akila ;
Anitha, J. ;
Pandian, S. Immanuel Alex ;
Peter, J. Dinesh .
JOURNAL OF MEDICAL SYSTEMS, 2020, 44 (01)
[3]   Dataset of breast ultrasound images [J].
Al-Dhabyani, Walid ;
Gomaa, Mohammed ;
Khaled, Hussien ;
Fahmy, Aly .
DATA IN BRIEF, 2020, 28
[4]   Vision-Transformer-Based Transfer Learning for Mammogram Classification [J].
Ayana, Gelan ;
Dese, Kokeb ;
Dereje, Yisak ;
Kebede, Yonas ;
Barki, Hika ;
Amdissa, Dechassa ;
Husen, Nahimiya ;
Mulugeta, Fikadu ;
Habtamu, Bontu ;
Choe, Se-Woon .
DIAGNOSTICS, 2023, 13 (02)
[5]   BUViTNet: Breast Ultrasound Detection via Vision Transformers [J].
Ayana, Gelan ;
Choe, Se-Woon .
DIAGNOSTICS, 2022, 12 (11)
[6]   Ultrasound-Responsive Nanocarriers for Breast Cancer Chemotherapy [J].
Ayana, Gelan ;
Ryu, Jaemyung ;
Choe, Se-woon .
MICROMACHINES, 2022, 13 (09)
[7]   De-Speckling Breast Cancer Ultrasound Images Using a Rotationally Invariant Block Matching Based Non-Local Means (RIBM-NLM) Method [J].
Ayana, Gelan ;
Dese, Kokeb ;
Raj, Hakkins ;
Krishnamoorthy, Janarthanan ;
Kwa, Timothy .
DIAGNOSTICS, 2022, 12 (04)
[8]   Patchless Multi-Stage Transfer Learning for Improved Mammographic Breast Mass Classification [J].
Ayana, Gelan ;
Park, Jinhyung ;
Choe, Se-woon .
CANCERS, 2022, 14 (05)
[9]   A Novel Multistage Transfer Learning for Ultrasound Breast Cancer Image Classification [J].
Ayana, Gelan ;
Park, Jinhyung ;
Jeong, Jin-Woo ;
Choe, Se-woon .
DIAGNOSTICS, 2022, 12 (01)
[10]   Transfer Learning in Breast Cancer Diagnoses via Ultrasound Imaging [J].
Ayana, Gelan ;
Dese, Kokeb ;
Choe, Se-woon .
CANCERS, 2021, 13 (04) :1-16