Scholarlink

Breast cancer is one of the most common and deadly cancers among women worldwide. Early detection and treatment are the most effective methods of reducing mortality. Advances in machine learning and technology offer new opportunities for improving breast cancer diagnosis. By leveraging the power of data processing, machine learning algorithms can quickly analyze mammography images to detect anomalies, aiding in early detection. This paper evaluates and compares the performance of four pre-existing computer vision models for this task. The models were assessed using various metrics, with the aim of identifying the most promising ones for real-world deployment in clinical settings. The results demonstrate that while all models performed well in general computer vision tasks, certain models exhibited higher accuracy and stability, making them more suitable for clinical use. These findings provide a foundation for future research aimed at implementing machine learning models in breast cancer diagnosis, with the potential for real-world application in clinical environments.

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

Performance Comparison of Pre-Trained CNN Models for Breast Cancer Detection in Mammography Images Using Transfer Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • İrem Bahar Şahinkeser,
  • Bilal Saoud,
  • Ibraheem Shayea,
  • Abitova Gulnara

摘要

Breast cancer is one of the most common and deadly cancers among women worldwide. Early detection and treatment are the most effective methods of reducing mortality. Advances in machine learning and technology offer new opportunities for improving breast cancer diagnosis. By leveraging the power of data processing, machine learning algorithms can quickly analyze mammography images to detect anomalies, aiding in early detection. This paper evaluates and compares the performance of four pre-existing computer vision models for this task. The models were assessed using various metrics, with the aim of identifying the most promising ones for real-world deployment in clinical settings. The results demonstrate that while all models performed well in general computer vision tasks, certain models exhibited higher accuracy and stability, making them more suitable for clinical use. These findings provide a foundation for future research aimed at implementing machine learning models in breast cancer diagnosis, with the potential for real-world application in clinical environments.