基于原型的乳腺癌病理图像分类算法
Algorithm for Breast Cancer Histopathological Image Classification with Prototypes
摘要: 乳腺癌病理图像的自动分类是开发乳腺癌计算机辅助诊断系统的关键。针对乳腺肿瘤病理图像的特点，提出了一种基于LBP原型的特征提取方法，首先，随机地从训练图像中选取若干子图像作为原型并提取其LBP特征；其次，对于任意输入图像，计算图像中所有和原型同样大小的子图像和原型的LBP特征的余弦距离，然后，通过池化操作得到最终的特征；最后，利用SVM集成的方法对图像进行分类。在BreakHis数据集上对算法进行了验证，结果表明，本文提出的特征提取方法优于一些传统的方法。
Abstract: Automatic classification of breast cancer pathological images is the key to the development of computer-aided diagnosis system for breast cancer. According to the characteristics of breast tumor pathological images, a feature extraction method based on LBP prototypes was proposed. Firstly, some sub-images were randomly selected from the training images as prototypes and their LBP features were extracted. Secondly, for arbitrary input images, the cosine distances between the LBP features of all sub-images of the same size and those of the prototypes were calculated, and then, the final features were obtained by pooling operation. Finally, the images were classified by integration of SVMs. Algorithm is verified on the BreakHis dataset. The experimental results show that the proposed feature extraction method is superior to some traditional methods.
文章引用：陈霧, 穆国旺. 基于原型的乳腺癌病理图像分类算法[J]. 计算机科学与应用, 2021, 11(2): 277-284. https://doi.org/10.12677/CSA.2021.112028

参考文献

[1] Boyle, P. and Levin, B. (2008) World Cancer Report 2008. Tech. Rep., International Agency for Research on Cancer, Lyon.
[2] Gurcan, M.N., Boucheron, L.E., Can, A., et al. (2009) Histopathological Image Analysis: A Review. IEEE Reviews in Biomedical Engineering, 2, 147-171. [Google Scholar] [CrossRef] 
[3] Desir, C., Petitjean, C., Heutte, L., et al. (2012) Classification of Endomicroscopic Images of the Lung Based on Random Subwin-dows and Extra-Trees. IEEE Transactions on Biomedical Engineering, 59, 2677-2683. [Google Scholar] [CrossRef] 
[4] Arevalo, J., Gonzalez, F.A., Ramospollan, R., et al. (2015) Convolutional Neural Networks for Mammography Mass Lesion Classification. International Conference of the IEEE Engineering in Medicine and Biology Society, Milano, 25-29 August 2015, 797-800. [Google Scholar] [CrossRef] 
[5] Nejad, E.M., Affendey, L.S., Latip, R.B., et al. (2017) Classifi-cation of Histopathology Images of Breast into Benign and Malignant Using a Single-Layer Convolutional Neural Net-work. In: Proceedings of the International Conference on Imaging, Signal Processing and Communication, ACM, New York, 50-53. [Google Scholar] [CrossRef] 
[6] Araujo, T., Aresta, G., Castro, E., et al. (2017) Classification of Breast Cancer Histology Images Using Convolutional Neural Networks. PLoS ONE, 12, e0177544. [Google Scholar] [CrossRef] [PubMed]
[7] Zheng, Y., Jiang, Z., Xie, F., et al. (2017) Feature Extraction from Histopathological Images Based on Nucleus-Guided Convolutional Neural Network for Breast Lesion Classifica-tion. Pattern Recognition, 71, 14-25. [Google Scholar] [CrossRef] 
[8] Spanhol, F.A., Oliveira, L.S., Cavalin, P.R., et al. (2017) Deep Features for Breast Cancer Histopathological Image Classification. Systems, Man and Cybernetics, Banff, 5-8 October 2017, 1868-1873. [Google Scholar] [CrossRef] 
[9] Doyle, S., Agner, S., Madabhushi, A., et al. (2008) Automated Grading of Breast Cancer Histopathology Using Spectral Clustering with Textural and Architectural Image Features. 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, Paris, 14-17 May 2008, 496-499. [Google Scholar] [CrossRef] 
[10] Wang, P., Hu, X., Li, Y., et al. (2016) Automatic Cell Nuclei Segmentation and Classification of Breast Cancer Histopathology Images. Signal Processing, 122, 1-13. [Google Scholar] [CrossRef] 
[11] Spanhol, F.A., Oliveira, L.S., Petitjean, C., et al. (2015) A Da-taset for Breast Cancer Histopathological Image Classification. IEEE Transactions on Bio-Medical Engineering, 63, 1455-1462. [Google Scholar] [CrossRef] 
[12] Cruzroa, A., Ovalle, J.E., Madabhushi, A., et al. (2013) A Deep Learning Architecture for Image Representation, Visual Interpretability and Automated Basal-Cell Carcinoma Cancer De-tection. Medical Image Computing and Computer Assisted Intervention, Nagoya, 22-26 September 2013, 403-410. [Google Scholar] [CrossRef] [PubMed]
[13] Gupta, V. and Bhavsar, A. (2017) Breast Cancer Histopatho-logical Image Classification: Is Magnification Important. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, 21-26 July 2017, 17-24. [Google Scholar] [CrossRef] 
[14] Shukla, K.K., Tiwari, A. and Sharma, S. (2017) Classification of Histopathological Images of Breast Cancerous and Non Cancerous Cells Based on Morphological Features. Biomedical and Pharmacology Journal, 10, 353-366. [Google Scholar] [CrossRef] 
[15] Pimkin, A., Makarchuk, G., Kondratenko, V., et al. (2018) Ensembling Neural Networks for Digital Pathology Images Classification and Segmentation. International Conference Image Analy-sis and Recognition, Póvoa de Varzim, 27-29 June 2018, 877-886. [Google Scholar] [CrossRef] 
[16] Marami, B., Prastawa, M., Chan, M., et al. (2018) Ensemble Network for Region Identification in Breast Histopathology Slides. International Conference Image Analysis and Recog-nition, Póvoa de Varzim, 27-29 June 2018, 861-868. [Google Scholar] [CrossRef] 
[17] Ojala, T., Pietikäinen, M. and Mäenpää, T. (2002) Multireso-lution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Transactions on Pat-tern Analysis & Machine Intelligence, 24, 971-987. [Google Scholar] [CrossRef]