基于拉曼光谱和SVM的乳腺病灶识别模型研究
Breast Disease Recognition Model Research Based on Raman Spectroscopy and Support Vector Machine
DOI: 10.12677/CSA.2020.108160, PDF,    国家自然科学基金支持
作者: 高 婷, 闫 英, 杨春鹏, 贾致真, 胡丽红*：东北师范大学信息科学与技术学院，吉林 长春；张海鹏, 韩 冰*：吉林大学第一医院乳腺外科，吉林 长春
关键词: 计算机应用技术；乳腺癌；拉曼光谱；支持向量机；特征权重；集成学习；Computer Application Technology； Breast Cancer； Raman Spectroscopy； Support Vector Machine； Feature Weighting Algorithms； Ensemble Learning
摘要: 乳腺癌是女性主要癌症之一，若癌细胞进一步转移到骨骼、中枢神经系统和内脏，将会导致预后不良和总体生存率的降低。相比于传统的诊断乳腺肿瘤的病理学方法耗时且破费的特点，拉曼光谱的检测方法损伤较小且诊断周期短。本文利用吉林大学第一医院乳腺外科提供的实验检测样本，建立了新鲜乳腺病灶组织的拉曼光谱数据库，在特征选择的基础上应用支持向量机(SVM)方法构建了乳腺组织良恶性识别模型，并运用集成学习的思想以便快速鉴别乳腺病灶的类型。
Abstract: Breast cancer is one of the leading cancers in women, if the cancer cells further transfer to the bones and internal organs, central nervous system will result in poor prognosis and the overall survival rate lower. Compared with the traditional pathological methods, Raman spectroscopy method is time-consuming and expensive. In this paper, a Raman spectral database of fresh breast lesions was established by using the experimental test samples provided by the department of breast surgery, the first hospital of Jilin University. On the basis of feature selection, a benign and malignant breast tissue recognition model was established by using support vector mechanism as well as ensemble learning in order to quickly identify the types of breast lesions.
文章引用：高婷, 闫英, 杨春鹏, 贾致真, 张海鹏, 胡丽红, 韩冰. 基于拉曼光谱和SVM的乳腺病灶识别模型研究[J]. 计算机科学与应用, 2020, 10(8): 1526-1534. https://doi.org/10.12677/CSA.2020.108160

参考文献

[1] Abigail, S.H., Karen, E.S., Maryann, F., Joseph, C., Ramachandra, R.D. and Michael, S.F. (2005) Diagnosing Breast Cancer by Using Raman Spectroscopy. Proceedings of the National Academy of Sciences of the United States of America, 102, 12371-12376. [Google Scholar] [CrossRef] [PubMed]
[2] Hu, C.X., Wang, J.X., Zheng, C., Xu, S.P., Zhang, H.P., Liang, Y.C., Bi, L.R., Fan, Z.M., Han, B. and Xu, W.Q. (2013) Raman Spectra Exploring Breast Tissues: Comparison of Principal Component Analysis and Support Vector Machine-Recursive Feature Elimination. Medical Physics, 40, 063501-063507. [Google Scholar] [CrossRef] [PubMed]
[3] Hu, C.X., Zheng, C., Zhang, H.P., Bi, L.R., Xu, S.P., Fan, Z.M., Han, B. and Xu, W.Q. (2013) Analysis of Fresh Breast Cancer Tissue by Near Infrated Raman Spectroscopy. Chemical Journal of Chinese Universities, 34, 2721-2727.
[4] Zhao, H.T. and Wong, W.K. (2014) Reg-ularized Discriminant Entropy Analysis. Pattern Recognition, 47, 806-819. [Google Scholar] [CrossRef] 
[5] Xu, L.-P., Ge, L.-Q., Gu, Y., Liu, M., Zhang, Q.-X., Li, F. and Luo, B. (2013) Application of EDXRF Analysis and Determination of Iron and Titanium in Geological Samples Based on PCA-BP Neural Network. Spectroscopy and Spectral Analysis, 33, 1392-1396.
[6] 胡丽娜. 基于改进的数据集划分和离群点检测算法构建乳腺疾病分类模型[D]: [硕士学位论文]. 长春: 东北师范大学, 2019: 1-49.
[7] Xu, H.B. (2014) Can Tamoxifen Become a New Standard for Adjuvant Treatment of Early Breast Cancer in 10 Years? Chi-nese Journal of Medical Guide, 1, 102-102.
[8] Roberto, K.H.G., Mario, C.U.A., Gledson, E.J., Marcio, J.C.P., Edvan, C.S. and Teresa, C.B.S. (2005) A Method for Calibration and Validation Subset Partitioning. Talanta, 67, 736-740. [Google Scholar] [CrossRef] [PubMed]
[9] Kira, K. and Rendell, L. (1992) A Practical Approach to Feature Selection. Machine Learning Proceedings 1992, 249-256. [Google Scholar] [CrossRef] 
[10] 江雨荷, 齐惠颖. 基于多组数据融合的乳腺癌生存预测模型构建[J]. 数据分析与知识发现, 2019(8): 88-93.
[11] Tuia, D., Volpi, M., DallaMura, M., Rakotomamonjy, A. and Flamary, R. (2014) Automatic Feature Learning for Spatio-Spectral Image Classification with Sparse SVM. IEEE Transactions on Geoscience and Remote Sensing, 52, 6062-6074. [Google Scholar] [CrossRef] 
[12] 贾致真. 基于拉曼光谱的乳腺良恶性肿瘤识别模型研究[D]: [硕士学位论文]. 长春: 东北师范大学, 2017.
[13] 崔艳莹. 基于集成学习的有机太阳能电池光电转化效率预测模型研究[D]: [硕士学位论文]. 长春: 东北师范大学, 2019: 1-77.
[14] 侯丽. 基于AdaBoost和深度学习的红外乳腺癌检测方法研究[D]: [硕士学位论文]. 武汉: 华中科技大学2017: 1-92.