J Shanghai Jiaotong Univ Sci ›› 2025, Vol. 30 ›› Issue (4): 790-799.doi: 10.1007/s12204-024-2761-9
收稿日期:
2023-12-04
接受日期:
2023-12-25
发布日期:
2025-07-31
苗军1,常艺茹1,陈辰2,张茂炫1,刘艳3,齐洪钢3,郭志军4,徐倩5
Received:
2023-12-04
Accepted:
2023-12-25
Published:
2025-07-31
摘要: 针对当前磨玻璃肺结节特征维数高、冗余数据多、单一分类器识别准确率较低的问题,提出了一种基于CatBoost特征选择和Stacking集成学习的磨玻璃肺结节识别方法。该方法首先使用特征选择算法进行重要特征筛选,去除作用较少的特征,达到数据降维的效果;其次,将随机森林、决策树、KNN分类、LightGBM作为基分类器,支持向量机作为元分类器进行集成学习模型的融合和搭建,在保持基分类器多样性的同时提升分类模型的准确率。实验结果显示,所提方法的识别准确率达到94.375%。与单分类器中性能最好的随机森林算法相比,该方法的准确率提高了1.875%。与磨玻璃肺结节识别领域最近的深度学习方法ResNet + GBM + Attention和MVCSNet相比,准确率也获得了提升或者性能可比。实验表明,所提出的模型能够对肺结节进行有效的特征选择和分类识别。
中图分类号:
. 基于CatBoost特征选择和Stacking集成学习的磨玻璃肺结节识别[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(4): 790-799.
Miao Jun, Chang Yiru, Chen Chen, Zhang Maoyuan, Liu Yan, Qi Honggang, Guo Zhijun, Xu Qian. Ground-Glass Lung Nodules Recognition Based on CatBoost Feature Selection and Stacking Ensemble Learning[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(4): 790-799.
[1] AGGARWAL P, VIG R, SARDANA H K. Semantic and content-based medical image retrieval for lung cancer diagnosis with the inclusion of expert knowledge and proven pathology [C]//2013 IEEE Second International Conference on Image Information Processing. Shimla: IEEE, 2013: 346-351. [2] WANG X, MA D. Advances in computer-aided diagnosis in pulmonary nodules [J]. Chinese Journal of Radiology, 2006, 40(4): 443-445 (in Chinese). [3] GAO L, YU X X, KANG B, et al. Predictive value of CT-based radiomics nomogram for the invasiveness of lung pure ground-glass nodules [J]. Journal of Shandong University (Health Science), 2022, 60(5): 87-97 (in Chinese). [4] WAN H Y, LI J, WANG B, et al. Establishment of prediction model for isolated pulmonary benign or malignant nodule by Bayesian network [J]. Journal of Chinese Oncology, 2022, 28(5): 380-384 (in Chinese). [5] CAI J H, DUAN S F, YUAN H, et al. Machine learning in differentiating pulmonary invasive adenocarcinoma from non-invasive adenocarcinoma manifested as pure ground-glass nodule [J]. Chinese Journal of Medical Imaging Technology, 2020, 36(3): 405-410 (in Chinese). [6] MA?KIEWICZ A, RATAJCZAK W. Principal components analysis (PCA) [J]. Computers & Geosciences, 1993, 19(3): 303-342. [7] LIU X F. The clinical value of CT radiomics in the diagnosis of ground-glass pulmonary nodules [D]. Wuhu: Wannan Medical College, 2021 (in Chinese). [8] DAI Y Q, GUO X Y, WANG M, et al. Feature selection of high-dimensional biomedical data based on shuffled frog leaping algorithm [J]. Application Research of Computers, 2021, 38(4): 1062-1068 (in Chinese). [9] DARABI N, REZAI A, HAMIDPOUR S S F. Breast cancer detection using RSFS-based feature selection algorithms in thermal images J]. Biomedical Engineering: Applications, Basis and Communications, 2021, 33(3): 2150020. [10] LI Y F, LUO Y, GUO L, et al. Radiomics analysis and machine learning for classification of benign and malignant pulmonary nodules [J]. Radiologic Practice, 2021, 36(4): 464-469 (in Chinese). [11] MIAO X F, LIU M, JIANG Y. Hepatitis C prediction based on machine learning algorithms [J]. Journal of Jilin University (Information Science Edition), 2022, 40(4): 638-643 (in Chinese). [12] WU T F, ZHANG R S. Research on the application of machine learning in the malignant grinding glass density nodules of lung [J]. Journal of Guangzhou University (Natural Science Edition), 2018, 17(3): 33-39 (in Chinese). [13] CHANG T T, LIU H W, FENG J. Support vector machine ensemble learning algorithm research based on heterogeneous data [J]. Journal of Xidian University, 2010, 37(1): 136-141 (in Chinese). [14] PANG L, LAN W X, WANG Q Q, et al. Machine learning-based survival prediction model for colorectal adenocarcinoma cancer [J]. Modern Preventive Medicine, 2023, 50(2): 227-232 (in Chinese). [15] BARTLETT P, FREUND Y, LEE W S, et al. Boosting the margin: A new explanation for the effectiveness of voting methods [J]. The Annals of Statistics, 1998, 26(5): 1651-1686. [16] CHE X J, YU Y J, LIU Q L, et al. Enhanced Bagging ensemble learning and multi?target detection algorithm [J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(12): 2916-2923 (in Chinese). [17] KUANG J, HONG M J, LIU X C, et al. Classification of pulmonary nodules based on attention mechanism [J]. Computer Applications and Software, 2022, 39(1): 163-167 (in Chinese). [18] ZHU Q K, WANG Y Q, CHU X P, et al. Multi-view coupled self-attention network for pulmonary nodules classification [M]// Computer vision – ACCV 2022. Cham: Springer, 2022: 37-51. [19] KIRA K, RENDELL L. The feature selection problem: Traditional methods and a new algorithm [C]// 10th National Conference on Artificial Intelligence. San Jose: AAAI, 1992: 129-134. [20] HE X Y, GONG J, WANG L J, et al. Feature selection based on feature vectorization on computer tomography scan of pulmonary nodules [J]. Application Research of Computers, 2018, 35(8): 2544-2548 (in Chinese). [21] WANG J, ZHANG X L, ZHAO J J. Feature selection algorithm for diagnostic model of solitary pulmonary nodules [J]. China Sciencepaper, 2014, 9(10): 1201-1205 (in Chinese). [22] DIMITRIADOU E, WEINGESSEL A, HORNIK K. Voting-merging: An ensemble method for clustering [M]// Artificial neural networks — ICANN 2001. Berlin, Heidelberg: Springer, 2001: 217-224. [23] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778. [24] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [J]. Communications of the ACM, 2017, 60(6): 84-90. [25] HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks [C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 2261-2269. |
[1] | . 基于深度学习的肺癌病例文本结构化算法[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(4): 778-789. |
[2] | . 基于表面肌电信号的BP-LSTM混合模型肘部运动实时预测[J]. J Shanghai Jiaotong Univ Sci, 2025, 30(3): 455-462. |
[3] | 刘月笙, 贺宁, 贺利乐, 张译文, 习坤, 张梦芮. 基于机器学习的移动机器人路径跟踪MPC控制器参数自整定[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(6): 1028-1036. |
[4] | 刘文1, 3, 许剑新2, 4, 杨根科1, 3, 陈媛芳5. 基于LSTM-BiDBN入侵检测系统的在线车辆取证责任方认定方法[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(6): 1161-1168. |
[5] | 李明爱1,2,3,许冬芹1. 综述:运动想像脑机接口中的迁移学习[J]. J Shanghai Jiaotong Univ Sci, 2024, 29(1): 37-59. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||