Scholarlink

<p>Pulmonary emphysema, a progressive respiratory disease and a subset of Chronic Obstructive Pulmonary Disease (COPD), is characterized by lung tissue degradation. Accurate prediction and classification of emphysema are essential for effective management and early detection. Although existing diagnostic methods such as spirometry and CT-based evaluations are valuable, they often have limitations due to interpretive variability and the inability to detect specific emphysema patterns. This paper introduces a novel approach to enhancing the accuracy and efficiency of CT-based pulmonary emphysema diagnosis by integrating an improved weighted quantum ant bee optimization (IWQABO) method with a deep convolutional neural network (DCNN). The primary challenges addressed include improving classification reliability across various emphysema subtypes and extracting optimal features from high-dimensional CT scan data. The IWQABO method optimizes the network’s hyperparameters to enhance classification accuracy, while the DCNN excels at extracting features from complex imaging data. Two data sets were employed in the study: the CTED data set and a real-time emphysema data set. The experimental results demonstrate significant improvements in classification accuracy, with a precision of 95.8%, a sensitivity of 94.5%, and a specificity of 96.3%. These results outperform traditional diagnostic methods, such as spirometry and manual CT assessments. The findings highlight the advantages of combining DCNN and IWQABO techniques for diagnosing pulmonary emphysema, showcasing their potential to improve treatment outcomes and enhance clinical decision-making for COPD patients.</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

Advanced prediction and classification of pulmonary emphysema in COPD using deep graph convolutional neural network with improved weighted quantum ant bee optimization for CT-based diagnosis

  • 期刊论文

  • 发表日期：

    2025年5月26日

查看全文
  • Suganya Jeyakumar,
  • Senthil Kumar Selvaraj,
  • Prakash Muthusamy,
  • Akilandeswari Sritharan,
  • Paul Arokiadass Jerald Mariadass

摘要

Pulmonary emphysema, a progressive respiratory disease and a subset of Chronic Obstructive Pulmonary Disease (COPD), is characterized by lung tissue degradation. Accurate prediction and classification of emphysema are essential for effective management and early detection. Although existing diagnostic methods such as spirometry and CT-based evaluations are valuable, they often have limitations due to interpretive variability and the inability to detect specific emphysema patterns. This paper introduces a novel approach to enhancing the accuracy and efficiency of CT-based pulmonary emphysema diagnosis by integrating an improved weighted quantum ant bee optimization (IWQABO) method with a deep convolutional neural network (DCNN). The primary challenges addressed include improving classification reliability across various emphysema subtypes and extracting optimal features from high-dimensional CT scan data. The IWQABO method optimizes the network’s hyperparameters to enhance classification accuracy, while the DCNN excels at extracting features from complex imaging data. Two data sets were employed in the study: the CTED data set and a real-time emphysema data set. The experimental results demonstrate significant improvements in classification accuracy, with a precision of 95.8%, a sensitivity of 94.5%, and a specificity of 96.3%. These results outperform traditional diagnostic methods, such as spirometry and manual CT assessments. The findings highlight the advantages of combining DCNN and IWQABO techniques for diagnosing pulmonary emphysema, showcasing their potential to improve treatment outcomes and enhance clinical decision-making for COPD patients.