Discriminative Feature-oriented Dictionary Learning Method With Fisher Criterion for Histopathological Image Classification
-
摘要: 针对当前面向组织病理图像特征提取的字典学习方法中存在着学习的无病字典与有病字典相似程度高，判别性弱的问题，本文提出一种新的面向判别性特征字典学习方法（Discriminative feature-oriented dictionary learning based on Fisher criterion，FCDFDL）.该方法基于Fisher准则构造目标函数的惩罚项，最小化学习字典的类内距离与最大化学习字典的类间距离，大大降低无病字典与有病字典间的相似性.同时，优化学习字典对同类样本的重构性能，并约束学习字典对非同类样本的重构性能.然后，利用本文学习的无病与有病字典对测试样本进行稀疏表示，采用重构误差向量的统计量构造分类器.最后，分别在ADL数据集与BreaKHis数据集上验证了本文方法的有效性.实验结果表明，本文学习字典的判别性更强，获得了更优的分类性能.Abstract: The problem of high similarity between learned healthy dictionary and diseased dictionary and low discrimination exists in the current dictionary learning methods for histopathological image feature extraction. In this paper, we present a novel discriminative feature-oriented dictionary learning method based on Fisher criterion (FCDFDL). This method constructs a penalty item of the objective function using Fisher criterion to minimize the intra-class distance of learned dictionaries and maximize the inter-class distance of learned dictionaries. Thus, the similarity between healthy and diseased dictionaries is reduced. Furthermore, the reconstruction of the same class samples is improved over the learned dictionaries, while reconstruction of different class samples is suppressed. Then, the sparse representation of test samples is respectively performed on the learned healthy dictionary and the diseased dictionary, and the classifier is constructed by employing the reconstruction error vector of test samples. Finally, the proposed FCDFDL is tested on ADL and BreaKHis datasets, and experimental results show that the learned dictionaries have stronger discrimination and improved classification performance as compared to the other dictionary learning methods, for histopathological image.
-
Key words:
- Histopathological image /
- Fisher criterion /
- dictionary learning /
- discriminative feature
1) 本文责任编委 张道强 -
图 3 FCDFDL, DFDL, FDDL, LC-KSVD方法学习字典的可视图
Fig. 3 The visual maps of learned dictionaries with FCDFDL, DFDL, FDDL, and LC-KSVD method
图 5 参数$\alpha $, $\beta $的变化对不同病理图像分类精度的影响
Fig. 5 Classification accuracy with different parameters $\alpha $, $\beta $ on different pathological images
图 6 FCDFDL方法下图块尺寸的变化对不同病理图像分类精度的影响
Fig. 6 Classification accuracy on different pathological images with different image block size, and with FCDFDL method
表 1 不同方法在肺部图像的分类结果对比
Table 1 Classification results comparison of different methods on lung images
The class of samples Health Diseased Method 0.8875 0.1125 WND-CHARM 0.7250 0.2750 SRC Healthy samples 0.7500 0.2500 SHIRC 0.7703 0.2297 LC-KSVD 0.9325 0.0675 FDDL 0.9234 0.0766 DFDL 0.9509 0.0491 FCDFDL 0.3762 0.6238 WND-CHARM 0.2417 0.7583 SRC Diseased samples 0.15 0.85 SHIRC 0.1607 0.8393 LC-KSVD 0.1000 0.9000 FDDL 0.0576 0.9424 DFDL 0.0375 0.9625 FCDFDL 
下载: 导出CSV
表 2 不同方法在脾脏图像的分类结果对比
The class of samples Health Diseased Method 0.5512 0.4488 WND-CHARM 0.7083 0.2917 SRC 0.6500 0.3500 SHIRC Healthy samples 0.8193 0.1807 LC-KSVD 0.8694 0.1306 FDDL 0.8999 0.1001 DFDL 0.9064 0.0936 FCDFDL 0.1275 0.8725 WND-CHARM 0.2083 0.7917 SRC 0.1167 0.8833 SHIRC Diseased samples 0.1457 0.8543 LC-KSVD 0.0857 0.9143 FDDL 0.0599 0.9401 DFDL 0.0409 0.9591 FCDFDL
