生物医学工程学杂志

生物医学工程学杂志

基于栈式深度多项式网络集成学习框架的帕金森病计算机辅助诊断

查看全文

特征表达是基于磁共振成像(MRI)的帕金森病(PD)计算机辅助诊断系统诊断准确性的重要决定因素。深度多项式网络(DPN)是一种新的有监督深度学习算法,对于小数据集具有良好的特征表达能力。本文提出一种面向 PD 计算机辅助诊断的栈式 DPN(SDPN)集成学习框架,以有效提高基于小数据的 PD 辅助诊断准确性。本框架对所提取的 MRI 特征的每一个特征子集分别通过 SDPN 得到新的特征表达,然后采用支持向量机(SVM)对每个子集进行分类,再对所有分类器进行集成学习,得到最终的 PD 诊断结果。通过对公开的帕金森病数据库 PPMI 进行实验,基于脑网络特征的分类精度、敏感度和特异性分别为 90.15%、85.48% 和 93.27%;而基于多视图脑区特征的分类精度、敏感度和特异性分别为 87.18%、86.90% 和 87.27%。与在 PPMI 数据库中的 MRI 数据集进行实验的其他算法研究相比,本文所提出的算法获得了更好的分类结果。本文研究表明了所提出的 SDPN 集成学习框架的有效性,具有应用于 PD 计算机辅助诊断的可行性。

Feature representation is the crucial factor for the magnetic resonance imaging (MRI) based computer-aided diagnosis (CAD) of Parkinson’s disease (PD). Deep polynomial network (DPN) is a novel supervised deep learning algorithm, which has excellent feature representation for small dataset. In this work, a stacked DPN (SDPN) based ensemble learning framework is proposed for diagnosis of PD, which can improve diagnostic accuracy for small dataset. In the proposed framework, SDPN was performed on each subset of extracted features from MRI images to generate new feature representation. The support vector machine (SVM) was then adopted to perform classification task on each subset. The ensemble learning algorithm was then performed on all the SVM classifiers to generate the final diagnosis for PD. The experimental results on the Parkinson’s Progression Markers Initiative dataset (PPMI) showed that the proposed algorithm achieved the classification accuracy, sensitivity and specificity of 90.15%, 85.48% and 93.27%, respectively, with the brain network features, and it also got the classification accuracy of 87.18%, sensitivity of 86.90% and specificity of 87.27% on the multi-view features extracted from different brain regions. Moreover, the proposed algorithm outperformed other algorithms on the MRI dataset from PPMI. It suggests that the proposed SDPN-based ensemble learning framework has the feasibility and effectiveness for the CAD of PD.

关键词: 帕金森病; 磁共振成像; 栈式深度多项式网络; 集成学习

Key words: Parkinson's disease; magnetic resonance imaging; stacked deep polynomial network; ensemble learning

登录后 ,请手动点击刷新查看全文内容。 没有账号,
登录后 ,请手动点击刷新查看图表内容。 没有账号,
1. Pyatigorskaya N, Gallea C, Garcia-Lorenzo D, et al. A review of the use of magnetic resonance imaging in Parkinson's disease. Ther Adv Neurol Disord, 2014, 7(4): 206-220.
2. Long Dan, Wang Jinwei, Xuan Min, et al. Automatic classification of early Parkinson's disease with multi-modal MR imaging. PLoS One, 2012, 7(11): e47714.
3. Ye C, Storrs J, Tan L, et al. Detecting brain structural changes as biomarker from magnetic resonance images using a local feature based SVM approach. J Neurosci Methods, 2014, 221(2): 22-31.
4. Salvatore C, Cerasa A, Castiglioni I, et al. Machine learning on brain MRI data for differential diagnosis of Parkinson's disease and Progressive Supranuclear Palsy. J Neurosci Methods, 2014, 222: 230-237.
5. Rana B, Juneja A, Saxena M, et al. Regions-of-interest based automated diagnosis of Parkinson's disease using T1-weighted MRI. Expert Syst Appl, 2015, 42(9): 4506-4516.
6. Adeli E, Shi Feng, An Le, et al. Joint feature-sample selection and robust diagnosis of Parkinson's disease from MRI data. Neuroimage, 2016, 141: 206-219.
7. Peng Bo, Wang Suhong, Zhou Zhiyong, et al. A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson's disease. Neurosci Lett, 2017, 651: 88-94.
8. Shen D, Wu G, Suk H I. Deep learning in medical image analysis. Annu Rev Biomed Eng, 2017, 19: 221.
9. Plis S M, Hjelm D R, Salakhutdinov R, et al. Deep learning for neuroimaging: a validation study. Front Neurosci, 2014, 8(8): 229.
10. 陈诗慧, 刘维湘, 秦璟, 等. 基于深度学习和医学图像的癌症计算机辅助诊断研究进展. 生物医学工程学杂志, 2017, 34(2): 314-319.
11. Payan A, Montana G. Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks. Computer Science, 2015. arXiv: 1502.02506.
12. Suk H I, Lee S W, Shen Dinggang, et al. Latent feature representation with stacked auto-encoder for AD/MCI diagnosis. Brain Struct Funct, 2015, 220(2): 841-859.
13. Livni R, Shalev-Shwartz S, Shamir O. An algorithm for training polynomial networks. Computer Science, 2013, 26(18): 4748-4750.
14. Shi J, Zheng X, Li Y, et al. Multimodal neuroimaging feature learning with multimodal stacked deep polynomial networks for diagnosis of Alzheimer's disease. IEEE Journal of Biomedical & Health Informatics, 2018, 22(1): 173-183.
15. Shi Jun, Zhou Shichong, Liu Xiao, et al. Stacked deep polynomial network based representation learning for tumor classification with small ultrasound image dataset. Neurocomputing, 2016, 194: 87-94.
16. Zhu P, Zhang L, Hu Q, et al. Multi-scale patch based collaborative representation for face recognition with margin distribution optimization// European Conference on Computer Vision. 2012, 7572: 822-835.
17. Yang F, Lu H, Yang M H. Robust visual tracking via multiple kernel boosting with affinity constraints. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(2): 242-254.
18. Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell, 2013, 35(8): 1798-1828.