Scholarlink

<p>Prostate cancer is one of the most prevalent malignancies worldwide, necessitating the development of advanced and efficient detection models. This research presents the Prostate Cancer Detection Network (ProCDNet), a novel framework that integrates LDR-DenseNet for feature extraction and EAO-QML for disease classification, providing a highly efficient and accurate solution for prostate cancer detection. Here, the Lightweight Deep Residual DenseNet (LDR-DenseNet) is utilized for feature extraction, which integrates DenseNet and Residual Learning (ResNet) to enhance feature propagation, minimize redundancy, and improve learning efficiency while maintaining computational efficiency. To further enhance detection accuracy, a Quantum Machine Learning (QML) model is employed, where the loss function optimization is refined using the Enhanced Addax Optimization (EAO) algorithm. The EAO algorithm integrates Chebyshev mapping within the conventional Addax optimization framework to ensure robust convergence and improved classification performance. The analysis of the proposed ProCDNet model based on Accuracy, Precision, Recall, F1-Score, Specificity, and MSE acquired the values of 99.27, 99.0856, 98.282, 98.851, 99.967, and 0.00913 respectively.</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

ProCDNet: prostate cancer detection network using quantum machine learning with enhanced addax optimization

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月7日

查看全文
  • M. R. Prathap,
  • K. S. Vairavel,
  • C. Kumar,
  • Abdullah Alwabli

摘要

Prostate cancer is one of the most prevalent malignancies worldwide, necessitating the development of advanced and efficient detection models. This research presents the Prostate Cancer Detection Network (ProCDNet), a novel framework that integrates LDR-DenseNet for feature extraction and EAO-QML for disease classification, providing a highly efficient and accurate solution for prostate cancer detection. Here, the Lightweight Deep Residual DenseNet (LDR-DenseNet) is utilized for feature extraction, which integrates DenseNet and Residual Learning (ResNet) to enhance feature propagation, minimize redundancy, and improve learning efficiency while maintaining computational efficiency. To further enhance detection accuracy, a Quantum Machine Learning (QML) model is employed, where the loss function optimization is refined using the Enhanced Addax Optimization (EAO) algorithm. The EAO algorithm integrates Chebyshev mapping within the conventional Addax optimization framework to ensure robust convergence and improved classification performance. The analysis of the proposed ProCDNet model based on Accuracy, Precision, Recall, F1-Score, Specificity, and MSE acquired the values of 99.27, 99.0856, 98.282, 98.851, 99.967, and 0.00913 respectively.