下载: 导出CSV
表 3 不同方法在肾脏图像的分类结果对比
Table 3 Classification results comparison of different methods on kidney images
The class of samples Healthy Diseased Method 0.6925 0.3075 WND-CHARM 0.7910 0.2090 SRC 0.811 0.189 SHIRC Healthy samples 0.8215 0.1785 LC-KSVD 0.8409 0.1591 FDDL 0.8723 0.1277 DFDL 0.8809 0.1191 FCDFDL 0.2812 0.7188 WND-CHARM 0.2220 0.7780 SRC 0.1946 0.8054 SHIRC Diseased samples 0.1857 0.8143 LC-KSVD 0.1971 0.8029 FDDL 0.1405 0.8595 DFDL 0.1311 0.8689 FCDFDL
下载: 导出CSV
表 4 不同方法在BreaKHis数据库上的分类结果对比
Table 4 Classification results comparison of different methods on BreaKHis dataset
The class of samples Adenosis Phyllodes tumor Method 0.7225 0.2775 WND-CHARM 0.7875 0.2125 SRC Adenosis samples 0.8775 0.1225 SHIRC 0.8921 0.1079 LC-KSVD 0.8896 0.1104 FDDL 0.9057 0.0943 DFDL 0.9385 0.0615 FCDFDL 0.3192 0.6808 WND-CHARM 0.2925 0.7075 SRC Phylldes tumor samples 0.2875 0.7125 SHIRC 0.1422 0.8578 LC-KSVD 0.1047 0.8953 FDDL 0.0924 0.9076 DFDL 0.0723 0.9277 FCDFDL
下载: 导出CSV
-
[1] Gurcan M N, Boucheron L E, Can A, Madabhushi A, Rajpoot N M, Yener B. Histopathological image analysis:a review. IEEE Reviews in Biomedical Engineering, 2009, 2:147-171 doi: 10.1109/RBME.2009.2034865 [2] McCann M T, Ozolek J A, Castro C A, Parvin B, Kovacevic J. Automated histology analysis:opportunities for signal processing. IEEE Signal Processing Magazine, 2015, 32(1):78-87 doi: 10.1109/MSP.2014.2346443 [3] Madabhushi A, Lee G. Image analysis and machine learning in digital pathology:challenges and opportunities. Medical Image Analysis, 2016, 33:170-175 doi: 10.1016/j.media.2016.06.037 [4] Dundar M M, Badve S, Bilgin G, Raykar V, Jain R, Sertel O, Gurcan M N. Computerized classification of intraductal breast lesions using histopathological images. IEEE Transactions on Biomedical Engineering, 2011, 58(7):1977-1984 doi: 10.1109/TBME.2011.2110648 [5] Tabesh A, Teverovskiy M, Pang H Y, Kumar V P, Verbel D, Kotsianti A, Saidi O. Multifeature prostate cancer diagnosis and Gleason grading of histological images. IEEE Transactions on Medical Imaging, 2007, 26(10):1366-1378 doi: 10.1109/TMI.2007.898536 [6] Doyle S, Agner S, Madabhushi A, Feldman M, Tomaszewski J. Automated grading of breast cancer histopathology using spectral clustering with textural and architectural image features. In: Proceedings of the 5th IEEE International Symposium on Biomedical Imaging: from Nano to Macro. Paris, France: IEEE, 2008. 496-499 [7] Li W Q, Coats M, Zhang J G, McKenna S J. Discriminating dysplasia:optical tomographic texture analysis of colorectal polyps. Medical Image Analysis, 2015, 26(1):57-69 doi: 10.1016/j.media.2015.08.002 [8] Linder N, Konsti J, Turkki R, Rahtu E, Lundin M, Nordling S, Haglund C, Ahonen T, Pietikäinen M, Lundin J. Identification of tumor epithelium and stroma in tissue microarrays using texture analysis. Diagnostic Pathology, 2012, 7(1):22 doi: 10.1186/1746-1596-7-22 [9] Al-Kadi O S. Texture measures combination for improved meningioma classification of histopathological images. Pattern Recognition, 2015, 43(6):2043-2053 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=JJ0215850394 [10] Irshad H, Jalali S, Roux L, Racoceanu D, Hwee L J, Le Naour G, Capron F. Automated mitosis detection using texture, SIFT features and HMAX biologically inspired approach. Journal of Pathology Informatics, 2013, 4(S2):S12 http://d.old.wanfangdata.com.cn/OAPaper/oai_pubmedcentral.nih.gov_3678748 [11] Ergin S, Kilinc O. A new feature extraction framework based on wavelets for breast cancer diagnosis. Computers in Biology and Medicine, 2014, 51:171-182 doi: 10.1016/j.compbiomed.2014.05.008 [12] Wright J, Yang A Y, Ganesh A, Sastry S S, Ma Y. Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227 doi: 10.1109/TPAMI.2008.79 [13] Srinivas U, Mousavi H, Jeon C, Monga V, Hattel A, Jayarao B. SHIRC: a simultaneous sparsity model for histopathological image representation and classification. In: Proceedings of the 10th IEEE International Symposium on Biomedical Imaging (ISBI). Asilomar, CA, USA: IEEE, 2013. 1118-1121 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6556675 [14] Srinivas U, Mousavi H S, Monga V, Hattel A, Jayarao B. Simultaneous sparsity model for histopathological image representation and classification. IEEE Transactions on Medical Imaging, 2014, 33(5):1163-1179 doi: 10.1109/TMI.2014.2306173 [15] Nayak N, Chang H, Borowsky A, Spellman P, Parvin B. Classification of tumor histopathology via sparse feature learning. In: Proceedings of the 10th IEEE International Symposium on Biomedical Imaging (ISBI). Asilomar, CA, USA: IEEE, 2013. 410-413 http://ieeexplore.ieee.org/document/6556499/ [16] Chang H, Zhou Y, Spellman P, Parvin B. Stacked predictive sparse coding for classification of distinct regions in tumor histopathology. In: Proceedings of the 2013 IEEE International Conference on Computer Vision (ICCV). Sydney, NSW, Australia: IEEE, 2013. 169-176 http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6751130&filter%3DAND(p_IS_Number%3A6751100) [17] Chang H, Zhou Y, Borowsky A, Barner K, Spellman P, Parvin B. Stacked predictive sparse decomposition for classification of histology sections. International Journal of Computer Vision, 2015, 113(1):3-18 doi: 10.1007/s11263-014-0790-9 [18] Shi J, Li Y, Zhu J, Sun H J, Cai Y. Joint sparse coding based spatial pyramid matching for classification of color medical image. Computerized Medical Imaging and Graphics, 2015, 41:61-66 doi: 10.1016/j.compmedimag.2014.06.002 [19] Zhou Y, Chang H, Barner K, Spellman P, Parvin B. Classification of histology sections via multispectral convolutional sparse coding. In: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Columbus, OH, USA: IEEE, 2014. 3081-3088 http://dl.acm.org/citation.cfm?id=2679600.2680188 [20] Shi Y H, Gao Y, Yang Y B, Zhang Y, Wang D. Multimodal sparse representation-based classification for lung needle biopsy images. IEEE Transactions on Biomedical Engineering, 2013, 60(10):2675-2685 doi: 10.1109/TBME.2013.2262099 [21] Xu J, Xiang L, Liu Q S, Gilmore H, Wu J Z, Tang J H, Madabhushi A. Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE Transactions on Medical Imaging, 2016, 35(1):119-130 doi: 10.1109/TMI.2015.2458702 [22] Zhang X F, Dou H, Ju T, Xu J, Zhang S T. Fusing heterogeneous features from stacked sparse autoencoder for histopathological image analysis. IEEE Journal of Biomedical and Health Informatics, 2016, 20(5):1377-1383 doi: 10.1109/JBHI.2015.2461671 [23] 汤红忠, 张小刚, 陈华, 程炜, 唐美玲.