Indistinct Frame Detection in Colonoscopy Videos

被引:19
作者
Arnold, Mirko [1 ]
Ghosh, Anarta [1 ]
Lacey, Gerard [1 ]
Patchett, Stephen [2 ]
Mulcahy, Hugh [3 ]
机构
[1] Trinity Coll Dublin, Sch Comp Sci & Stat, Dublin, Ireland
[2] Beaumont Hosp, Dept Gastroenterol, Dublin, Ireland
[3] St Vincents Univ Hosp, Ctr Colorectal Dis, Dublin, Ireland
来源
2009 13TH INTERNATIONAL MACHINE VISION AND IMAGE PROCESSING CONFERENCE | 2009年
关键词
image classification; colonoscopy; wavelet transforms; biomedical image processing;
D O I
10.1109/IMVIP.2009.16
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An automated system for analysis of colonoscopy videos is expected to complement the expertise and the experience of a medical professional in: (a) detecting lesions and (b) assessing the quality of a given procedure. Colonoscopy videos contain a significant number of frames which do not carry any clinical information. The presence of such frames would slow down or cause the failure of the processing steps of such an automated system. Furthermore, many existing metrics to measure the quality of the colonoscopy procedures directly involve the number of such indistinct frames present in the videos. We propose a novel algorithm to detect indistinct frames based on the wavelet analysis. The L-2 norm of the detail coefficients of the wavelet decomposition of a colonoscopy image is considered as the feature vector of the proposed classification system. The algorithm was tested on a manually labeled, balanced data set. It achieved an accuracy of 99.59% in a leave-two-out cross validation procedure based on Bayesian classification. Furthermore, when applied to full colonoscopy videos, the presented algorithm detected 26.2% of the frames as indistinct, of which 92.3% were correctly classified. The proposed method outperforms the current best performing algorithm both in terms of accuracy and computation time.
引用
收藏
页码:47 / +
页数:3
相关论文
共 11 条
[1]   Informative-frame filtering in endoscopy videos [J].
An, YH ;
Hwang, S ;
Oh, JH ;
Lee, J ;
Tavanapog, W ;
de Groen, PC ;
Wong, J .
MEDICAL IMAGING 2005: IMAGE PROCESSING, PT 1-3, 2005, 5747 :291-302
[2]  
[Anonymous], 2011, Pei. data mining concepts and techniques
[3]  
[Anonymous], 297 WHO
[4]   Association of Colonoscopy and Death From Colorectal Cancer [J].
Baxter, Nancy N. ;
Goldwasser, Meredith A. ;
Paszat, Lawrence F. ;
Saskin, Refik ;
Urbach, David R. ;
Rabeneck, Linda .
ANNALS OF INTERNAL MEDICINE, 2009, 150 (01) :1-W1
[6]  
Daubechies Ingrid, 1992, Journal of the Acoustical Society of America
[7]   COMPARING THE AREAS UNDER 2 OR MORE CORRELATED RECEIVER OPERATING CHARACTERISTIC CURVES - A NONPARAMETRIC APPROACH [J].
DELONG, ER ;
DELONG, DM ;
CLARKEPEARSON, DI .
BIOMETRICS, 1988, 44 (03) :837-845
[8]  
Duda R. O., 2000, Pattern classification
[9]  
HWANG S, 2005, P 13 ANN ACM INT C M, P912
[10]  
LIU D, 2007, ENG MED BIOL SOC 200, P3470