Colorectal Polyps Detection Using Texture Features and Support Vector Machine

Authors:
Da-Chuan Cheng;Wen-Chien Ting;Yung-Fu Chen;Qin Pu;Xiaoyi Jiang
Affiliations:
Department of Radiological Technology, China Medical University, Taichung, Taiwan;Colorectal Surgery, China Medical University Hospital, Taichung, Taiwan 404;Department of Health Services Administration, China Medical University, Taichung, Taiwan;Department of Internal Medicine, University Hospital of Freiburg, Freiburg, Germany;Department of Mathematics and Computer Science, University of Münster, Münster, Germany 48161
Venue:
MDA '08 Proceedings of the 3rd international conference on Advances in Mass Data Analysis of Images and Signals in Medicine, Biotechnology, Chemistry and Food Industry
Year:
2008

Citing 3
Cited 2

A Comparative Study of Texture Features for the Discrimination of Gastric Polyps in Endoscopic Video

CBMS '05 Proceedings of the 18th IEEE Symposium on Computer-Based Medical Systems
Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa

IEEE Transactions on Information Technology in Biomedicine
Computer-aided tumor detection in endoscopic video using color wavelet features

IEEE Transactions on Information Technology in Biomedicine

A comparison between Haralick's texture descriptor and the texture descriptor based on random sets for biological images

MLDM'11 Proceedings of the 7th international conference on Machine learning and data mining in pattern recognition
Automatic real-time detection of endoscopic procedures using temporal features

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we propose a novel method in detecting colorectal polyps on colonoscopic images. Texture features are applied in polyps and normal tissues training and classification. Support vector machine is used as a classifier to identify the position of polyps. Seventy-four colonoscopic images are collected to test the system. Half of them are used as training images and half are used as testing. The experimental result shows the system can identify all polyps if the colonoscopic images contain single polyp. The sensitivity is 86.2% and the false-positive rate is 1.26 mark per-image.