Prostate tumor CAD model based on neural network with feature-level fusion in magnetic resonance imaging

doi:10.11772/j.issn.1001-9081.2015.10.2813

Journal of Computer Applications ›› 2015, Vol. 35 ›› Issue (10): 2813-2818.DOI: 10.11772/j.issn.1001-9081.2015.10.2813

Previous Articles Next Articles

Prostate tumor CAD model based on neural network with feature-level fusion in magnetic resonance imaging

LU Huiling, ZHOU Tao, WANG Huiqun, WANG Wenwen

School of Science, Ningxia Medical University. Yinchuan Ningxia 750004, China

Received:2015-06-01 Revised:2015-06-21 Online:2015-10-10 Published:2015-10-14

基于特征级融合神经网络的磁共振成像前列腺肿瘤CAD模型

陆惠玲, 周涛, 王惠群, 王文文

宁夏医科大学理学院, 银川 750004

通讯作者: 周涛(1977-),男,宁夏同心人,教授,博士,主要研究方向:基于影像的计算机辅助诊断、医学大数据分析、智能算法,zhoutaonxmu@126.com
作者简介:陆惠玲(1976-),女,河北定兴人,副教授,主要研究方向:医学图像分析与处理、智能算法;王惠群(1991-),女,宁夏银川人,硕士研究生,主要研究方向:医学图像融合与识别;王文文(1992-),女,宁夏银川人,硕士研究生,主要研究方向:智能医学信息处理。
基金资助:
国家自然科学基金资助项目(81160183,61561040);宁夏自然科学基金资助项目(NZ12179,NZ14085);宁夏高等学校科研项目(NGY2013062);陕西省语音与图像信息处理重点实验室开放课题资助项目(SJ2013003);宁夏医科大学特殊人才项目(XT2011004)。

Abstract

Abstract: Focusing on the issue that feature relevancy and dimension disaster problem in high-dimensional representation of Magnetic Resonance Imaging (MRI) prostate tumor Region of Interesting (ROI), a prostate tumor CAD model was proposed based on Neural Network (NN) with Principal Component Analysis (PCA) feature-level fusion in MRI. Firstly, 102 dimension features were extracted form MRI prostate tumor ROI, including 6 dimension geometry features, 6 dimension statistical features, 7 dimension Hu invariant moment features, 56 dimension GLCM texture features, 3 dimension Tamura texture features and 24 dimension frequency features. Secondly, 8 dimension features with cumulative contribution rate of 89.62% were obtained by using PCA in feature-level fusion, reducing the dimension of the feature vectors. Thirdly, the classical NN, which used Broyden-Fletcher-Goldfarb-Shanno (BFGS), Back-Propagation (BP) and Gradient Descent (GD), Levenberg-Marquardt as the training algorithm, was regarded as classifier to classify the features. Finally, 180 MRI images of prostate patients were used as original data, and the prostate tumor CAD model based on NN with feature-level fusion was utilized to diagnose. The experimental results illustrate that the ability to identify benign and malignant prostate tumor of neural network with PCA feature-level fusion is improved at least 10%, and the feature-level fusion strategy is effective, which increases the feature irrelevancy to a certain extent.

Key words: prostate tumor, computer-aided diagnosis, Principal Component Analysis (PCA), Neural Network (NN), feature-level fusion

摘要： 针对磁共振成像(MRI)前列腺肿瘤感兴趣区域(ROI)在高维特征表示下存在特征相关和维数灾难问题,提出了一种基于主成分分析(PCA)的特征级融合神经网络(NN)的MRI前列腺肿瘤CAD模型。首先提取MRI前列腺肿瘤ROI的6维几何特征、6维统计特征、7维Hu不变矩特征、56维灰度共生矩阵的纹理特征、3维Tamura纹理特征和24维频域特征,得到102维特征矢量;然后通过PCA进行特征级融合得到累计贡献率达到89.62%的8维变换特征,降低特征矢量的维数;再次利用经典的神经网络(四种训练算法BFGS拟牛顿算法、BP算法、最速梯度下降算法和Levenberg-Marquardt算法)作为分类器进行分类识别;最后以180幅前列腺患者的MRI图像为原始数据,采用基于特征级融合神经网络(NN)的计算机辅助诊断模型对前列腺肿瘤进行辅助诊断。实验结果表明:经过特征级融合的神经网络识别前列腺良恶性肿瘤的能力至少提高10%左右,这种特征级融合策略是有效的,一定程度上提高了特征之间的不相关性。

关键词: 前列腺肿瘤, 计算机辅助诊断, 主成分分析, 神经网络, 特征级融合

CLC Number:

LU Huiling, ZHOU Tao, WANG Huiqun, WANG Wenwen. Prostate tumor CAD model based on neural network with feature-level fusion in magnetic resonance imaging[J]. Journal of Computer Applications, 2015, 35(10): 2813-2818.

