[1]洪雁飞,魏本征,刘川,等.基于深度学习的椎间孔狭窄自动多分级研究[J].智能系统学报,2019,14(04):708-715.[doi:10.11992/tis.201806015]
 HONG Yanfei,WEI Benzheng,LIU Chuan,et al.Deep learning based automatic multi-classification algorithm for intervertebral foraminal stenosis[J].CAAI Transactions on Intelligent Systems,2019,14(04):708-715.[doi:10.11992/tis.201806015]
点击复制

基于深度学习的椎间孔狭窄自动多分级研究(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年04期
页码:
708-715
栏目:
出版日期:
2019-07-02

文章信息/Info

Title:
Deep learning based automatic multi-classification algorithm for intervertebral foraminal stenosis
作者:
洪雁飞12 魏本征12 刘川2 韩忠义12 李天阳12
1. 山东中医药大学 理工学院, 山东 济南 250355;
2. 山东中医药大学 计算医学实验室, 山东 济南 250355
Author(s):
HONG Yanfei12 WEI Benzheng12 LIU Chuan2 HAN Zhongyi12 LI Tianyang12
1. College of Science and Technology, Shandong University of Traditional Chinese Medicine, Ji’nan 250355, China;
2. Computational Medicine Lab, Shandong University of Traditional Chinese Medicine, Ji’nan 250355, China
关键词:
椎间孔狭窄自动分级机器学习深度学习特征提取监督训练迁移学习过拟合
Keywords:
intervertebral foraminal stenosisautomatic grademachine learningdeep learningfeature extractionsupervised trainingtransfer learningover fitting
分类号:
TP311
DOI:
10.11992/tis.201806015
摘要:
椎间孔狭窄症的术前定性分级诊断对临床医生治疗策略的制定和患者健康恢复至关重要,但目前该方面临床上仍然存在很多问题,并且缺乏相关的研究和行之有效的方法用于辅助临床医生诊断。因此,为提高计算机辅助椎间孔狭窄症诊断准确率以及医生工作效率,本文提出一种基于深度学习的椎间孔狭窄图像自动分级算法。从人体矢状切脊柱核磁共振图像中提取脊柱椎间孔图像,并做图像预处理;设计一种监督式深度卷积神经网络模型,用于实现脊柱椎间孔图像数据集的自动多分级;利用迁移学习方法,解决深度学习算法在小样本数据集上的过拟合问题。实验结果表明,本文算法在脊柱椎间孔图像数据集上的分类精确度可达到87.5%以上,且其具有良好的鲁棒性和泛化能力。
Abstract:
Preoperative qualitative diagnosis of intervertebral foraminal stenosis is essential for the formulation of clinician treatment strategies and patients’ health recovery. However, there are still many clinical challenges in this aspect and a lack of relevant research and proven methods to assist clinicians in diagnosis. Therefore, a deep learning-based automatic classification algorithm is proposed in this study to improve the diagnosis accuracy and the efficiency. First, we extracted the spinal foramen images from the sagittal spine MRI image, and then these images were preprocessed. Second, a supervised deep convolutional neural network model was designed to achieve automatic multi-classification for the datasets of the intervertebral foraminal stenosis. Finally, we used the transfer learning to optimize the overfitting problem of the deep learning algorithm in the small sample dataset. The experimental results show that the classification accuracy of this algorithm on the dataset of spinal foramen was 87.5%, and it has good robustness and generalization performance.

参考文献/References:

