计算机科学 ›› 2017, Vol. 44 ›› Issue (10): 45-50.doi: 10.11896/j.issn.1002-137X.2017.10.008
雷一鸣,赵希梅,王国栋,于可歆
LEI Yi-ming, ZHAO Xi-mei, WANG Guo-dong and YU Ke-xin
摘要: 肝硬化的计算机辅助诊断对肝脏疾病的早期治疗和诊断具有重要意义。针对B超图像中肝硬化病变区域边缘模糊和回声不均匀、尺度因素影响等问题,提出了改进的LBP算法并提取了相应的SLBP特征。该特征较传统的纹理特征更准确地描述了B超图像中肝硬化病变的特征,结合二维Gabor变换,解决了上述难题。鉴于传统的机器学习方法的训练时间较长,采用基于超限学习机的训练方法,并首次将其应用于肝硬化识别。实验结果表明,所提方法对测试集的分类准确率达到95.4%,在时间效率上较传统方法有很大提高。ROC曲线表明,提出的分类方法在准确率和泛化能力上均优于传统方法,有助于肝硬化的临床诊断。
[1] ZHOU G H,WANG Y Y,et al.A system for hepatocirrhosisanalysis based on features extracted from ultrasonic images oflivers[J].Technical Acoustics,2003,22(4):288-291.(in Chi-nese) 周国辉,汪源源,等.基于超声图像特征的肝硬化分析系统[J].声学技术,2003,22(4):288-291. [2] MITREA D,LUPSOR M P,NEDEVSCHI S,et al.Discovering the cirrhosis grades from ultrasound images by using textural features and clustering methods[C]∥ International Conference on Telecommunications & Signal Processing.2008:633-637. [3] FUJITA Y,HAMAMOTO Y,SEGAWA M,et al.An improved method for cirrhosis detection using liver’s ultrasound images[C]∥International Conference on Pattern Recognition.2010:2294-2297. [4] WU C M,CHANG C U.Text Features for Classification of Ultrasonic Liver Images [J].IEEE Transactions on medical imaging,1992,11(2):145-146. [5] SILVIA S,CASTAO G,BURGUEO A L.A diagnostic mo-del to differentiate simple steatosis from nonalcoholic steatohe-patitis based on the likelihood ratio form of Bayes theorem[J].Clinical Biochemistry,2009,42:624-629. [6] CHEN F.Identifying Ultrasonic Liver Image Based on BP Neural Network[J].Network and Information Technology, 2007,6(8):43-44.(in Chinese) 陈菲.基于BP神经网络的超声肝图像识别[J].网络与信息技术,2007,6(8):43-44. [7] LIU H,GUO D M,LIU X C.Cirrhosis classification based on MRI with duplicative-feature support vector machine (DFSVM)[J].Biomedical Signal Processing and Control,2013,8(4):346-353. [8] MALAA K,SADASIVAMB V,ALAGAPPAN S.Neural network based texture analysis of CT images for fatty andcirrhosis liver classification[J].Applied Soft Computing,2015,32(c):80-86. [9] HUANG G B,ZHU Q Y,SIEW C K.Extreme Learning Ma-chine:A New Learning Scheme of Feedforward Neural Networks[J].Neurocomputing,2006,70:489-501. [10] HUANG Z Y,YU Y L,GU J,et al.An Efficient Method for Traffic Sign Recognition Based on Extreme Learning Machine[J].IEEE Transactions on Cybernetics,2017,47(4):920. [11] XU J T,ZHOU H M,HUANG G B.Extreme Learning Machine Based Fast Object Recognition[C]∥15th International Confe-rence on Information Fusion(FUSION).2012:1490-1496. [12] ZHAO J,ZHANG Z Y,MEN G Z.Thyroid Disease Classification Method Based on Integration Improved ELM[J].Computer Simulation,2014,1(3):392-396.(in Chinese) 赵杰,张振宇,门国尊.基于集成改进ELM的甲状腺疾病分类方法[J].计算机仿真,2014,1(3):392-396. [13] VAPNIK V N.Statistical Learning Theory[M].New York:John Wiley & Sons,1998. [14] GAO C,WANG K F,YU Z D.License Plate Recognition Using MSER and HOG Based on ELM[C]∥IEEE.2014:217-221. [15] RAO C R,MTRA S K.Generalized Inverse of Matrices and Its Applications[M].New York:John Wiley & Sons,1971. [16] ZHAO Z G,WU X,HONG D F,et al.Palmprint ReognitionMethod Based on Energy Spectrum of GLBP[J].Computer Science,2014,1(8):293-296.(in Chinese) 赵志刚,吴鑫,洪丹枫,等.基于信息熵的GLBP掌纹识别算法[J].计算机科学,2014,1(8):293-296. [17] LEE T S.Image representation using 2D Gabor wavelets[J].IEEE Transactions on Pattern Analysis Machine Intelligence,1996,18(10):959-971. |
No related articles found! |
|