首页> 外文会议>Global Conference for Advancement in Technology >Classification Methods to Improve Performance in Breast Cancer Screening
【24h】

Classification Methods to Improve Performance in Breast Cancer Screening

机译:提高乳腺癌筛选性能的分类方法

获取原文
获取外文期刊封面目录资料

摘要

Breast cancer is a very aggressive type of cancer with a very low median survival. Today the deaths of women in the age group 15-55 are increasing because of malignant cells are increasing in breast. For the death of women it is the main cause. So, the possibility of improvement is only the early diagnosis of patients. Machine Learning (ML) techniques can assist the physicians by expanding tools for detection at initial stage and analysis of breast cancer thus increasing the probability of patient's survival [1]. At present, mammography is the best imaging strategy utilized by radiologist for screening breast tumours. In this paper, author proposes a system using different classification method like Support Vector Machine (SVM), Naive Bayes, Decision tree and MLP (Multi-Layer Perceptron) for early detection of cancer. Propose system extracts the texture based features and shape based features using LBP, GLCM, Otsu, Compactness, Fourier Transform. The main focus of the presented work is on application of MLP for breast cancer classification. In addition medical images data has been used to improve accuracy. Proposed system will do the comparative study between both datasets by extracting the feature with and without removing pectoral muscles.
机译:乳腺癌是一种非常激进的癌症,中位数非常低。今天,由于恶性细胞在乳腺癌中增加,年龄组妇女的死亡日益增加。对于女性的死亡,这是主要原因。因此,改善的可能性只是患者的早期诊断。机器学习(ML)技术可以通过扩展在初始阶段的检测工具和乳腺癌分析中来帮助医生,从而增加患者存活率的可能性[1]。目前,乳房X线照相术是放射学家用于筛查乳腺肿瘤的最佳成像策略。在本文中,作者提出了一种使用不同分类方法的系统,如支持向量机(SVM),幼稚贝叶斯,决策树和MLP(多层Perceptron),用于早期检测癌症。建议系统使用LBP,GLCM,OTSU,紧凑性,傅里叶变换提取基于纹理的特征和形状的特征。所提出的工作的主要重点是在MLP应用于乳腺癌分类。此外,医学图像数据已被用来提高精度。建议的系统将通过提取具有和不移除胸肌的特征来进行两个数据集之间的比较研究。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号