Scholarlink

This research study introduces a new method of categorizing lung cancer using the INAX-Net model. It is built upon two different architectures, Inception V4 and AlexNet, which are combined with a multi-class SVM classifier. Adenocarcinoma, large cell carcinoma, squamous cell carcinoma as well as normal healthy tissue are among the types that can be classified according to this model’s employment of LIDC-IDRI CT Scan Dataset. Multi-scale feature extraction capacity from inception V4 is merged seamlessly with high-level feature capturing strength of alexnet in INAX-net through its layers ensuring effective flow information between them. The proposed approach performs better than other methods with an accuracy level of 99.43% and specificity ratio reaching 99.512%. Therefore, this extensive technique proves that deep learning architectures together with SVM classifiers can be used for accurate detection of lung cancer, thus greatly enhancing precision while increasing both sensitivity and specificity at once.

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

Precision Lung Cancer Classification Using the INAX-Net Model and Multiclass SVM

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Syed Zaheer Ahammed,
  • Radhika Baskar,
  • G. Nalini Priya

摘要

This research study introduces a new method of categorizing lung cancer using the INAX-Net model. It is built upon two different architectures, Inception V4 and AlexNet, which are combined with a multi-class SVM classifier. Adenocarcinoma, large cell carcinoma, squamous cell carcinoma as well as normal healthy tissue are among the types that can be classified according to this model’s employment of LIDC-IDRI CT Scan Dataset. Multi-scale feature extraction capacity from inception V4 is merged seamlessly with high-level feature capturing strength of alexnet in INAX-net through its layers ensuring effective flow information between them. The proposed approach performs better than other methods with an accuracy level of 99.43% and specificity ratio reaching 99.512%. Therefore, this extensive technique proves that deep learning architectures together with SVM classifiers can be used for accurate detection of lung cancer, thus greatly enhancing precision while increasing both sensitivity and specificity at once.