Scholarlink

<p>This paper presents an innovative deep neural network algorithm designed to improve the automatic recognition accuracy of epithelial and mesenchymal tissues in breast cancer pathological images. The key innovation centers around the development of two novel algorithms: the Tissue Enhancement Vision Fusion technique and the Comprehensive Gray-Scale Threshold Intelligent Judgment method. These algorithms optimize the analysis and diagnosis process of breast cancer pathological images by introducing new approaches to feature enhancement and quantitative assessment that have not been explored in existing literature. The Tissue Enhancement Vision Fusion technique enhances the intuitive observation of key features in images through heatmap generation, while the Comprehensive Gray-Scale Threshold Intelligent Judgment method quantitatively assesses image characteristics, thereby enhancing the precision and efficiency of the model in recognizing epithelial and mesenchymal tissues. By strategically adjusting the EfficientNet model structure in conjunction with these two newly proposed algorithms, the proposed deep learning framework significantly improves the performance of breast cancer pathological image processing. The experimental results demonstrate that the enhanced model achieves recognition accuracies of 0.8548 and 0.8125 for epithelial and mesenchymal tissues, respectively, outperforming existing methods in both accuracy and efficiency. This breakthrough not only validates the effectiveness of the proposed algorithms but also provides robust technical support for early detection and precise diagnosis of breast cancer.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning-based Pathological Image Analysis Algorithm for Early Diagnosis of Breast Cancer

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月21日

查看全文
  • Tangsen Huang,
  • Xingru Huang,
  • Haibing Yin

摘要

This paper presents an innovative deep neural network algorithm designed to improve the automatic recognition accuracy of epithelial and mesenchymal tissues in breast cancer pathological images. The key innovation centers around the development of two novel algorithms: the Tissue Enhancement Vision Fusion technique and the Comprehensive Gray-Scale Threshold Intelligent Judgment method. These algorithms optimize the analysis and diagnosis process of breast cancer pathological images by introducing new approaches to feature enhancement and quantitative assessment that have not been explored in existing literature. The Tissue Enhancement Vision Fusion technique enhances the intuitive observation of key features in images through heatmap generation, while the Comprehensive Gray-Scale Threshold Intelligent Judgment method quantitatively assesses image characteristics, thereby enhancing the precision and efficiency of the model in recognizing epithelial and mesenchymal tissues. By strategically adjusting the EfficientNet model structure in conjunction with these two newly proposed algorithms, the proposed deep learning framework significantly improves the performance of breast cancer pathological image processing. The experimental results demonstrate that the enhanced model achieves recognition accuracies of 0.8548 and 0.8125 for epithelial and mesenchymal tissues, respectively, outperforming existing methods in both accuracy and efficiency. This breakthrough not only validates the effectiveness of the proposed algorithms but also provides robust technical support for early detection and precise diagnosis of breast cancer.