Colorectal Cancer Diagnostic Algorithm Based on Sub-Patch Weight Color Histogram in Combination of Improved Least Squares Support Vector Machine for Pathological Image
- 26 Downloads
In order to improve the diagnostic accuracy of colon cancer, a novel classification algorithm based on sub-patch weight color histogram and improved SVM is proposed, which has good approximation ability for complex pathological image. Our proposed algorithm combines wavelet kernel SVM with color histogram to classify pathological image. Firstly, the pathological image is divided into non-overlapping sub-patches, and the features of sub-patch histogram are extracted. Then, the global and local features are fused by the sub-patch weighting algorithm. Then, the RelicfF based forward selection algorithm is used to integrate color features and texture features so as to enhance the characterization capabilities of the tumor cell. Finally, Morlet wavelet kernel-based least squares support vector machine method is adopted to enhance the generalization ability of the model for small sample with non-linear and high-dimensional pattern classification problems. Experimental results show that the proposed pathological diagnostic algorithm can gain higher accuracy compared with existing comparison algorithms.
KeywordsColon cancer Pathological image Diagnostic Color histogram Morlet wavelet Support vector machine Sub-patch weight RelicfF strategy
This study is supported by the National Natural Science Foundation of China (No.81571773, 81781771943 81771943), Shanghai municipal health and Family Planning Commission (No.201640191).
Compliance with ethical standards
Conflict of interest
We declare that we have no conflict of interest.
Human or animals participants
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed consent was obtained from all individual participants included in the study.
- 1.Hong, Y., Wei, H, and Zeng-Li, L., Research for the colon cancer based on the EMD and LS-SVM[C]. Fourth International Conference on Intelligent Computation Technology & Automation. IEEE Computer Society, 24(7):329-331, 2011.Google Scholar
- 4.Mizaku, A, and Land, W. H., Biomolecular feature selection of colorectal cancer microarray data using GA-SVM hybrid and noise perturbation to address overfitting[J]. Dissertations & Theses -Gradworks, 12(1):64-76, 2009.Google Scholar
- 7.Shi, W., Dongkai, J., Ke, W., Application of modified wavelet features and multi-class sphere SVM to pathological vocal detection[C]. Seventh International Conference on Natural Computation. IEEE, pp:1290-1298, 2011.Google Scholar
- 8.Majhi, B., Dash, R., and Nayak, D. R., Stationary wavelet transform and AdaBoost with SVM based pathological brain detection in MRI scanning[J]. CNS Neurol. Disord. Drug Targets 16(2):32-44, 2017.Google Scholar
- 9.Cataldo, S. D., Ficarra, E., and Macii, E., Automated discrimination of pathological regions in tissue images: Unsupervised clustering vs. supervised SVM classification[C]. International Joint Conference on Biomedical Engineering Systems and Technologies. Springer, Berlin, Heidelberg, pp:2100-2111, 2008.Google Scholar
- 10.Cataldo,Wang S, Huo J, et al. Bayesian Framework with Non-local and Low-rank Constraint for Image Reconstruction[C]// Journal of Physics Conference Series. pp:1-11, 2017.Google Scholar
- 13.Xia, Kai Jian, H. S. Yin, and J. Q. Wang. "A novel improved deep convolutional neural network model for medical image fusion." Cluster Computing, 23(20):1-13, 2018.Google Scholar
- 14.Song, B., Zhang, G., Wang, H., et al., A feasibility study of high order texture features with application to pathological diagnosis of colon lesions for CT Colonography[C]. Nuclear Science Symposium & Medical Imaging Conference. IEEE, 2013.Google Scholar
- 17.Wang, C., Guan, Y., Zuo, C., et al., Value of the texture feature for solitary pulmonary nodules and mass lesions based on PET/CT[C]. International Conference on Bioinformatics & Biomedical Engineering. 2010.Google Scholar
- 18.Song, B., Zhang, G., Zhu, H., et al., A feasibility study of high order volumetric texture features for computer aided diagnosis of polyps via CT colonography[C]. Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC). pp:719-724, 2012.Google Scholar
- 21.Jiang, X., Liang, Q., and Shen, T., A new color information entropy retrieval method for pathological cell image[C]// Computer & Computing Technologies in Agriculture Iv-ifip Tc 12 Conference. 0.Google Scholar
- 22.Jiang, X., Liang, Q., and Shen, T., A new color information entropy retrieval method for pathological cell image[J]. Computer and Computing Technologies in Agriculture IV, 22(12):872-880, 2016.Google Scholar
- 23.Xia K J, Yin H S, Zhang Y D. Deep Semantic Segmentation of Kidney and Space-Occupying Lesion Area Based on SCNN and ResNet Models Combined with SIFT-Flow Algorithm[J]. Journal of Medical Systems, 2019, 43(1):2.Google Scholar
- 24.Sammouda, M, and Mukai, K., Diagnosis of liver cancer based on the analysis of pathological liver color images[C]. Medical Imaging: Image Processing. International Society for Optics and Photonics, pp:12-21, 2000.Google Scholar
- 25.Malekian, V., Mokhtari, M., Sadri, S., et al., Detection of collagenous colitis based on histopathology image segmentation of colon[C]// Iranian Conference on Machine Vision & Image Processing. IEEE, 2011.Google Scholar
- 30.Jin, Y., Fayad, L., and Laine, A. F., Contrast enhancement by multi-scale adaptive histogram equalization[J]. Proc. SPIE Int. Soc. Opt. Eng. 4478:206–213, 2001.Google Scholar