Mean shift-based lesion detection of gastroscopic images

Authors:
Kai Sun;Yilun Wu;Xiaolin Lin;Shidan Cheng;Yue-Min Zhu;Su Zhang
Affiliations:
School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China;School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China;Department of Gastroenterology, Ruijin Hospital, Shanghai, China;Department of Gastroenterology, Ruijin Hospital, Shanghai, China;CREATIS, CNRS UMR5220, Inserm U1044, INSA Lyon, Villeurbanne, France;School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
Venue:
IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2011

Citing 13
Cited 0

Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift, Mode Seeking, and Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
A decision-theoretic generalization of on-line learning and an application to boosting

EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
Robust analysis of feature spaces: color image segmentation

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Color Texture Recognition in Video Sequences using Wavelet Covariance Features and Support Vector Machines

EUROMICRO '03 Proceedings of the 29th Conference on EUROMICRO
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
Detecting Informative Frames from Wireless Capsule Endoscopic Video Using Color and Texture Features

MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Computer-assisted pit-pattern classification in different wavelet domains for supporting dignity assessment of colonic polyps

Pattern Recognition
Texture analysis for ulcer detection in capsule endoscopy images

Image and Vision Computing
Interactive image segmentation by maximal similarity based region merging

Pattern Recognition
Computer-aided small bowel tumor detection for capsule endoscopy

Artificial Intelligence in Medicine
An mean shift based gray level co-occurrence matrix for endoscope image diagnosis

ICMB'10 Proceedings of the Second international conference on Medical Biometrics
Iterated graph cuts for image segmentation

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gastroscopy is one of the most important ways for diagnosing gastric cancer. Computer-aided detection of gastroscopic images is helpful in improving the accuracy of gastric cancer diagnosis. This paper proposes a method for lesion detection of gastroscopic images. Mean-shift segmentation is initially applied to reduce the information interference caused when global image or rectangular block serves as an identification area. A well performed three-dimensional color histogram feature is extracted from YCbCr color space. Mean shift-based Color Wavelet Covariance (MS-CWC) is proposed to reduce the cost of computing. Finally, after comparing Perceptron with AdaBoost, the latter is selected to train the classifier for detecting abnormal regions in gastroscopic images. Experiments show that the proposed method is feasible for lesion detection of gastroscopic images; the false negative rate(FNR), false positive rate(FPR), and error rates(ER) are 15.50%, 16.89%, and 16.35%, respectively.