计算机应用 ›› 2020, Vol. 40 ›› Issue (10): 2917-2922.DOI: 10.11772/j.issn.1001-9081.2020020136

• 人工智能 • 上一篇    下一篇

基于生成对抗网络的自动细胞核分割半监督学习方法

程凯1, 王妍2, 刘剑飞1   

  1. 1. 安徽大学 电气工程与自动化学院, 合肥 230061;
    2. 安徽大学 计算机科学与技术学院, 合肥 230061
  • 收稿日期:2020-02-15 修回日期:2020-04-05 出版日期:2020-10-10 发布日期:2020-04-17
  • 通讯作者: 程凯
  • 作者简介:程凯(1994-),男,湖北黄石人,硕士,主要研究方向:模式识别、计算机视觉;王妍(1985-),女,天津人,博士研究生,主要研究方向:模式识别、计算机视觉;刘剑飞(1983-),男,江苏盐城人,研究员,博士,CCF会员,主要研究方向:模式识别、计算机视觉、医疗影像。
  • 基金资助:
    国家自然科学基金资助项目(61702001)。

Semi-supervised learning method for automatic nuclei segmentation using generative adversarial network

CHENG Kai1, WANG Yan2, LIU Jianfei1   

  1. 1. School of Electrical Engineering and Automation, Anhui University, Hefei Anhui 230061, China;
    2. School of Computer Science and Technology, Anhui University, Hefei Anhui 230061, China
  • Received:2020-02-15 Revised:2020-04-05 Online:2020-10-10 Published:2020-04-17
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61702001).

摘要: 为了减少对标注图像数量的依赖,提出一种新颖的半监督学习方法用于细胞核的自动分割。首先,通过新的卷积神经网络(CNN)从背景中自动提取细胞区域。其次,判别器网络通过应用全卷积网络来为输入的图像生成置信图;同时耦合对抗性损失和标准交叉熵损失,以改善分割网络的性能。最后,将标记图像和无标记图像与置信图结合来训练分割网络,使分割网络可以在提取的细胞区域中识别单个细胞核。对84张图像(训练集中的1/8图像带标注,其余图像无标注)的实验结果表明,提出的细胞核分割方法的分割准确率度量(SEG)得分可以达到77.9%,F1得分可以达到76.0%,这比该方法使用670张图像且训练集中的所有图像都带标注时的表现要好。

关键词: 生成对抗网络, 细胞核分割, 半监督学习, 全卷积网络, 置信图

Abstract: In order to reduce the dependence on the number of labeled images, a novel semi-supervised learning method was proposed for automatic segmentation of nuclei. Firstly, a novel Convolutional Neural Network (CNN) was used to extract the cell region from the background. Then, a confidence map for the input image was generated by the discriminator network via applying a full convolutional network. At the same time, the adversarial loss and the standard cross-entropy loss were coupled to improve the performance of the segmentation network. Finally, the labeled images and unlabeled images were combined with the confidence maps to train the segmentation network, so that the segmentation network was able to identify the nuclei in the extracted cell regions. Experimental results on 84 images (1/8 of the total images in the training set were labeled, and the rest were unlabeled) showed that the SEGmentation accuracy measurement (SEG) score of the proposed nuclei segmentation method achieved 77.9% and F1 score of the method was 76.0%, which were better than those of the method when using 670 images (all images in the training set were labeled).

Key words: Generative Adversarial Network (GAN), nuclei segmentation, semi-supervised learning, fully convolutional network, confidence map

中图分类号: