基于迁移学习和深度卷积神经网络的乳腺肿瘤诊断系统

褚晶辉; 吴泽蕤; 吕卫; 李喆

doi:doi:10.3788/lop55.081001

激光与光电子学进展, 2018, 55 (8): 081001, 网络出版: 2018-08-13

基于迁移学习和深度卷积神经网络的乳腺肿瘤诊断系统下载： 1503次

Breast Cancer Diagnosis System Based on Transfer Learning and Deep Convolutional Neural Networks

论文大纲

褚晶辉吴泽蕤吕卫李喆

作者单位

天津大学电气自动化与信息工程学院, 天津 300072

AI 词云图 AI一句话精读 AI短摘要

注：本部分内容由 AI 自动生成，请您知悉。

摘要

乳腺肿瘤计算机辅助诊断(CAD)系统在医学检测和诊断中的应用日益重要。为了区分核磁共振图像(MRI)中肿瘤与非肿瘤，利用深度学习和迁移学习方法，设计了一种新型乳腺肿瘤CAD系统：1）对数据集进行不平衡处理和数据增强；2）在MRI数据集上，利用卷积神经网络（CNN）提取CNN特征，并利用相同的支持向量机分类器，计算每层CNN的特征图的分类F1分数，选取分类性能最高的一层作为微调节点，其后维度较低层为连接新网络节点；3）在选取的网络接入节点，连接新设计的两层全连接层组成新的网络，利用迁移学习，对新网络载入权重；4）采用固定微调节点前的网络层不可训练，其余层可训练的方式微调。分别基于深度卷积网络(VGG16)、Inception V3、深度残差网络(ResNet50)构建的CAD系统，性能均高于主流的CAD系统，其中基于VGG16和ResNet50搭建的系统性能突出，且二次迁移可以提高VGG16系统性能。

Abstract

Breast cancer computer-aided diagnosis (CAD) system is playing more and more important role in medical detection and diagnosis. In order to classify tumor and non-tumor in magnetic resonance imaging (MRI), a novel breast cancer CAD system based on deep learning and transfer learning is designed. First, we balance the imbalanced data sets and use data augmentation to deal with it. Then, we use the convolutional neural network (CNN) to extract CNN features from MRI data sets, use the same support vector machine to evaluate the feature extraction abilities of different layers, and select the highest F1 score layer as the node of fine-tuning, the layers behind it, which has relatively low dimension as the node of connection of new networks. Next, we select the newly designed fully-connected layers with two layers to form a new network, and use transfer learning to load weights on the new network. At last, we freeze the layers before the node of fine-tuning, while other layers can be trained in the fine-tuning procedure. The CAD systems are built on three CNN networks, including VGG16, Inception V3, and ResNet50. The effects of the system based on VGG16 and ResNet50 have the best performance, and twice transfer learning can improve the performance of VGG16 network system.

参考文献

[1] Pei C D, Wang C M, Xu S Z. Segmentation of the breast region in mammograms using marker-controlled watershed transform［C］. The 2nd IEEE International Conference on Information Science and Engineering, 2010: 2371-2374.

[2] Ries L A G, Harkins D, Krapcho M, et al. SEER cancer statistics review, 1975-2003［R］. Bethesda: National Cancer Institute, 2006.

[3] Fenton J J, Taplin S H, Carney P A, et al. Influence of computer-aided detection on performance of screening mammography［J］. New England Journal of Medicine, 2007, 356(14): 1399-1409.

[4] Tang J, Rangayyan R M, Xu J, et al. Computer-aided detection and diagnosis of breast cancer with mammography: recent advances［J］. IEEE Transactions on Information Technology in Biomedicine, 2009, 13(2): 236-251.

[5] Litjens G, Kooi T, Bejnordi B E, et al. A survey on deep learning in medical image analysis［J］. Medical Image Analysis, 2017, 42: 60-88.

[6] Yoon S, Kim S. Mutual information-based SVM-RFE for diagnostic classification of digitized mammograms［J］. Pattern Recognition Letters, 2009, 30(16): 1489-1495.

[7] Pan S J, Yang Q. A survey on transfer learning［J］. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.

[8] Japkowicz N. Learning from imbalanced data sets: a comparison of various strategies［C］. AAAI Workshop on Learning from Imbalanced Data Sets, 2000, 68: 10-15.

[9] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks［J］. Advances in Neural Information Processing Systems, 2012: 1097-1105.

[10] Sharif R A, Azizpour H, Sullivan J, et al. CNN features off-the-shelf: an astounding baseline for recognition［C］. IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2014: 806-813.

[11] Boureau Y L, Bach F, LeCun Y, et al. Learning mid-level features for recognition［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2010: 2559-2566.

[12] Le Q V. Building high-level features using large scale unsupervised learning［C］. IEEE International Conference on Acoustics, Speech and Signal Processing, 2013: 8595-8598.

[13] Bar Y, Diamant I, Wolf L, et al. Chest pathology detection using deep learning with non-medical training［J］. IEEE 12th International Symposium on Biomedical Imaging, 2015: 294-297.

[14] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition［C］. International Conference on Learning Representations, 2015.

[15] Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2818-2826.

[16] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition［C］. IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.

[17] Khan S A, Yong S P. An evaluation of convolutional neural nets for medical image anatomy classification［J］. Advances in Machine Learning and Signal Processing, 2016: 293-303.

[18] 刘大伟, 韩玲, 韩晓勇. 基于深度学习的高分辨率遥感影像分类研究［J］. 光学学报, 2016, 36(4): 0428001.

Liu D W, Han L, Han X Y. High spatial resolution remote sensing image classification based on deep learning［J］. Acta Optica Sinica, 2016, 36(4): 0428001.

[19] 程效军, 郭王, 李泉, 等. 基于强度与颜色信息的地面LiDAR点云联合分类方法［J］. 中国激光, 2017, 44(10): 1010007.

Cheng X J, Guo W, Li Q, et al. Joint classification method for terrestrial LiDAR point cloud based on intensity and color information［J］. Chinese Journal of Lasers, 2017, 44(10): 1010007.

[20] Kitanovski I, Jankulovski B, Dimitrovski I, et al. Comparison of feature extraction algorithms for mammography images［C］. The 4th International Congress on Image and Signal Processing, 2011: 888-892.

[21] Hong J. Gray level-gradient cooccurrence matrix texture analysis method［J］. Acta Automatica Sinica, 1984, 10(1): 22-25.

[22] Galloway M M. Texture analysis using gray level run lengths［J］. Computer Graphics and Image Processing, 1975, 4(2): 172-179.

褚晶辉, 吴泽蕤, 吕卫, 李喆. 基于迁移学习和深度卷积神经网络的乳腺肿瘤诊断系统[J]. 激光与光电子学进展, 2018, 55(8): 081001. Chu Jinghui, Wu Zerui, Lü Wei, Li Zhe. Breast Cancer Diagnosis System Based on Transfer Learning and Deep Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2018, 55(8): 081001.

基于迁移学习和深度卷积神经网络的乳腺肿瘤诊断系统下载： 1503次

关于本站 Cookie 的使用提示

全站搜索

基于迁移学习和深度卷积神经网络的乳腺肿瘤诊断系统 下载： 1503次

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于迁移学习和深度卷积神经网络的乳腺肿瘤诊断系统下载： 1503次