A deep fusion-based vision transformer for breast cancer classification

被引:1
作者
Fiaz, Ahsan [1 ]
Raza, Basit [1 ]
Faheem, Muhammad [2 ]
Raza, Aadil [3 ]
机构
[1] COMSATS Univ Islamabad CUI, Dept Comp Sci, Islamabad, Pakistan
[2] Univ Vaasa, Sch Technol & Innovat, Vaasa 65200, Finland
[3] COMSATS Univ Islamabad CUI, Dept Phys, Islamabad, Pakistan
关键词
artificial intelligence; breast cancer; classification; deep learning; histopathology images; machine learning;
D O I
10.1049/htl2.12093
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Breast cancer is one of the most common causes of death in women in the modern world. Cancerous tissue detection in histopathological images relies on complex features related to tissue structure and staining properties. Convolutional neural network (CNN) models like ResNet50, Inception-V1, and VGG-16, while useful in many applications, cannot capture the patterns of cell layers and staining properties. Most previous approaches, such as stain normalization and instance-based vision transformers, either miss important features or do not process the whole image effectively. Therefore, a deep fusion-based vision Transformer model (DFViT) that combines CNNs and transformers for better feature extraction is proposed. DFViT captures local and global patterns more effectively by fusing RGB and stain-normalized images. Trained and tested on several datasets, such as BreakHis, breast cancer histology (BACH), and UCSC cancer genomics (UC), the results demonstrate outstanding accuracy, F1 score, precision, and recall, setting a new milestone in histopathological image analysis for diagnosing breast cancer.
引用
收藏
页码:471 / 484
页数:14
相关论文
共 50 条
[21]   Classification of Breast Cancer Subtypes Using Deep Learning Methods [J].
Izmirlioglu, Ergun ;
Atas, Ahmet Enes ;
Bilgin, Gokhan .
32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU 2024, 2024,
[22]   Deep Learning Model Based Breast Cancer Histopathological Image Classification [J].
Wei, Benzheng ;
Han, Zhongyi ;
He, Xueying ;
Yin, Yilong .
2017 2ND IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND BIG DATA ANALYSIS (ICCCBDA 2017), 2017, :348-353
[23]   Deep feature fusion-based stacked denoising autoencoder for tag recommendation systems [J].
Fei, Zhengshun ;
Wang, Jinglong ;
Liu, Kangling ;
Attahi, Eric ;
Huang, Bingqiang .
IET CYBER-SYSTEMS AND ROBOTICS, 2023, 5 (03)
[24]   Enhanced nuclear information fusion and visual transformer for pathological breast cancer image classification [J].
Zhang, Qinyi ;
Gao, Honglei ;
Li, Wenhao ;
Xu, Zhipeng ;
Ouyang, Ting ;
Gu, Zongyun .
SCIENTIFIC REPORTS, 2025, 15 (01)
[25]   Breast Cancer Histological Image Classification Using Fine-Tuned Deep Network Fusion [J].
Mahbod, Amirreza ;
Ellinger, Isabella ;
Ecker, Rupert ;
Smedby, Orjan ;
Wang, Chunliang .
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2018), 2018, 10882 :754-762
[26]   Transformer-based Deep Neural Network for Breast Cancer Classification on Digital Breast Tomosynthesis Images [J].
Lee, Weonsuk ;
Lee, Hyeonsoo ;
Lee, Hyunjae ;
Park, Eun Kyung ;
Nam, Hyeonseob ;
Kooi, Thijs .
RADIOLOGY-ARTIFICIAL INTELLIGENCE, 2023, 5 (03)
[27]   The effects of fusion-based feature extraction for fabric defect classification [J].
Ciklacandir, Fatma Gunseli Yasar ;
Utku, Semih ;
Ozdemir, Hakan .
TEXTILE RESEARCH JOURNAL, 2023, 93 (23-24) :5448-5460
[28]   MSF-Model: Multi-Scale Feature Fusion-Based Domain Adaptive Model for Breast Cancer Classification of Histopathology Images [J].
Khan, Hameed Ullah ;
Raza, Basit ;
Waheed, Abdul ;
Shah, Habib .
IEEE ACCESS, 2022, 10 :122530-122547
[29]   Breast Cancer Classification Through Transfer Learning with Vision Transformer, PCA, and Machine Learning Models [J].
Gutierrez-Cardenas, Juan .
INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (04) :1027-1036
[30]   RI-ViT: A Multi-Scale Hybrid Method Based on Vision Transformer for Breast Cancer Detection in Histopathological Images [J].
Monjezi, Ehsan ;
Akbarizadeh, Gholamreza ;
Ansari-Asl, Karim .
IEEE ACCESS, 2024, 12 :186074-186086