带边界条件约束的非相干字典学习方法及其稀疏表示.自动化学报, 2015, 41(2):312-319 http://www.aas.net.cn/CN/abstract/abstract18610.shtmlTang Hong-Zhong, Zhang Xiao-Gang, Chen Hua, Cheng Wei, Tang Mei-Ling. Incoherent dictionary learning method with border condition constrained for sparse representation. Acta Automatica Sinica, 2015, 41(2):312-319 http://www.aas.net.cn/CN/abstract/abstract18610.shtml [24] 文伟, 王英华, 冯博, 刘宏伟.基于监督非相干字典学习的极化SAR图像舰船目标检测.自动化学报, 2015, 41(11):1926-1940 http://www.aas.net.cn/CN/abstract/abstract18767.shtmlWen Wei, Wang Ying-Hua, Feng Bo, Liu Hong-Wei. Supervised incoherent dictionary learning for ship detection with PolSAR images. Acta Automatica Sinica, 2015, 41(11):1926-1940 http://www.aas.net.cn/CN/abstract/abstract18767.shtml [25] Zhang Q, Li B X. Discriminative K-SVD for dictionary learning in face recognition. In: Proceedings of the 2010 IEEE Computer Vision and Pattern Recognition. San Francisco, CA, USA: IEEE, 2010. 2691-2698 [26] Jiang Z L, Lin Z, Davis L S. Label consistent K-SVD:learning a discriminative dictionary for recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(11):2651-2664 doi: 10.1109/TPAMI.2013.88 [27] Yang M, Zhang L, Feng X C, Zhang D. Fisher discrimination dictionary learning for sparse representation. In: Proceedings of the 2011 IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain: IEEE, 2011. 543-550 http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6126286 [28] 潘宗序, 禹晶, 胡少兴, 孙卫东.基于多尺度结构自相似性的单幅图像超分辨率算法.自动化学报, 2014, 40(4):594-603 http://www.aas.net.cn/CN/abstract/abstract18325.shtmlPan Zong-Xu, Yu Jing, Hu Shao-Xing, Sun Wei-Dong. Single image super resolution based on multi-scale structural self-similarity. Acta Automatica Sinica, 2014, 40(4):594-603 http://www.aas.net.cn/CN/abstract/abstract18325.shtml [29] Vu T H, Mousavi H S, Monga V, Rao U K A, Rao G. DFDL: discriminative feature-oriented dictionary learning for histopathological image classification. In: Proceedings of the 12th International Symposium on Biomedical Imaging (ISBI). New York, NY, USA: IEEE, 2015. 990-994 http://cn.arxiv.org/abs/1502.01032 [30] Tropp J A, Gilbert A C. Signal recovery from random measurements via orthogonal matching pursuit. IEEE Transactions on Information Theory, 2007, 53(12):4655-4666 doi: 10.1109/TIT.2007.909108 [31] Animal Diagnostic Laboratory. Safeguarding animal and human health and facilitating animal agricultureOnline, available: http://vbs.psu.edu/adl, December 12, 2017 [32] Spanhol F A, Oliveira L S, Petitjean C, Heutte L. A dataset for breast cancer histopathological image classification. IEEE Transactions on Biomedical Engineering, 2016, 63(7):1455-1462 doi: 10.1109/TBME.2015.2496264 [33] Orlov N, Shamir L, Macura T, Johnston J, Eckley D M, Goldberg I G. WND-CHARM:multi-purpose image classification using compound image transforms. Pattern Recognition Letters, 2008, 29(11):1684-1693 doi: 10.1016/j.patrec.2008.04.013 -
图(6) / 表(4)
计量
- 文章访问数: 1918
- HTML全文浏览量: 364
- PDF下载量: 531
- 被引次数: 0
