To assist pathologists in diagnosing breast tumors, a method was proposed to automatically recognize and analyze breast pathological images by computers. With BreaKHis as data sample, the improved network model of VGG19A was proposed based on the convolutional neural network model of VGG19. By adding BN algorithm before activation function in convolution layer and adding dropconnect layer in full connection layer, the performance of network model was optimized to improve the recognition accuracy of network model. Considering that the transfer learning method could make the network model learn pathological features more fully, the method was introduced into the training of VGG19A network. The network was applied to the recognition of breast pathological images, and PFTAS+QDA, PFTAS+SVM, PFTAS+RF, SingleTask CNN, AlexNet and VGG19 algorithms were used in comparative experiments. The results show that compared with the existing methods, the proposed method can improve the accuracy and generalization performance of image recognition, which has important practical application value.
Key words
breast tumor /
convolutional neural network /
VGG19A network /
BN algorithm /
dropconnect algorithm /
transfer learning
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
［1］MCGUIRE S. World cancer report 2014［J］.Advances in Nutrition, 2016,7(2):418-419.
［2］LECUN Y, BENGIO Y, HINTON G. Deep learning［J］. Nature,2015, 521: 436-444.
［3］WU S T, ZHONG S H, LIU Y. Deep residual learning for image steganalysis［J］. Multimedia Tools and Applications, 2018,77(9): 10437-10453.
［4］何雪英,韩忠义,魏本征.基于深度学习的乳腺癌病理图像自动分类［J］.计算机工程与应用,2018,54(12):121-125.
HE X Y, HAN Z Y, WEI B Z. Breast cancer histopathological image autoclassification using deep learning［J］.Computer Engineering and Applications,2018,54(12):121-125. (in Chinese)
［5］SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for largescale image recognition［DB.OL］.https:∥arxiv.org/abs/1409.1556.
［6］IOFFE S,SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift［C］∥Proceedings of the 32nd International Conference on Machine Learning, 2015.
［7］LIAN Z F, JING X J, WANG X H, et al. Dropconnect regularization method with sparsity constraint for neural networks［J］.Chinese Journal of Electronics: 2016, 25(1):152-158.
［8］阳馨,蒋伟,刘晓玲.基于多种特征池化的中文文本分类算法［J］.四川大学学报(自然科学版),2017,54(2):287-292.
YANG X, JIANG W, LIU X L. Chinese text categorization based on multipooling［J］. Journal of Sichuan University (Natural Science Edition), 2017,54(2): 287-292. (in Chinese)
［9］SPANHOL F A, OLIVEIRA L S, PETITJEAN C, et al. A dataset for breast cancer histopathological image classification［J］. IEEE Transactions on Biomedical Engineering, 2016, 63(7):1455-1462.
［10］SHIN H C, ROTH H R, GAO M C, et al. Deep convolutional neural networks for computeraided detection: CNN architectures, dataset characteristics and transfer learning［J］. IEEE Transactions on Medical Imaging, 2016, 35(5):1285-1298.
［11］张建华,孔繁涛,吴建寨,等.基于改进VGG卷积神经网络的棉花病害识别模型［J］.中国农业大学学报,2018,23(11):161-171.
ZHANG J H, KONG F T, WU J Z, et al. Cotton disease identification model based on improved VGG convolution neural network［J］. Journal of China Agricultural University, 2018, 23(11):161-171. (in Chinese)
［12］孔英会,景美丽.基于混淆矩阵和集成学习的分类方法研究［J］.计算机工程与科学,2012,34(6):111-117.
KONG Y H, JING M L. Research of the classification method based on confusion matrixes and ensemble learning［J］. Computer Engineering and Science, 2012,34(6):111-117. (in Chinese)
{{custom_fnGroup.title_en}}
Footnotes
{{custom_fn.content}}
PDF(2027 KB)
({{custom_author.role_en}}), {{javascript:window.custom_author_en_index++;}}