陆惠玲, 周涛, 王惠群, 王文文. 基于特征级融合神经网络的磁共振成像前列腺肿瘤CAD模型[J]. 计算机应用, 2015, 35(10): 2813-2818.

References

[1] SHI F, WEI J, WANG Z, et al. Normal prostate and benign prostatic hyperplasia:MR imaging at 1.5T[J]. Chinese Journal of Geriatrics, 1997,4(16):79-83. (施发表,韦嘉瑚,王占立,等.正常和良性增生前列腺的高场强磁共振成像特征[J]. 中华老年医学杂志,1997,4(16):79-83.)
[2] HUA L, JU X, WU H, et al. The expression of androgen receptor gene in benign prostatic hyperplasia and prostatic cancer tissues[J]. Chinese Journal of Geriatrics,2003,22(7):405-408.(华立新,居小兵,吴宏飞,等.良性前列腺增生和前列腺癌组织中雄激素受体的表达[J].中华老年医学杂志, 2003,22(7):405-408.)
[3] YANG Z. Computer-aided diagnosis of prostate lesions based on ultrasound images[D]. Hefei: University of Science and Technology of China,2009.(杨振森.基于超声图像的前列腺病变计算机辅助诊断[D].合肥:中国科学技术大学,2009.)
[4] LEMAITRE G, MARTI R, FREIXENET J, et al. Computer-aided detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review[J]. Computers in Biology and Medicine, 2015,60:8-31.
[5] QIN J, BAI H, LIU C, et al. Application of computer-aided diagnosis in early detection of pulmonary nodules based on digital chest radiograph[J]. Journal of Biomedical Engineering,2014,31(5):1117-1120.(秦菊,白红利,刘畅,等.计算机辅助诊断在数字化胸片肺结节早期检出中的应用[J].生物医学工程学杂志,2014,31(5):1117-1120.)
[6] ZHANG G, LIAO Q, JIAO C, et al. Study of computer aided diagnosis technology in virtual colonoscopy[J].Journal of Xidian University,2015,42(2):157-161.(张国鹏, 廖琪梅,焦纯,等.虚拟结肠镜的计算机辅助诊断技术研究[J].西安电子科技大学学报,2015,42(2):157-161.)
[7] NIAF E, ROUVIERE O, MEGE-LECHEVALLIER F, et al. Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI[J]. Physics in Medicine and Biology,2012,57(12):3833-51.
[8] KANDEMIR M, HAMPRECHT F A. Computer-aided diagnosis from weak supervision: a benchmarking study[J]. Computerized Medical Imaging and Graphics, 2015,42:44-50
[9] ZOLLNER F G, EMBLEM K E, SCHAD L R. SVM-based glioma grading: optimization by feature reduction analysis[J]. Zeitschrift Für Medizinische Physik, 2012,22(3):205-214.
[10] LIU H, GUO D, LIU X.Cirrhosis classification based on MRI with Duplicative-Feature Support Vector Machine (DFSVM)[J]. Biomedical Signal Processing and Control,2013,8(4):346-353.
[11] ZHOU T, LU H, CHEN Z, et al. Prostate tumor recognition based on two-stage ensemble SVM[J]. Optics and Precision Engineering, 2013,21(8):2138-2145.(周涛,陆惠玲,陈志强,等.基于两阶段集成支持向量机的前列腺肿瘤识别研究[J].光学精密工程, 2013,21(8):2138-2145)
[12] BO H, MA F, JIAO L. Research on computation of GLCM of image texture[J]. Acta Electronica Sinica, 2006,34(1):155-159.(薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析[J].电子学报, 2006,34(1):155-159.)
[13] ZHAO W, CHELLAPPA R, PHILLIPS P J, et al. Face recognition: a literature survey[J]. ACM Computing Surveys,2003,35(4):399-459.
[14] TAN L. The theory and application of the dimension reduction on the high-dimensional data set[D]. Hefei: University of Science and Technology of China,2005.(谭璐.高维数据的降维理论及应用[D].合肥:中国科学技术大学,2005.)
[15] LANGLEY P. Selection of relevant features in machine learning[C]//Proceedings of the AAAI Fall Symposium on Relevance. Menlo Park: AAAI Press, 1994: 140-144.
[16] ZHUO L, YANG M. Dimensional reduction and classification of hyperspectral data for tree species using PCA algorithm[J]. Science of Surveying and Mapping,2014,39(2):146-149.(卓林辉,杨敏华.利用PCA算法进行乔木树种高光谱数据降维与分类[J].测绘科学,2014,39(2):146-149.)

