计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (4): 1-21.DOI: 10.3778/j.issn.1002-8331.2108-0205

• 热点与综述 • 上一篇    下一篇

乳腺X线图像计算机辅助诊断技术综述

陈智丽,高皓,潘以轩,邢风   

  1. 1.沈阳建筑大学 信息与控制工程学院,沈阳 110168
    2.中国建筑第八工程局有限公司 总包协调部,江苏 苏州 215000
    3.深圳市赢时胜信息技术股份有限公司 AMS事业部,北京 100032
  • 出版日期:2022-02-15 发布日期:2022-02-15

Review of Computer Aided Diagnosis Technology in Mammography

CHEN Zhili, GAO Hao, PAN Yixuan, XING Feng   

  1. 1.School of Information and Control Engineering, Shenyang Jianzhu University, Shenyang 110168, China
    2.Department of General Contracting and Coordination, China Construction Eighth Engineering Division Co., Ltd., Suzhou, Jiangsu 215000, China
    3.AMS Division, Shenzhen Ysstech Info-Tech Co., Ltd., Beijing 100032, China
  • Online:2022-02-15 Published:2022-02-15

摘要: 近年来,乳腺癌严重威胁全球女性的身体健康,乳腺X线摄影是乳腺癌筛查的有效影像检查手段。乳腺X线图像计算机辅助诊断(computer aided diagnosis,CAD)运用计算机视觉、图像处理、机器学习等人工智能先进技术,自动分析处理乳腺X线图像,可为医生在临床中提供重要的诊断参考。主要面向肿块和微钙化病变检测、分割和分类等问题,从传统方法和深度学习方法两个角度,综述乳腺X线图像计算机辅助诊断技术的发展现状。鉴于近年来深度学习方法取得的突破性成果,回顾了经典的深度学习网络模型,着重介绍了深度学习方法在乳腺X线图像分析中的最新应用,对比分析了传统方法的弊端和深度学习方法的优势。对现有技术存在的问题进行分析,并对未来发展方向进行展望。

关键词: 乳腺X线图像, 计算机辅助诊断(CAD), 计算机视觉, 深度学习, 人工智能

Abstract: In recent years, breast cancer has seriously threatened the health of women all over the world. Mammography is an effective imaging examination tool for breast cancer screening. Computer aided diagnosis(CAD) uses advanced artificial intelligence technologies such as computer vision, image processing, machine learning, etc. to automatically analyze and process mammographic images, which can provide important diagnostic references for doctors in clinical practice. This paper mainly focuses on the detection, segmentation and classification of masses and microcalcifications in mammograms, and reviews the development status of computer aided diagnosis technology in mammography, from the perspectives of traditional and deep learning methods. Considering the breakthrough achievements of deep learning, this paper reviews classical deep learning network models, focuses on the latest application of deep learning in mammography, and compares and analyzes the disadvantages of traditional methods and the advantages of deep learning methods. Finally, the problems of the existing technology are analyzed and the future development direction is prospected.

Key words: mammography, computer aided diagnosis(CAD), computer vision, deep learning, artificial intelligence