生物医学工程学杂志

生物医学工程学杂志

基于卷积神经网络提取超声图像甲状腺结节钙化点的研究

查看全文

超声是检测甲状腺结节的首选方法,钙化特征是甲状腺结节良恶性判别的重要特征。但是由于囊壁等结节内部结构的干扰,钙化点提取一直是医学影像处理技术中的难点。本文提出了一种基于深度学习算法的钙化点提取法,并在阿列克谢(Alexnet)卷积神经网络的基础上提出了两种改进方法:① 通过添加逐层对应的反池化(unpooling)和反卷积层(deconv2D)使网络向着所需要的特征进行训练并最终提取出钙化特征;② 通过修改 Alexnet 模型卷积模板的数量和全连接层节点的数量,使其特征提取更加精细;最终通过两种方法的结合得到改进网络。为了验证本文所提出的方法,本文从数据集中选取钙化结节图像 8 416 张、无钙化结节图像 10 844 张。改进的 Alexnet 卷积神经网络方法的钙化特征提取准确率为 86%,较传统方法有了较大提升,为甲状腺结节的良恶性识别提供了有效的手段。

Ultrasound is the best way to diagnose thyroid nodules. To discriminate benign and malignant nodules, calcification is an important characteristic. However, calcification in ultrasonic images cannot be extracted accurately because of capsule wall and other internal tissue. In this paper, deep learning was first proposed to extract calcification, and two improved methods were proposed on the basis of Alexnet convolutional neural network. First, adding the corresponding anti-pooling (unpooling) and deconvolution layers (deconv2D) made the network to be trained for the required features and finally extract the calcification feature. Second, modifying the number of convolution templates and full connection layer nodes made feature extraction more refined. The final network was the combination of two improved methods above. To verify the method presented in this article, we got 8 416 images with calcification, and 10 844 without calcification. The result showed that the accuracy of the calcification extraction was 86% by using the improved Alexnet convolutional neural network. Compared with traditional methods, it has been improved greatly, which provides effective means for the identification of benign and malignant thyroid nodules.

关键词: 甲状腺结节; 钙化点; 卷积神经网络; 阿列克谢卷积神经网络

Key words: thyroid nodules; calcification; convolutional neural networks; Alexnet convolutional neural network

引用本文: 左东奇, 韩霖, 陈科, 李程, 花瞻, 林江莉. 基于卷积神经网络提取超声图像甲状腺结节钙化点的研究. 生物医学工程学杂志, 2018, 35(5): 679-687. doi: 10.7507/1001-5515.201710017 复制

登录后 ,请手动点击刷新查看全文内容。 没有账号,
登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. 余秋. 甲状腺良恶性结节病理特征与超声弹性成像参数的相关性分析. 海南医学院学报: 1-9. DOI: 10.13210/j.cnki.jhmu.20180524.007.
2. 高明, 郑向前. 甲状腺癌过去与未来十年. 中国肿瘤临床, 2018, 45(01): 2-6.
3. Seiberling K A, Dutra J C, Grant T, et al. Role of intrathyroidal calcifications detected on ultrasound as a marker of malignancy. Laryngoscope, 2004, 114(10): 1753-1757.
4. Hoang J K, Lee W K, Lee M, D, et al. US features of thyroid malignancy: pearls and pitfalls,. Radiographics,, 2007, 27(3): 847-860.
5. Chen Kuenyuan, Chen C N, Wu M H, et al. Computerized detection and quantification of microcalcifications in thyroid nodules. Ultrasound Med Biol, 2011, 37(6): 870-878.
6. Choi W J, Park J S, Kim K G, et al. Computerized analysis of calcification of thyroid nodules as visualized by ultrasonography. Eur J Radiol, 2015, 84(10): 1949-1953.
7. 韩晓涛. 基于超声图像的甲状腺结节计算机辅助诊断方法研究. 成都: 西南交通大学, 2016.
8. Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. The 25th International Conference on Neural Information Processing System, Lake Tahoe, 2012: 1097-1105.
9. Lawrence S, Giles C L, Tsoi A C, et al. Face recognition: a convolutional neural-network approach. IEEE Transactions on Neural Networks, 1997, 8(1): 98-113.
10. Howard A G. . Some improvements on deep convolutional neural network based image classification. Computer Science, 2013, arXiv: 1312. 5402.
11. Gu Jiuxiang, Wang Zhenhua, Jason K, et al. Recent advances in convolutional neural networks, 2017.
12. Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, Washington: IEEE Computer Society, 2015: 1-8.