Scholarlink

<p>The precise and effective diagnostic instruments are essential owing to the lung cancer is the foremost reasons of death globally. Therefore, the research develops a unique approach for forecasting of lung cancer by incorporating modern segmentation and classification approaches. The developed system is initiated with preprocessing stage applied to image datasets, comprising resizing and non-local means filtering to improve image quality. The mean shift clustering with colour mapping is exploited for assuring precise identification of abnormal regions, assuring efficient segmentation. Moreover, a classification model employing an Artificial Rabbit Optimized (ARO) Attention Convolutional Neural Network (CNN) to capably categorise the lung tumour. An explainable Artificial Intelligence (AI) approach is integrated to offer transparency in the decision making process, increasing the trustworthiness of forecasts. The performance of system is assessed via Python tool assuring maximum accuracy of 94.8%. There by, the frame work delivers a solution for lung cancer forecasting, balancing interpretability, computational efficiency and precision.</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

An Interpretable Frame Work for Lung Cancer Prediction Using Artificial Rabbit Optimized Attention Convolution Neural Networks

  • 期刊论文

  • 发表日期：

    2026年4月10日

查看全文
  • R. Robert,
  • V. Muneeswaran,
  • Jose Saji Kumar

摘要

The precise and effective diagnostic instruments are essential owing to the lung cancer is the foremost reasons of death globally. Therefore, the research develops a unique approach for forecasting of lung cancer by incorporating modern segmentation and classification approaches. The developed system is initiated with preprocessing stage applied to image datasets, comprising resizing and non-local means filtering to improve image quality. The mean shift clustering with colour mapping is exploited for assuring precise identification of abnormal regions, assuring efficient segmentation. Moreover, a classification model employing an Artificial Rabbit Optimized (ARO) Attention Convolutional Neural Network (CNN) to capably categorise the lung tumour. An explainable Artificial Intelligence (AI) approach is integrated to offer transparency in the decision making process, increasing the trustworthiness of forecasts. The performance of system is assessed via Python tool assuring maximum accuracy of 94.8%. There by, the frame work delivers a solution for lung cancer forecasting, balancing interpretability, computational efficiency and precision.