计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (7): 44-58.DOI: 10.3778/j.issn.1002-8331.2009-0161

• 热点与综述 • 上一篇    下一篇

卷积神经网络在生物医学图像上的应用进展

杨培伟,周余红,邢岗,田智强,许夏瑜   

  1. 1.西安交通大学 生命科学与技术学院 生物信息工程教育部重点实验室,西安 710049
    2.西安交通大学 仿生工程与生物力学中心,西安 710049
    3.西安交通大学 软件学院,西安 710049
  • 出版日期:2021-04-01 发布日期:2021-04-02

Applications of Convolutional Neural Network in Biomedical Image

YANG Peiwei, ZHOU Yuhong, XING Gang, TIAN Zhiqiang, XU Xiayu   

  1. 1.The Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science and Technology, Xi’an Jiaotong University, Xi’an 710049, China
    2.Bioinspired Engineering and Biomechanics Center(BEBC), Xi’an Jiaotong University, Xi’an 710049, China
    3.School of Software Engineering, Xi’an Jiaotong University, Xi’an 710049, China
  • Online:2021-04-01 Published:2021-04-02

摘要:

生物医学成像领域的迅速发展引起相关图像信息的爆炸式增长,对其图像进行人工智能辅助分析日益成为科学研究、临床应用、即时诊断等领域的迫切需求。近年来深度学习,尤其是卷积神经网络在生物医学图像分析领域取得广泛应用,在生物医学图像的信息提取,包括细胞分类、检测,生理及病理图像的分割、检测等领域发挥日益重要的作用。介绍了深度学习及卷积神经网络相关技术的发展;重点针对近几年卷积神经网络在细胞生物学图像、医学图像领域的应用进展进行了梳理;对卷积神经网络在生物医学图像分析领域研究目前存在的问题及可能的发展方向进行了展望。

关键词: 生物医学, 深度学习, 卷积神经网络, 图像处理

Abstract:

The rapid development of the biomedical imaging techniques has caused rapid explosion of imaging information. Computer-assisted analysis of biomedical images has therefore become a research field with urgent needs. In recent years, deep learning, especially convolutional neural network, is widely used in biomedical image analysis. It plays an increasingly important role in the extraction and analysis of biomedical image information, such as cell segmentation and classification, physiological and pathological image segmentationand detection. Firstly, the development of convolutional neural network and other related techniques is briefly reviewed. Then it focuses on the application of convolutional neural networks in cell biology image and medical image. At last, the existing issues and potential directions in related fields are discussed.

Key words: biomedical science, deep learning, convolutional neural networks, image processing