Prognostic information extract from CT images of patients with liver cancer using two-dimensional lattice complexity
WU Ruixia1, ZHANG Zirui1, CHEN Yubin1, YE Suzhe1, Zheng Minghua2, KE Daguan1.
1.School of Biomedical Engineering, Wenzhou Medical University, Wenzhou, 325035; 2.Department of Hepatology, the First Affiliated Hospital of Wenzhou Medical University, Wenzhou, 325015
WU Ruixia,ZHANG Zirui,CHEN Yubin, et al. Prognostic information extract from CT images of patients with liver cancer using two-dimensional lattice complexity[J]. JOURNAL OF WEZHOU MEDICAL UNIVERSITY, 2018, 48(6): 396-400.
Abstract：Objective: To verify whether the two-dimensional (2-D) lattice complexity algorithm can effectively extract hidden prognostic information in some medical images. Methods: The preoperative abdominal CT images of 92 patients with hepatocellular carcinoma (HCC) were converted into binary images with a size of 32×32 pixels and then into one-dimensional binary symbolic sequence by using two-dimensional Hilbert curves for calculating lattice complexity. All cases were scanned by support vector machine (SVM) for 10-fold cross-validation to select the best characteristics. And then, based on the characteristics of 46 patients, a classification model was established to identify the pattern recognition of other 46 patients’ survival period. Results: When using 28 images for each patient, the best average accuracy of classification in 10-fold cross-validation was 75.0% with the lattice complexity under the control parameter 19. For the 46 patients, the test accuracy was 69.6%. Conclusion: With 2-D lattice complexity, we could extract from CT images some prognostic information not previously captured.
[1] BISHOP C M. Pattern recognition and machine learning[M]. New York: Springer International Publishing AG, 2006.
[2] LANZARINI L C, DE GIUSTI A E. Pattern recognition in medical images using neural networks[J]. J Comput Sci Technol, 2001, 1(4): 45-54.
[3] NAGARAJ S, RAO G N, KOTESWARARAO K, et al. The role of pattern recognition in computer-aided diagnosis and computer-aided detection in medical imaging: a clinical val-idation[J]. Int J Comput Appl, 2010, 8(5): 18-22.
[4] GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: Images are more thanpictures, they are data[J]. Radiology, 2016, 278(2): 563-577.
[5] 柯大观, 张宏, 童勤业. 格子复杂性和符号序列的细粒化[J]. 物理学报,2005, 54(2): 534-542.
[6] KE D G, TONG Q Y. Easily adaptable complexity measure for finite time series[J]. Phys Rev E, 2008, 77(6 pt 2): 066215.
[7] KE D G. Unifying complexity and information[J]. Sci Rep, 2013, 3: 1585
[8] 刘军, 邹倩, 柯大观, 等. 基于脑电格子复杂性分析的麻醉深度监测研究[J]. 传感技术学报, 2015, 28(12): 1747-1753.
[9] QIAO G, LI J, HUANG A, et al. Artificial neural networking model for the prediction of post-hepatectomy survival of patients with early hepatocellular carcinoma[J]. J Gastroen Hepato, 2014, 29(12): 2014-2020.
[10] SAGAN H. Hilbert’s space-filling curve[M]. New York: Springer International Publishing AG, 1994: 9-30.
[11] BUTZ A R. Alternative algorithm for Hilbert’s space-filling curve[J]. IEEE T Comput, 1971, 20(4): 424-426.
[12] LANGTON C G. Computation at the edge of chaos: Phase-transitions and emergent computation[J]. Physica D, 1990, 42 (1): 12-37.
[13] ANANOS G F J, TSALLIS C. Ensemble averages and nonextensivity at the edge of chaos of one-dimensional maps[J]. Phys Rev Lett, 2004, 93: 020601.
[14] 丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011, 40(1): 2-10.
[15] CHANG C, LIN C. LIBSVM: A library for support vector machines[J]. ACMT Intell Syst Technol, 2011, 2(3): 1-27.
[16] NUNES J, BOUAOUNE Y, DELECHELLE E, et al. Image analysis by bidimensional empirical mode decomposition[J]. Image Vision Comput, 2003, 21(12): 1019-1026.