Prostate tumor CAD model based on neural network with feature-level fusion in magnetic resonance imaging

基于特征级融合神经网络的磁共振成像前列腺肿瘤CAD模型

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	XU Shaowei, QIN Pinle, ZENG Jianchao, ZHAO Zhikai, GAO Yuan. Automatic segmentation algorithm of two-stage mediastinal lymph nodes using attention mechanism [J]. Journal of Computer Applications, 2021, 41(2): 556-562.
[2]	Jin ZHAO, Wen’ai SONG, Jun TAI, Jijiang YANG, Qing WANG, Xiaodan LI, Yi LEI, Yue QIU. Review of computer-aided face diagnosis for obstructive sleep apnea in children [J]. Journal of Computer Applications, 2021, 41(11): 3394-3401.
[3]	LU Rongxiu, CHEN Mingming, YANG Hui, ZHU Jianyong. Element component content dynamic monitoring system based on time sequence characteristics of solution images [J]. Journal of Computer Applications, 2021, 41(10): 3075-3081.
[4]	SUN Zhongjie, WAN Tao, CHEN Dong, WANG Hao, ZHAO Yanli, QIN Zengchang. Application of deep learning in histopathological image classification of aortic medial degeneration [J]. Journal of Computer Applications, 2021, 41(1): 280-285.
[5]	LI Dongbo, HUANG Lyuwen. Reweighted sparse principal component analysis algorithm and its application in face recognition [J]. Journal of Computer Applications, 2020, 40(3): 717-722.
[6]	ZHANG Xiaobo, YANG Yan, LI Tianrui, LU Fan, PENG Lilan. Early diagnosis and prediction of Parkinson's disease based on clustering medical text data [J]. Journal of Computer Applications, 2020, 40(10): 3088-3094.
[7]	ZHOU Fei, XIA Pengcheng. Signal strength difference fingerprint localization algorithm based on principal component analysis and chi-square distance [J]. Journal of Computer Applications, 2019, 39(5): 1405-1410.
[8]	CHEN Wanzhi, XU Dongsheng, ZHANG Jing, TANG Yu. Intrusion detection method for industrial control system with optimized support vector machine and K-means++ [J]. Journal of Computer Applications, 2019, 39(4): 1089-1094.
[9]	WANG Xin, LI Ke, XU Mingjun, NING Chen. Improved remote sensing image classification algorithm based on deep learning [J]. Journal of Computer Applications, 2019, 39(2): 382-387.
[10]	QIN Pinle, LI Pengbo, ZHANG Ruiping, ZENG Jianchao, LIU Shijie, XU Shaowei. Automatic recognition algorithm of cervical lymph nodes using adaptive receptive field mechanism [J]. Journal of Computer Applications, 2019, 39(12): 3535-3540.
[11]	QIN Pinle, LI Pengbo, ZENG Jianchao, ZHU Hui, XU Shaowei. Automatic recognition algorithm for cervical lymph nodes using cascaded fully convolutional neural networks [J]. Journal of Computer Applications, 2019, 39(10): 2915-2922.
[12]	WAN Yuan, ZHANG Jinghui, WU Kefeng, MENG Xiaojing. Image classification based on multi-layer non-negativity and locality Laplacian sparse coding [J]. Journal of Computer Applications, 2018, 38(9): 2489-2494.
[13]	FENG Liwei, ZHANG Cheng, LI Yuan, XIE Yanhong. Fault detection for multistage process based on improved local neighborhood standardization and kNN [J]. Journal of Computer Applications, 2018, 38(7): 2130-2135.
[14]	YIN Li, LIN Xinqi, CHEN Lifei. Moving object removal forgery detection algorithm in video frame [J]. Journal of Computer Applications, 2018, 38(3): 879-883.
[15]	XUE Yu, MEI Xue, ZHI Youran, XU Zhixing, SHI Xiang. Sub-health state identification method of subway door based on time series data mining [J]. Journal of Computer Applications, 2018, 38(3): 905-910.