Scholarlink

<p>Cervical cancer remains a significant global health concern, necessitating accurate and early diagnosis to improve patient outcomes. This study presents a new cervical cancer detection (C<sup>2</sup>D) strategy consisting of three critical stages: (i) pre-processing stage (P<sup>2</sup>S), (ii) feature selection stage (FS<sup>2</sup>), and (iii) detection stage (DS). The pre-processing stage exploits VGG16 for deep extraction of features. The feature selection stage utilizes the potent binary Golden Jackal Optimization (BGJO) technique for optimal choosing of features. The detection stage employs an improved fully connected neural network (IFCNN) for high-accuracy classification. The proposed hybrid strategy achieves an impressive accuracy of approximately 97%, significantly outperforming traditional classifiers such as K-Nearest Neighbors, Decision Trees, Random Forests, Gaussian Naive Bayes, and Support Vector Machines in terms of accuracy, precision, recall, and F1-score. These results demonstrate the effectiveness of the proposed strategy in enhancing diagnostic accuracy and reliability for early detection of cervical cancer, offering a promising solution to support clinical decision-making.</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

Cervical cancer detection: enhancing accuracy and early diagnosis through data analysis

  • 期刊论文

  • 发表日期：

    2026年3月14日

查看全文
  • Samah A. Gamel,
  • Shereen H. Ali,
  • Fatma M. Talaat

摘要

Cervical cancer remains a significant global health concern, necessitating accurate and early diagnosis to improve patient outcomes. This study presents a new cervical cancer detection (C2D) strategy consisting of three critical stages: (i) pre-processing stage (P2S), (ii) feature selection stage (FS2), and (iii) detection stage (DS). The pre-processing stage exploits VGG16 for deep extraction of features. The feature selection stage utilizes the potent binary Golden Jackal Optimization (BGJO) technique for optimal choosing of features. The detection stage employs an improved fully connected neural network (IFCNN) for high-accuracy classification. The proposed hybrid strategy achieves an impressive accuracy of approximately 97%, significantly outperforming traditional classifiers such as K-Nearest Neighbors, Decision Trees, Random Forests, Gaussian Naive Bayes, and Support Vector Machines in terms of accuracy, precision, recall, and F1-score. These results demonstrate the effectiveness of the proposed strategy in enhancing diagnostic accuracy and reliability for early detection of cervical cancer, offering a promising solution to support clinical decision-making.