Colorectal Cancer Diagnostic Algorithm Based on Sub-Patch Weight Color Histogram in Combination of Improved Least Squares Support Vector Machine for Pathological Image

• Published in: Journal of medical systems Vol. 43; no. 9; pp. 306 - 9
• Main Authors: Yang, Kai, Zhou, Bi, Yi, Fei, Chen, Yan, Chen, Yingsheng
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2019; Springer Nature B.V
• Subjects: Algorithms; Cancer; Classification; Colon; Colon cancer; Color; Colorectal cancer; Colorectal carcinoma; Colorectal Neoplasms - diagnosis; Colorectal Neoplasms - pathology; Cytodiagnosis - methods; Diagnostic systems; Distributed Analytics and Deep Learning in Health Care; Feature extraction; Health Informatics; Health Sciences; Histograms; Humans; Image & Signal Processing; Image classification; Image Processing, Computer-Assisted - methods; Kernels; Least squares; Magnetic Resonance Imaging - methods; Medical diagnosis; Medical imaging; Medicine; Medicine & Public Health; Morlet wavelet; Pattern Recognition, Automated - methods; Statistics for Life Sciences; Support Vector Machine; Support vector machines; Weight; Pathological image; Colon cancer; Morlet wavelet; Diagnostic; Color histogram; Support vector machine; RelicfF strategy; Sub-patch weight
• ISSN: 0148-5598; 1573-689X; 1573-689X
• DOI: 10.1007/s10916-019-1429-8

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.