Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (5): 112-117.DOI: 10.3778/j.issn.1002-8331.1804-0300

Previous Articles     Next Articles

Cirrhosis Recognition by Deep Learning Model GoogleNet-PNN

JU Weixin1, ZHAO Ximei1,2, WEI Bin2, WANG Guodong1   

  1. 1.College of Computer Science and Technology, Qingdao University, Qingdao, Shandong 266071, China
    2.Shandong Province Key Laboratory of Digital Medicine and Computer Aided Surgery, Qingdao, Shandong 266000, China
  • Online:2019-03-01 Published:2019-03-06

深度学习模型GoogleNet-PNN对肝硬化的识别

鞠维欣1,赵希梅1,2,魏  宾2,王国栋1   

  1. 1.青岛大学 计算机科学技术学院,山东 青岛 266071
    2.山东省数字医学与计算机辅助手术重点实验室,山东 青岛 266000

Abstract: Traditional machine learning is difficult to extract high quality features and it consumes much time and energy, Therefore, based on the deep learning method and combined with convolution neural network and probabilistic neural network, a new model called GoogleNet-PNN is first put forward and applied. Firstly, it automatically learns features and avoids the complexity of manually extracting features. Secondly, it combines the advantages of PNN, such as easy training and fast convergence speed. It has achieved good results in the experiment of liver disease classification. What’s more, combined with the migrating learning, the method firstly pre-trains in the natural image set and then is applied to the medical image, which avoids the overfitting problem caused by the shortage of samples. Finally, experimental results show recognition accuracy is better than other methods and it has reached 98% objectively.

Key words: deep learning, medical image, convolution neural network, probabilistic neural network, transfer learning

摘要: 针对传统机器学习人工提取特征耗时耗力,并且提取高质量特征存在一定困难等问题,将基于深度学习的方法,首次结合卷积神经网络和概率神经网络,提出了一种新的模型GoogleNet-PNN,其自动学习特征,避免了手动提取特征的繁琐性,而且结合了PNN训练容易、收敛速度快等特点,在肝病分类的实验中取得了较好的效果;并使用了迁移学习的方法,通过在自然图像集的预训练,然后应用到医学图像,避免了因样本不足而出现的过拟合问题,实验结果最终表明识别准确率要优于其他方法,达到了98%的客观识别率。

关键词: 深度学习, 医学图像, 卷积神经网络, 概率神经网络, 迁移学习