Lesion Recognition Method of Liver CT Images Based on Random Forest

被引：5

作者：

Jin, Xinyu ^{[1
]}

Zhang, Ting ^{[1
]}

Li, Lanjuan ^{[1
]}

Wu, Haitao ^{[1
]}

Sun, Bin ^{[1
]}

机构：

[1] Zhejiang Univ, Coll Informat Sci & Elect Engn, Hangzhou, Zhejiang, Peoples R China

来源：

2016 8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY IN MEDICINE AND EDUCATION (ITME) | 2016年

关键词：

random forest; liver CT image; feature selection;

D O I：

10.1109/ITME.2016.0058

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Random forest algorithm has been intensively researched and developed in the field of machine learning, thanks to its considerable performance on classification. In terms of the identification of liver CT images, random forest algorithm is deployed to train and discover the characteristics of several common liver lesions through the usage of features vectors, such as image gray, texture, etc. This paper proposes an improved random forest algorithm based on feature selections. Concluding from experiment, the revised algorithm obtains a promising accuracy of classification.

引用

页码：227 / 230

页数：4

共 9 条

[1] Classifier Approaches for Liver Steatosis using Ultrasound Images [J].

Andrade, Andreia ;

Silva, Jose Silvestre ;

Santos, Jaime ;

Belo-Soares, Pedro .

4TH CONFERENCE OF ENTERPRISE INFORMATION SYSTEMS - ALIGNING TECHNOLOGY, ORGANIZATIONS AND PEOPLE (CENTERIS 2012), 2012, 5 :763-770

[2]

[Anonymous], 2012, MICCAI INT WORKSH ME

[3]

[Anonymous], 2002, P 5 NORD SIGN PROC S

[4]

Chang CY, 2007, 2007 THIRD INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION HIDING AND MULTIMEDIA SIGNAL PROCESSING, VOL 1, PROCEEDINGS, P7

[5]

Ho TK, 1998, IEEE T PATTERN ANAL, V20, P832, DOI 10.1109/34.709601

[6]

Lu P, 2015, INT CONF COMP SCI ED, P685, DOI 10.1109/ICCSE.2015.7250333

[7]

Owjimehr M, 2014, IRAN CONF ELECTR ENG, P1956, DOI 10.1109/IranianCEE.2014.6999862

[8]

Serra J., 1983, IMAGE ANAL MATH MORP

[9]

Tin Kam Ho, 1995, Proceedings of the Third International Conference on Document Analysis and Recognition, P278, DOI 10.1109/ICDAR.1995.598994

← 1 →