结直肠癌患者肝脏CT图像分类中决策树模型的应用

被引:4
作者
曹务腾 [1 ]
庄乔棣 [2 ]
练延帮 [1 ]
龚佳英 [1 ]
熊斐 [1 ]
邱建平 [1 ]
张波 [1 ]
杨然 [2 ]
周智洋 [1 ]
机构
[1] 中山大学附属第六医院放射科
[2] 中山大学移动信息工程学院
关键词
数据挖掘; 决策树; 肝脏; CT图像; 分类;
D O I
暂无
中图分类号
R735.3 [肠肿瘤]; R730.44 [放射线、同位素诊断];
学科分类号
100214 ; 100105 ;
摘要
目的:探讨数据挖掘中决策树模型在结直肠癌患者肝脏CT图像分类中的应用。方法:分别选取结直肠癌患者肝转移、单纯性肝囊肿以及正常肝脏的CT增强图像各20例。对该60例肝脏CT增强图像分别进行灰度直方图、灰度共生矩阵以及图像变换的纹理特征提取,然后采用朴素贝叶斯分类器和决策树归纳分类器对图像进行分类。最终分类结果与临床事实分类对照,利用十折交叉验证法验证两种分类模型的有效性。结果:基于数据挖掘的决策树模型对结直肠癌患者肝脏CT图像进行分类准确性较高。决策树归纳的分类准确性远高于朴素贝叶斯分类器(准确性96.7%vs 76.7%,Kappa值0.95 vs 0.65,P<0.05)。结论:基于数据挖掘的决策树模型可以对结直肠癌患者肝脏CT图像进行分类,不仅能够判断肝脏有无相关病灶,而且仅依据图像的基本特性,可以自动识别肝脏乏血供转移瘤与单纯性肝囊肿,为未来计算机辅助诊疗疾病提供有效的参考信息及途径。
引用
收藏
页码:275 / 283
页数:9
相关论文
共 7 条
[1]   Survival Analysis of Patients with High-Grade Gliomas Based on Data Mining of Imaging Variables [J].
Zacharaki, E. I. ;
Morita, N. ;
Bhatt, P. ;
O'Rourke, D. M. ;
Melhem, E. R. ;
Davatzikos, C. .
AMERICAN JOURNAL OF NEURORADIOLOGY, 2012, 33 (06) :1065-1071
[2]   Predictions of the pathological response to neoadjuvant chemotherapy in patients with primary breast cancer using a data mining technique [J].
Takada, M. ;
Sugimoto, M. ;
Ohno, S. ;
Kuroi, K. ;
Sato, N. ;
Bando, H. ;
Masuda, N. ;
Iwata, H. ;
Kondo, M. ;
Sasano, H. ;
Chow, L. W. C. ;
Inamoto, T. ;
Naito, Y. ;
Tomita, M. ;
Toi, M. .
BREAST CANCER RESEARCH AND TREATMENT, 2012, 134 (02) :661-670
[3]  
A Comparative Study in Wavelets, Curvelets and Contourlets as Denoising Biomedical Images[J] . Mohamed Ali HAMDI.International Journal of Image, Graphics and Signal Processing(IJIGSP) . 2012 (1)
[4]  
Mining microarray data to predict the histological grade of a breast cancer[J] . Mickael Fabregue,Sandra Bringay,Pascal Poncelet,Maguelonne Teisseire,Béatrice Orsetti.Journal of Biomedical Informatics . 2011
[5]   Entropy-based feature extraction and decision tree induction for breast cancer diagnosis with standardized thermograph images [J].
Lee, Ming-Yih ;
Yang, Chi-Shih .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2010, 100 (03) :269-282
[6]  
Predicting breast cancer survivability: a comparison of three data mining methods[J] . Dursun Delen,Glenn Walker,Amit Kadam.Artificial Intelligence In Medicine . 2004 (2)
[7]  
Image mining: issues, framework, a generic tool and its application to medical-image diagnosis[J] . Petra Perner.Engineering Applications of Artificial Intelligence . 2002 (2)