Scholarlink

In this study, we present a novel Convolutional Neural Network (CNN)-based method for classifying breast detection cells. Tumors from breast cancer can be benign or malignant. The correct classification of a breast cancer tumor is essential for medical diagnosis. In this paper, a convolutional neural network (CNN) approach is suggested for the detection of breast cancer. It looks into the suggested method for automatically detecting breast cancer using several convolutional neural network (CNN) architectures [1]. It is a difficult task to diagnose breast cancer in order to improve patient treatment. A recent study suggests using CNN to find and get accurate findings, which may lessen human error in the process of diagnosis and lower the cost of cancer detection [2]. Our algorithm locates regions of bulk and categorizes them according to benign or cancerous [3]. On the evaluated dataset, the algorithm demonstrated 95% accuracy in detecting and 94% AUC-ROC.

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 Effectıve Svm-Based Performance Model for the Optımızed Neural Network Intended for Classıfyıng Breast Cancer Dısease

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Modugula Siva Jyothi,
  • S. V. S. V. Prasad Sanaboina,
  • Voruganti Naresh Kumar,
  • P. Raveendra Babu,
  • Abdul Subhani Shaik,
  • L. Chandrasekhar Reddy

摘要

In this study, we present a novel Convolutional Neural Network (CNN)-based method for classifying breast detection cells. Tumors from breast cancer can be benign or malignant. The correct classification of a breast cancer tumor is essential for medical diagnosis. In this paper, a convolutional neural network (CNN) approach is suggested for the detection of breast cancer. It looks into the suggested method for automatically detecting breast cancer using several convolutional neural network (CNN) architectures [1]. It is a difficult task to diagnose breast cancer in order to improve patient treatment. A recent study suggests using CNN to find and get accurate findings, which may lessen human error in the process of diagnosis and lower the cost of cancer detection [2]. Our algorithm locates regions of bulk and categorizes them according to benign or cancerous [3]. On the evaluated dataset, the algorithm demonstrated 95% accuracy in detecting and 94% AUC-ROC.