[1] KANEKO Y, MATSUMOTO M, TAKAISHI H, et al. Morphometric analysis of the lumbar intervertebral foramen in patients with degenerative lumbar scoliosis by multidetector-row computed tomography[J]. European spine journal, 2012, 21(12):2594-2602.
[2] RAJAEE S S, BAE H W, KANIM L E, et al. Spinal fusion in the united states:analysis of trends from 1998 to 2008[J]. Spine, 2012, 37(1):67-76.
[3] LEE S, LEE J W, YEOM J S, et al. A practical MRI grading system for lumbar foraminal stenosis[J]. American journal of roentgenology, 2010, 194(4):1095-1098.
[4] HAN Zhongyi, WEI Benzheng, LEUNG S, et al. Automated pathogenesis-based diagnosis of lumbar neural foraminal stenosis via deep multiscale multitask learning[J]. Neuroinformatics, 2018, 16(3/4):325-337.
[5] ALOMARI R S, CORSO J J, CHAUDHARY V. Labeling of lumbar discs using both pixel-and object-level features with a two-level probabilistic model[J]. IEEE transactions on medical imaging, 2011, 30(1):1-10.
[6] ZHAN Yiqiang, MANEESH D, HARDER M, et al. Robust MR spine detection using hierarchical learning and local articulated model[C]//Proceedings of the 15th International Conference on Medical Image Computing and Computer-Assisted Intervention. Nice, France, 2012:141–148, DOI:10.1007/978-3-642-33415-3_18.
[7] WANG Zhijie, ZHEN Xiantong, TAY K, et al. Regression segmentation for M3 spinal images[J]. IEEE transactions on medical imaging, 2015, 34(8):1640-1648.
[8] GHOSHA S, ALOMARI R S, CHAUDHARY V, et al. Automatic lumbar vertebra segmentation from clinical CT for wedge compression fracture diagnosis[C]//Proceedings of the SPIE 7963, Medical Imaging 2011:Computer-Aided Diagnosis. Lake Buena Vista (Orlando), United States, 2011:796303, DOI:10.1117/12.878055.
[9] HUANG S H, CHU Yihong, LAI Shanghong, et al. Learning-based vertebra detection and iterative normalized-cut segmentation for spinal MRI[J]. IEEE transactions on medical imaging, 2009, 28(10):1595-1605.
[10] KLINDER T, WOLZ R, LORENZ C, et al. Spine segmentation using articulated shape models[C]//Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention. New York, USA, 2008:227-234.
[11] HE Xiaoxu, YIN Yilong, SHARMA M, et al. Automated diagnosis of neural foraminal stenosis using synchronized superpixels representation[C]//Proceedings of the 19th International Conference on Medical Image Computing and Computer-Assisted Intervention. Athens, Greece, 2016:335-343.
[12] VERBIEST H. Results of surgical treatment of idiopathic developmental stenosis of the lumbar vertebral canal. A review of twenty-seven years’ experience[J]. The journal of bone and joint surgery, 1977, 59(2):181-188.
[13] LO S C B, LOU S L A, LIN J S, et al. Artificial convolution neural network techniques and applications for lung nodule detection[J]. IEEE transactions on medical imaging, 1995, 14(4):711-718.
[14] LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Medical image analysis, 2017, 42(9):60-88.
[15] WANG Xiaosong, PENG Yifan, LU Le, et al. ChestX-Ray8:Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases[C]//Proceeding of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017:3462-3471.
[16] SHEN Dinggang, WU Guorong, SUK H I. Deep learning in medical image analysis[J]. Annual review of biomedical engineering, 2017, 19:221-248.
[17] BENGIO Y, DELALLEAU O. On the expressive power of deep architectures[C]//Proceedings of the 22nd International Conference on Algorithmic Learning Theory. Espoo, Finland, 2011:18-36.
[18] PAN S J, YANG Qiang. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10):1345-1359.
[19] WILDERMUTH S, ZANETTI M, DUEWELL S, et al. Magnetic resonance imaging and magnetic resonance myelography in the presurgical diagnosis of lumbar foraminal stenosis[J]. Spine, 2007, 32(8):896-903.
[20] JIA Yangqing, SHELHAMER E, DONAHUE J, et al. Caffe:convolutional architecture for fast feature embedding[C]//Proceedings of the 22nd ACM International Conference on Multimedia. Orlando, USA, 2014:675-678.
[21] OJALA T, PIETIKÄINEN M, MÄENPÄÄ T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J]. IEEE transactions on pattern analysis and machine intelligence, 2002, 24(7):971-987.
[22] GUO Zhenhua, ZHANG Lei, ZHANG D. A completed modeling of local binary pattern operator for texture classification[J]. IEEE transactions on image processing, 2010, 19(6):1657-1663.
[23] HONG Huichao, ZHENG Lixin, PAN Shuwan. Fast computational technique for gray-level co-occurrence matrix based on graphics process unit in biomedical engineering applications[J]. Journal of medical imaging and health informatics, 2018, 8(2):309-312.
[24] RUBLEE E, RABAUD V, KONOLIGE K, et al. ORB:an efficient alternative to SIFT or SURF[C]//Proceedings of 2011 International Conference on Computer Vision. Barcelona, Spain, 2011:2564-2571.
[25] ?AHAN S, POLAT K, KODAZ H, et al. A new hybrid method based on fuzzy-artificial immune system and k-nn algorithm for breast cancer diagnosis[J]. Computers in biology and medicine, 2007, 37(3):415-423.
[26] WONG P K, GAO Xianghui, WONG K I, et al. Online extreme learning machine based modeling and optimization for point-by-point engine calibration[J]. Neurocomputing, 2018, 277:187-197.
[27] CORTES C, VAPNIK V. Support-vector networks[J]. Machine learning, 1995, 20(3):273-297.
[28] BREIMAN L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.

备注/Memo

备注/Memo:
收稿日期:2018-06-05。
基金项目:国家自然科学基金项目(U1201258,61572300);山东省自然科学基金项目(ZR2015FM010);山东高等学校科技计划项目(J15LN20);山东省医药卫生科技发展计划项目(2016WSO577);山东省中医药科技发展计划项目(2017-001).
作者简介:洪雁飞,女,1994年生,硕士研究生,主要研究方向为医学影像分析和机器学习算法;魏本征,男,1976年生,教授,主要研究方向为医学图像处理、机器学习、计算医学和医学信息工程。发表学术论文60余篇;刘川,男,1972年生,副教授,主要研究方向为中医骨伤学和中医药文化社会学。
通讯作者:魏本征.E-mail:wbz99@sina.com
更新日期/Last Update: 2019-08-25