改进支持向量机分类方法及其在原发性肝癌筛查中的应用

doi:10.3969/j.issn.0255-8297.2021.03.013

摘要/Abstract

摘要： 为了尽早检测出原发性肝癌患者，辅助医生进行医疗决策，提高患者临床疗效，提出一种基于临床常规检验指标的筛查方法。该方法使用支持向量机建模，采用差异进化算法进行参数优化，以接收者操作特征曲线下面积的值作为模型评价测度，将得到的最优模型用于检验数据识别，以判断该数据属于健康、良性病变还是原发性肝癌。此外，还根据临床需求绘制分类模型的性能指标曲线和阈值查找表，由用户选择阈值，使预测性能进一步提升。实验结果表明：与其他5种分类方法相比，该方法建立的模型具有更好的性能，其准确度可达0.94，Kappa系数可达0.90。研究结果可辅助医生进行原发性肝癌早期筛查，提高患者长期生存率。

关键词: 检验数据, 原发性肝癌检测, 支持向量机, 差异进化, 接收者操作特征曲线下面积

Abstract: To screen out primary liver cancer patients as early as possible, assist doctors to make better decisions and improve treatment effects, an early screening method based on routine laboratory data is proposed. To test the classification of healthy, benign lesions or primary liver cancer, a support vector machine method is optimized by using a differential evolution algorithm, in which the evaluation cost is the area under the ROC (receiver operating characteristic) curve. Moreover, to satisfy different clinical requirements, performance index curves and cut-off lookup tables of the training model are built, then cut-off values are selected by users to further improve the prediction performance. Compared with other 5 state-of-the-art methods, the proposed methods have better classification performance, of which the accuracy reaches 0.944 1, and the Kappa coefficient reaches 0.903 1. The research results can assist doctors to screen out the primary liver cancer early and improve the long-term survival rate of patients.

Key words: laboratory data, primary liver cancer detection, support vector machine (SVM), differential evolution (DE), area under receiver operation characteristic curve (AUC)

中图分类号:

TP391.4

曹国刚, 李梦雪, 陈颖, 曹聪, 王孜怡, 房萌, 高春芳, 刘云翔. 改进支持向量机分类方法及其在原发性肝癌筛查中的应用[J]. 应用科学学报, 2021, 39(3): 481-480.

CAO Guogang, LI Mengxue, CHEN Ying, CAO Cong, WANG Ziyi, FANG Meng, GAO Chunfang, LIU Yunxiang. Classification Method of Improved Support Vector Machine and Its Application in Early Detection of Primary Liver Cancer[J]. Journal of Applied Sciences, 2021, 39(3): 481-480.

