casa 24(1):

Research Article

UGGNet: Bridging U-Net and VGG for Advanced Breast Cancer Diagnosis

Download36 downloads
  • @ARTICLE{10.4108/eetcasa.v10i1.4681,
        author={Tran Cao Minh and Nguyen Kim Quoc and Phan Cong Vinh and Dang Nhu Phu and Vuong Xuan Chi and Ha Minh Tan},
        title={UGGNet: Bridging U-Net and VGG for Advanced Breast Cancer Diagnosis},
        journal={EAI Endorsed Transactions on Contex-aware Systems and Applications},
        volume={10},
        number={1},
        publisher={EAI},
        journal_a={CASA},
        year={2024},
        month={1},
        keywords={Breast Cancer, Classification, Deep Learning, Segmentation, Ultrasonic Image},
        doi={10.4108/eetcasa.v10i1.4681}
    }
    
  • Tran Cao Minh
    Nguyen Kim Quoc
    Phan Cong Vinh
    Dang Nhu Phu
    Vuong Xuan Chi
    Ha Minh Tan
    Year: 2024
    UGGNet: Bridging U-Net and VGG for Advanced Breast Cancer Diagnosis
    CASA
    EAI
    DOI: 10.4108/eetcasa.v10i1.4681
Tran Cao Minh1, Nguyen Kim Quoc1, Phan Cong Vinh1, Dang Nhu Phu1, Vuong Xuan Chi1, Ha Minh Tan1,*
  • 1: Trường ĐH Nguyễn Tất Thành
*Contact email: hmtan@ntt.edu.vn

Abstract

In the field of medical imaging, breast ultrasound has emerged as a crucial diagnostic tool for early detection of breast cancer. However, the accuracy of diagnosing the location of the affected area and the extent of the disease depends on the experience of the physician. In this paper, we propose a novel model called UGGNet, combining the power of the U-Net and VGG architectures to enhance the performance of breast ultrasound image analysis. The U-Net component of the model helps accurately segment the lesions, while the VGG component utilizes deep convolutional layers to extract features. The fusion of these two architectures in UGGNet aims to optimize both segmentation and feature representation, providing a comprehensive solution for accurate diagnosis in breast ultrasound images. Experimental results have demonstrated that the UGGNet model achieves a notable accuracy of 78.2\% on the "Breast Ultrasound Images Dataset."