| 基于CNN迁移学习的甲状腺结节检测方法 |
| |
| 引用本文： | 叶 晨,赵作鹏,马小平,胡延军,刘 翼,赵海含. 基于CNN迁移学习的甲状腺结节检测方法[J]. 计算机工程与应用, 2018, 54(22): 127-132. DOI: 10.3778/j.issn.1002-8331.1805-0444 |
| |
| 作者姓名： | 叶 晨 赵作鹏 马小平 胡延军 刘 翼 赵海含 |
| |
| 作者单位： | 1.中国矿业大学 计算机科学与技术学院，江苏 徐州 2211162.中国矿业大学 信息与控制工程学院，江苏 徐州 221116 |
| |
| 摘 要： | 将人工智能应用到医学图像中可减少医生工作量和患者的重复检查。针对现有甲状腺结节检测方法处理过程繁琐、特征提取困难等问题，提出一种基于卷积神经网络（CNN）的甲状腺结节检测方法。针对数据样本量小的限制，提出利用预训练与迁移学习改善网络性能的策略。根据不同结构CNN能够提取不同层次特征的特点，提出融合浅层与深层网络的方法。通过医院收集的3 414张图片对提出的方法进行验证，最终准确率为91.60%，灵敏度为90.08%，特异性为93.24%，接收者操作特征曲线下面积为96.55%。
|
| 关 键 词： | CT 卷积神经网络（CNN） 迁移学习 检测 |
Thyroid nodule detection method based on CNN and transfer learning |
| |
| YE Chen,ZHAO Zuopeng,MA Xiaoping,HU Yanjun,LIU Yi,ZHAO Haihan. Thyroid nodule detection method based on CNN and transfer learning[J]. Computer Engineering and Applications, 2018, 54(22): 127-132. DOI: 10.3778/j.issn.1002-8331.1805-0444 |
| |
| Authors: | YE Chen ZHAO Zuopeng MA Xiaoping HU Yanjun LIU Yi ZHAO Haihan |
| |
| Affiliation: | 1.School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China2.School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, Jiangsu 221116, China |
| |
| Abstract: | The application of artificial intelligence to medical images can reduce the workload of doctors and the repeated examination of patients. Aiming at the problems of the existing thyroid nodule detection methods such as complex processing procedures and difficult feature extraction, a thyroid nodule detection method based on Convolutional Neural Network（CNN） is put forward. For the small data sample size restrictions, the strategy for improving network performance using pre-training and transfer learning is proposed. According to the trait that different structure CNN can extract different levels of features, a method to simultaneously fuse two networks to improve the accuracy is advanced. The proposed method is validated on 3414 images collected from hospital with the accuracy of 91.60%, sensitivity of 90.08%, specificity of 93.24% and AUC of 96.55%. |
| |
| Keywords: | computed tomography Convolutional Neural Network（CNN） transfer learning detection |
|
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
