...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Medical Imaging and Health Informatics >Abnormality Detection and Classification in Computer-Aided Diagnosis (CAD) of Breast Cancer Images
【24h】

Abnormality Detection and Classification in Computer-Aided Diagnosis (CAD) of Breast Cancer Images

机译：乳腺癌图像计算机辅助诊断（CAD）中的异常检测和分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents a new approach for abnormality detection and classification of tumour in mammographic breast cancer images. The detection of masses is achieved in terms of their size and shape that can greatly help in early detection of breast tumor in breast images. The objective of the work is to detect the abnormal tumor or tissue inside mammographic breast cancer images using three stages namely pre-processing, segmentation and post processing. Pre-processing is used to reduce the noise signal and then segmentation is applied to detect the masses or abnormalities. Finally, post processing helps to find out the benign and malignant tissue with the affected area in the breast cancer image. The occurrences of cancer nodules are identified clearly and classified too. The algorithm achieves 96.5% sensitivity, 89% specificity and 95.6% accuracy value as compared with the observation by a radiologist.
机译：本文提出了一种在乳腺X射线摄影乳腺癌图像中进行异常检测和肿瘤分类的新方法。在肿块的大小和形状方面实现了肿块的检测，可以极大地帮助早期发现乳房图像中的乳腺肿瘤。该工作的目的是使用预处理，分割和后处理三个阶段来检测乳腺X线摄影乳腺癌图像内的异常肿瘤或组织。预处理用于减少噪声信号，然后进行分段以检测肿块或异常。最后，后处理有助于在乳腺癌图像中找出患处的良恶性组织。癌症结节的发生也被清楚地识别和分类。与放射科医生的观察结果相比，该算法可实现96.5％的灵敏度，89％的特异性和95.6％的准确度值。

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