参考文献

[1] Lun X Q, Zhao Y T. Recent progresses in predictive biomarkers for metastatic recurrence of human hepatocellular carcinoma: a review of literatures[J]. Journal of Cancer Research and Clinical Oncology, 2004, 130(9): 497-513.
[2] Ji J F, Shi J, Anuradha B, et al. MicroRNA expression, survival, and response to interferon in liver cancer[J]. New England Journal of Medicine, 2009, 361(15): 1437-1447.
[3] Llovet J M, Di Bisceglie A M, Bruix J, et al. Design and endpoints of clinical trials in hepatocellular carcinoma[J]. National Cancer Institute Journal, 2008, 1000(10): 698-711.
[4] 田娟秀, 刘国才, 谷珊珊, 等. 医学图像分析深度学习方法研究与挑战[J]. 自动化学报, 2018, 44(3): 401-424. Tian J X, Liu G C, Gu S S, et al. Deep learning in medical image analysis and its challenges[J]. Acta Automatica Sinica, 2018, 44(3): 401-424. (in Chinese)
[5] 叶萌萌. 基于支持向量机的肝脏肿瘤良、恶性识别研究[D]. 杭州: 浙江大学, 2012.
[6] 刘保魁. CD24蛋白在肝癌患者血浆中的表达及其临床意义[D]. 郑州: 郑州大学, 2013.
[7] 冯茜. Logistic回归和ROC曲线综合评价四种指标对原发性肝癌的诊断价值[J]. 标记免疫分析与临床, 2016, 23(6): 641-644, 664. Feng Q. Comprehensive evaluation of the diagnostic value of four markers for primary hepatic carcinoma by ROC curve and logistic regression[J]. Labeled Immunoassays and Clinical Medicine, 2016, 23(6): 641-644, 664. (in Chinese)
[8] Poynard T, Imbert B F, Munteanu M, et al. Overview of the diagnostic value of biochemical markers of liver fibrosis (fibrotest, HCV fibrosure) and necrosis (actitest) in patients with chronic hepatitis C[J]. Comparative Hepatology, 2004, 3(1): 1-8.
[9] Tao W C, Greenson J K, Fontana R J, et al. A simple noninvasive index can predict both significant fibrosis and cirrhosis in patients with chronic hepatitis C[J]. Hepatology, 2003, 38(2): 518-526.
[10] Azarkhish I, Raoufy M R, Gharibzadeh S. Artificial intelligence models for predicting iron deficiency anemia and iron serum level based on accessible laboratory data[J]. Journal of Medical Systems, 2012, 36(3): 2057-2061.
[11] Fang M, Zhao Y P, Zhou F G, et al. N-glycan based models improve diagnostic efficacies in hepatitis B virus-related hepatocellular carcinoma[J]. International Journal of Cancer, 2009, 127(1): 148-159.
[12] Zhao J Y, Zhao Y P, Wang H, et al. Association between metabolic abnormalities and HBV related hepatocelluar carcinoma in Chinese: a cross-sectional study[J]. Nutrition Journal, 2011, 10(1): 49.
[13] 陈长军, 詹永照, 文传军, 等. 支持向量描述鉴别分析及在人脸识别中的应用[J]. 计算机应用研究, 2010, 27(2): 488-490. Chen C J, Zhan Y Z, Wen C J, et al. Face recognition based on support vector network and relevance feedback[J]. Application Research of Computers, 2010, 27(2): 488-490. (in Chinese)
[14] 夏国恩, 金炜东, 张葛祥. 基于组合特征的手写体数字识别方法[J]. 计算机应用研究, 2006(6): 170-172. Xia G E, Jin W D, Zhang G X. Hand written digit recognition method based on combination features[J]. Application Research of Computers, 2006(6): 170-172. (in Chinese)
[15] 时永刚, 程坤, 刘志文. 结合深度学习和支持向量机的海马子区图像分割[J]. 中国图象图形学报, 2018, 23(4): 542-551. Shi Y G, Cheng K, Liu Z W. Segmentation of hippocampal subfields by using deep learning and support vector machine[J]. Journal of Image and Graphics, 2018, 23(4): 542-551. (in Chinese)
[16] Dina K B, Moch A B, Adiwijaya. On feature augmentation for semantic argument classification of the quran English translation using support vector machine[J]. Journal of Physics: Conference Series, 2018, 971: 012043.
[17] 李素, 袁志高, 王聪, 等. 群智能算法优化支持向量机参数综述[J]. 智能系统学报, 2018, 13(1): 70-84. Li S, Yuan Z G, Wang C, et al. Optimization of support vector machine parameters based on group intelligence algorithm[J]. CAAI Transactions on Intelligent Systems, 2018, 13(1): 70-84. (in Chinese)
[18] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000, 26(1): 36-46. Zhang X G. Introduction to statistical learning theory and support vector machines[J]. Acta Automatica Sinica, 2000, 26(1): 36-46. (in Chinese)
[19] 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. Ding S F, Qi B J, Tan H Y. An overview on theory and algorithm of support vector machines[J]. Journal of University of Electronic Science and Technology of China, 2011, 40(1): 2-10. (in Chinese)
[20] 郭明玮, 赵宇宙, 项俊平, 等. 基于支持向量机的目标检测算法综述[J]. 控制与决策, 2014, 29(2): 193-200. Guo M W, Zhao Y Z, Xiang J P, et al. Review of object detection methods based on SVM[J]. Control and Decision, 2014, 29(2): 193-200. (in Chinese)
[21] 张扬, 赵治栋, 叶海慧. 基于遗传算法和最小二乘支持向量机的胎儿状态智能评估[J]. 生物医学工程学杂志, 2019, 36(1): 131-139. Zhang Y, Zhao Z D, Ye H H. Intelligent fetal state assessment based on genetic algorithm and least square support vector machine[J]. Journal of Biomedical Engineering, 2019, 36(1): 131-139. (in Chinese)
[22] Li C B, Lin S S, Xu F Q, et al. Short-term wind power prediction based on data mining technology and improved support vector machine method: a case study in Northwest China[J]. Journal of Cleaner Production, 2018, 205(5): 909-922.
[23] Cao G G, Cao C, Qing Z, et al. Differential evolution improved with intelligent mutation operator based on proximity and ranking[C]// Proceedings of the 11th International Symposium on Computational Intelligence and Design, Piscataway, 2018: 196-201.
[24] 曹国刚, 张晴, 张培君, 等. 基于多核并行化差异进化算法的图像配准方法[J]. 计算机工程与应用, 2017, 53(20): 166-172. Cao G G, Zhang Q, Zhang P J, et al. Multicore-based parallelized differential evolution for image registration[J]. Computer Engineering and Applications, 2017, 53(20): 166-172. (in Chinese)
[25] Storn R, Price K. Differential evolution: a simple and efficient heuristic for global optimization over continuous spaces[J]. Journal of Global Optimization, 1997, 11(4): 341-359.
[26] Dragoi E N, Dafinescu V, et al. Parameter control and hybridization techniques in differential evolution: a survey[J]. Artificial Intelligence Review, 2016, 45(4): 447-470.
[27] Das S, Mullick S S, Suganthan P N. Recent advances in differential evolution – an updated survey[J]. Swarm and Evolutionary Computation, 2016, 27(2): 1-30.
[28] 戴小也, 於鑫慧, 饶中钰. 基于近红外光谱技术的猪肉品质检测应用研究[J]. 红外, 2018, 39(9): 22-26, 48. Dai X Y, Yu X H, Rao Z Y. Research on application of pork quality detection based on near infrared spectroscopy[J]. Infrared, 2018, 39(9): 22-26, 48. (in Chinese)