Scholarlink

<p>Lung cancer remains a leading cause of cancer-related mortality globally, primarily due to late-stage detection. To significantly enhance diagnostic precision and patient outcomes, this paper presents a novel Convolutional Neural Network (CNN) model for the early classification of lung cancer from CT images. The novelty of this work is involved in meticulously crafting the CNN architecture by integrating state-of-the-art deep learning techniques to differentiate between benign, malignant, and normal lung tissues with high precision. The publicly available dataset from Iraq-Oncology Teaching Hospital is used for the experiments. The Synthetic Minority Over-sampling Technique (SMOTE) is used to address the issue of class imbalance. Despite challenges like class imbalance and computational constraints, our model demonstrates robust generalizability and clinical potential. Extensive results show that the proposed model outperforms the traditional diagnostic methods to achieve an accuracy of 99.27%, precision of 99.44%, recall of 98.56%, and F1 score of 99.00%. This work establishes a new benchmark for lung cancer screening and emphasizes the need to utilize cutting-edge machine-learning algorithms in medical imaging to enable earlier interventions that lead to better patient outcomes.</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

Enhancing Clinical Outcomes Using Deep Learning Solution for Accurate Lung Cancer Classification

  • 期刊论文

  • 发表日期：

    2025年2月7日

查看全文
  • Aditya Shastri,
  • Yash Prajapati,
  • Harsh Katariya,
  • Manish Paliwal,
  • Ketan Sabale

摘要

Lung cancer remains a leading cause of cancer-related mortality globally, primarily due to late-stage detection. To significantly enhance diagnostic precision and patient outcomes, this paper presents a novel Convolutional Neural Network (CNN) model for the early classification of lung cancer from CT images. The novelty of this work is involved in meticulously crafting the CNN architecture by integrating state-of-the-art deep learning techniques to differentiate between benign, malignant, and normal lung tissues with high precision. The publicly available dataset from Iraq-Oncology Teaching Hospital is used for the experiments. The Synthetic Minority Over-sampling Technique (SMOTE) is used to address the issue of class imbalance. Despite challenges like class imbalance and computational constraints, our model demonstrates robust generalizability and clinical potential. Extensive results show that the proposed model outperforms the traditional diagnostic methods to achieve an accuracy of 99.27%, precision of 99.44%, recall of 98.56%, and F1 score of 99.00%. This work establishes a new benchmark for lung cancer screening and emphasizes the need to utilize cutting-edge machine-learning algorithms in medical imaging to enable earlier interventions that lead to better patient outcomes.