基于影像组学与集成学习的脑胶质瘤分级预测
PDF下载 (286)戴 宏,符冉迪,金 炜.基于影像组学与集成学习的脑胶质瘤分级预测[J].宁波大学学报(理工版),2021,34(4):28-34.DOI:
DAI Hong,FU Randi,JIN Wei.Glioma grading prediction based on radiomics and ensemble learning[J].Journal of Ningbo University(Natural Science & Engineering Edition),2021,34(4):28-34.DOI:
| Title: | Glioma grading prediction based on radiomics and ensemble learning |
| 作者: | 戴 宏, 符冉迪, 金 炜 |
| Author(s): | DAI Hong, FU Randi, JIN Wei |
| 关键词: | 脑胶质瘤分级; 影像组学; 递归特征消除; 集成学习 |
| Keywords: | glioma grading; radiomics; recursive feature elimination; ensemble learning |
| 分类号: | TP391 |
| 文献标识码: | A |
| 摘要: | 脑胶质瘤的术前分级对治疗决策和预后评估至关重要. 为了提高分级精度, 提出了一种基于影像组学和集成学习的无创胶质瘤术前分级方法. 首先, 从不同序列的感兴趣区域提取428个影像组学特征, 采用递归特征消除算法进行特征选择, 采用6种不同的机器学习算法对脑胶质瘤进行分级, 并对各自的性能进行评估; 然后, 根据评估结果, 选取逻辑回归、决策树和多层感知机3种分类器作为脑胶质瘤分级预测的机器学习算法; 最后, 将3种分类器的输出采用投票方式进行集成, 并评估硬投票机制与软投票机制的性能. 实验结果表明, 对于数据集BraTS2019, 基于硬投票机制的集成学习算法的性能较好, 受试者工作特性曲线下面积为0.933±0.031, 准确度为0.886±0.048, 敏感度为0.872±0.077, 特异度为0.905±0.105. 该方法不仅能增加胶质瘤分级模型的可解释性, 而且可以提高分级精度. |
| Abstract: | Glioma grading before surgery is very critical for the treatment planning and prognosis. In order to improve the grading accuracy, a non-invasive method for predicting the glioma grades based on radiomics and ensemble learning is proposed. First, 428 radiomics features are obtained from the region of interest (ROI) with different sequences. Feature selection is executed using Recursive Feature Elimination (RFE) algorithm, and 6 different machine learning algorithms are used to predict the glioma grade. Then, according to the evaluation results, three best classifiers, that is, Logistic Regression (LR), Decision Tree (DT) and Multilayer Perceptron (MLP), are selected as the machine learning algorithm for Glioma grading. Finally, these three classifiers are used for ensemble classification with a voting mechanism. The performance of hard and soft voting mechanism is also evaluated. Experimental results show that on the dataset BraTS2019, the hard voting mechanism based ensemble learning algorithm achieved the best performance, with the AUC value of 0.933±0.031, the accuracy of 0.886±0.048, the sensitivity of 0.872±0.077, and the specificity of 0.905±0.105. The presented work not only increases the interpretability of glioma grading model, but also ameliorates the grading accuracy. |
| 参考文献 /References: | [1] Ostrom Q, Cioffi G, Gittleman H, et al. CBTRUS statistical report: Primary brain and other central nervous system tumors diagnosed in the United States in 2012-2016[J]. Neuro-Oncology, 2019, 21(S5):v1-v100. [2] Wesseling P, Capper D. WHO 2016 classification of gliomas[J]. Neuropathology and Applied Neurobiology, 2018, 44(2):139-150. [3] Zacharaki E I, Wang S M, Chawla S, et al. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme[J]. Magnetic Resonance in Medicine, 2009, 62(6):1609-1618. [4] 韩文静, 胡贵祥, 胡玲静. 影像组学在脑胶质瘤中的研究进展[J]. 国际医学放射学杂志, 2020, 43(2):183-187. [5] 穆建华, 张雁伟, 吴志钢. 基于常规MRI图像的不同影像组学模型在脑胶质瘤术前分级中的应用[J]. 磁共振成像, 2020, 11(1):55-59. [6] Chen Q J, Wang L H, Wang L, et al. Glioma grade prediction using wavelet scattering-based radiomics[J]. IEEE Access, 2020, 8:106564-106575. [7] Menze B H, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS)[J]. IEEE Transactions on Medical Imaging, 2015, 34(10):1993-2024. [8] Bakas S, Akbari H, Sotiras A, et al. Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features[J]. Scientific Data, 2017, 4:170117. [9] Clark K, Vendt B, Smith K, et al. The cancer imaging archive (TCIA): Maintaining and operating a public information repository[J]. Journal of Digital Imaging, 2013, 26(6):1045-1057. [10] 国家卫生健康委员会医政医管局. 脑胶质瘤诊疗规范(2018年版)[J]. 中华神经外科杂志, 2019, 35(3):217- 239. [11] Qin J B, Liu Z Y, Zhang H, et al. Grading of gliomas by using radiomic features on multiple magnetic resonance imaging (MRI) sequences[J]. Medical Science Monitor, 2017, 23:2168-2178. [12] Landwehr N, Hall M, Frank E. Logistic model trees[J]. Machine Learning, 2005, 59(1/2):161-205. [13] Nello C. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods[M]. Cambridge: Cambridge University Press, 2000. [14] Pal S K, Mitra S. Multilayer perceptron, fuzzy sets, and classification[J]. IEEE Transactions on Neural Networks, 1992, 3(5):683-697. [15] Leo B. Classification and Regression Trees[M]. Belmont, CA: Wadsworth Publishing Company, 1984. [16] Wu Y P, Hao H H, Li J, et al. Four-sequence maximum entropy discrimination algorithm for glioma grading[J]. IEEE Access, 2019, 7:52246-52256. [17] Ye F Y, Pu J, Wang J, et al. Glioma grading based on 3D multimodal convolutional neural network and privileged learning[C]//2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Kansas City, MO, USA, 2017:759-763. |
| 备注/Memo: | 收稿日期: 2020－10－10. 宁波大学学报（理工版）网址: http://journallg.nbu.edu.cn/ 基金项目: 浙江省自然科学基金（LY20H180003）; 宁波市自然科学基金（T2019A610104）; 宁波市公益类科技计划项目（202002N3104）. 第一作者: 戴宏（1997－）, 男, 江西上饶人, 在读硕士研究生, 主要研究方向: 医学影像. E-mail: 1356913744@qq.com *通信作者: 符冉迪（1971－）, 男, 浙江宁波人, 副教授, 主要研究方向: 数字图像处理. E-mail: furandi_nbu@163.com 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
