Tumor detection in breast cancer pathology patches using a Multi-scale Multi-head Self-attention Ensemble Network on Whole Slide Images

被引:0
|
作者
Ge, Ruigang [1 ]
Chen, Guoyue [2 ]
Saruta, Kazuki [2 ]
Terata, Yuki [2 ]
机构
[1] Akita Prefectural Univ, Grad Sch Syst Sci & Technol, Dept Integrated Syst Sci, Akita 0150055, Japan
[2] Akita Prefectural Univ, Dept Informat & Comp Sci, Akita 0150055, Japan
来源
关键词
Convolutional neural network; Convolutional self-attention; Ensemble model; Multi-scale; Tumor detection;
D O I
10.1016/j.mlwa.2024.100592
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Breast cancer (BC) is the most common type of cancer among women globally and is one of the leading causes of cancer-related deaths among women. In the diagnosis of BC, histopathological assessment is the gold standard, where automated tumor detection technologies play a pivotal role. Utilizing Convolutional Neural Networks (CNNs) for automated analysis of image patches from Whole Slide Images (WSIs) enhances detection accuracy and alleviates the workload of pathologists. However, CNNs often face limitations in handling pathological patches due to a lack of sufficient contextual information and limited feature generation capabilities. To address this, we propose a novel Multi-scale Multi-head Self-attention Ensemble Network (MMSEN), which integrates a multi-scale feature generation module, a convolutional self-attention module, and an adaptive feature integration with an output module, effectively optimizing the performance of classical CNNs. The design of MMSEN optimizes the capture of key information and the comprehensive integration of features in WSIs pathological patches, significantly enhancing the precision of tumor detection. Validation results from a five-fold cross-validation experiment on the PatchCamelyon (PCam) dataset demonstrate that MMSEN achieves a ROC-AUC of 99.01% +/- 0.02%, an F1-score of 98.00% +/- 0.08%, a Balanced Accuracy (B-Acc) of 98.00% +/- 0.08%, and a Matthews Correlation Coefficient (MCC) of 96.00% +/- 0.16% (p<0.05). These results demonstrate the effectiveness and potential of MMSEN in detecting tumors from pathological patches in WSIs for BC.
引用
收藏
页数:26
相关论文
共 50 条
  • [1] MHAttnSurv: Multi-head attention for survival prediction using whole-slide pathology images
    Jiang, Shuai
    Suriawinata, Arief A.
    Hassanpour, Saeed
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 158
  • [2] Multi-head enhanced self-attention network for novelty detection
    Zhang, Yingying
    Gong, Yuxin
    Zhu, Haogang
    Bai, Xiao
    Tang, Wenzhong
    PATTERN RECOGNITION, 2020, 107
  • [3] Multi-Scale Self-Attention Network for Denoising Medical Images
    Lee, Kyungsu
    Lee, Haeyun
    Lee, Moon Hwan
    Chang, Jin Ho
    Kuo, C. -C. Jay
    Oh, Seung-June
    Woo, Jonghye
    Hwang, Jae Youn
    APSIPA TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING, 2023, 12 (05) : 1 - 26
  • [4] Intelligent Micro-Kick Detection Using a Multi-Head Self-Attention Network
    Zhang, Dezhi
    Sun, Weifeng
    Dai, Yongshou
    Wang, Dongyue
    Guo, Yanliang
    Gong, Chentao
    PROCESSES, 2025, 13 (02)
  • [5] Visual detection of moving stacked objects based on efficient multi-scale grouping and improved multi-head self-attention
    Fei, Sheng-wei
    Zhang, Hao-jie
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2025, 36 (03)
  • [6] Personalized multi-head self-attention network for news recommendation
    Zheng, Cong
    Song, Yixuan
    NEURAL NETWORKS, 2025, 181
  • [7] Detection of malicious URLs using Temporal Convolutional Network and Multi-Head Self-Attention mechanism
    Nguyet Quang Do
    Selamat, Ali
    Krejcar, Ondrej
    Fujita, Hamido
    APPLIED SOFT COMPUTING, 2025, 169
  • [8] Epilepsy detection based on multi-head self-attention mechanism
    Ru, Yandong
    An, Gaoyang
    Wei, Zheng
    Chen, Hongming
    PLOS ONE, 2024, 19 (06):
  • [9] MSSTGCN: Multi-Head Self-Attention and Spatial-Temporal Graph Convolutional Network for Multi-Scale Traffic Flow Prediction
    Zong, Xinlu
    Yu, Fan
    Chen, Zhen
    Xia, Xue
    CMC-COMPUTERS MATERIALS & CONTINUA, 2025, 82 (02): : 3517 - 3537
  • [10] Multi-scale self-attention generative adversarial network for pathology image restoration
    Liang, Meiyan
    Zhang, Qiannan
    Wang, Guogang
    Xu, Na
    Wang, Lin
    Liu, Haishun
    Zhang, Cunlin
    VISUAL COMPUTER, 2023, 39 (09): : 4305 - 4321