Texture and color based image segmentation and pathology detection in capsule endoscopy videos

This paper presents an in-depth study of several approaches to exploratory analysis of wireless capsule endoscopy images (WCE). It is demonstrated that versatile texture and color based descriptors of image regions corresponding to various anomalies of the gastrointestinal tract allows their accurate detection of pathologies in a sequence of WCE frames. Moreover, through classification of single pixels described by texture features of their neighborhood, the images can be segmented into homogeneous areas well matched to the image content. For both, detection and segmentation tasks the same procedure is applied which consists of features calculation, relevant feature subset selection and classification stages. This general three-stage framework is realized using various recognition strategies. In particular, the performance of the developed Vector Supported Convex Hull classification algorithm is compared against Support Vector Machines run in configuration with two different feature selection methods.

[1]  Duncan Bell,et al.  Stomach, intestine, and colon tissue discriminators for wireless capsule endoscopy images , 2005, SPIE Medical Imaging.

[2]  John N. Lygouras,et al.  A neuro-fuzzy-based system for detecting abnormal patterns in wireless-capsule endoscopic images , 2007, Neurocomputing.

[3]  David A. Freedman,et al.  Statistical Models: Theory and Practice: References , 2005 .

[4]  Nikolaos G. Bourbakis,et al.  Detecting abnormal patterns in WCE images , 2005, Fifth IEEE Symposium on Bioinformatics and Bioengineering (BIBE'05).

[5]  Baopu Li,et al.  Ulcer recognition in capsule endoscopy images by texture features , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[6]  Carlos S. Lima,et al.  Detection of small bowel tumors in capsule endoscopy frames using texture analysis based on the discrete wavelet transform , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[8]  P. Swain,et al.  Wireless capsule endoscopy. , 2002, The Israel Medical Association journal : IMAJ.

[9]  Miguel Tavares Coimbra,et al.  Extracting clinical information from endoscopic capsule exams using MPEG-7 visual descriptors , 2005 .

[10]  Carla E. Brodley,et al.  Feature Selection for Unsupervised Learning , 2004, J. Mach. Learn. Res..

[11]  Vincent Maunoury,et al.  Small-bowel ulcerations at wireless capsule endoscopy: go the whole way , 2007, Gut.

[12]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[13]  Zvi Fireman,et al.  Initial experience of wireless-capsule endoscopy for evaluating occult gastrointestinal bleeding and suspected small bowel pathology , 2002, American Journal of Gastroenterology.

[14]  Mark H. Fisher,et al.  Bleeding detection in wireless capsule endoscopy using adaptive colour histogram model and support vector classification , 2008, SPIE Medical Imaging.

[15]  David P. Dobkin,et al.  The quickhull algorithm for convex hulls , 1996, TOMS.

[16]  Andrzej Materka,et al.  Clustering stability-based feature selection for unsupervised texture classification , 2009 .

[17]  Ian Witten,et al.  Data Mining , 2000 .

[18]  Miguel Tavares Coimbra,et al.  MPEG-7 Visual Descriptors—Contributions for Automated Feature Extraction in Capsule Endoscopy , 2006, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Fernando Vilariño,et al.  ROC curves and video analysis optimization in intestinal capsule endoscopy , 2006, Pattern Recognit. Lett..

[20]  M. Goenka,et al.  Single center experience of capsule endoscopy in patients with obscure gastrointestinal bleeding. , 2011, World journal of gastroenterology.

[21]  P. Swain,et al.  Wireless capsule endoscopy and Crohn’s disease , 2005, Gut.

[22]  Artur Klepaczko,et al.  Convex Hull-Based Feature Selection in Application to Classification of Wireless Capsule Endoscopic Images , 2009, ACIVS.

[23]  Miguel Tavares Coimbra,et al.  Topographic Segmentation and Transit Time Estimation for Endoscopic Capsule Exams , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[24]  Miguel Tavares Coimbra,et al.  Automated Topographic Segmentation and Transit Time Estimation in Endoscopic Capsule Exams , 2008, IEEE Transactions on Medical Imaging.

[25]  Jack Sklansky,et al.  On Automatic Feature Selection , 1988, Int. J. Pattern Recognit. Artif. Intell..

[26]  Bill Buckles,et al.  Bleeding detection from capsule endoscopy videos , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[27]  Andrzej Materka,et al.  Quantitative description of 3D vascularity images: texture-based approach and its verification through cluster analysis , 2011, Pattern Analysis and Applications.

[28]  C. Robles-Medranda,et al.  Multiple Intestinal Erosions as a Result of Hemorrhage due to Parasites: Case Reports and Review of the Literature , 2011, Diagnostic and therapeutic endoscopy.

[29]  Paul Swain,et al.  Capsule endoscopy in the evaluation of patients with suspected small intestinal bleeding: Results of a pilot study. , 2002, Gastrointestinal endoscopy.

[30]  Max Q.-H. Meng,et al.  Computer-based detection of bleeding and ulcer in wireless capsule endoscopy images by chromaticity moments , 2009, Comput. Biol. Medicine.

[31]  Michal Strzelecki,et al.  MaZda - A software package for image texture analysis , 2009, Comput. Methods Programs Biomed..

[32]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[33]  Pavel Pudil,et al.  Current Feature Selection Techniques in Statistical Pattern Recognition , 2005, CORES.

[34]  Michal Mackiewicz,et al.  Wireless Capsule Endoscopy Color Video Segmentation , 2008, IEEE Transactions on Medical Imaging.

[35]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[36]  Maxwell M Chait,et al.  Gastroesophageal reflux disease: Important considerations for the older patients. , 2010, World journal of gastrointestinal endoscopy.

[37]  Daniel C Barbosa,et al.  Automatic small bowel tumor diagnosis by using multi-scale wavelet-based analysis in wireless capsule endoscopy images , 2012, Biomedical engineering online.

[38]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[39]  Marek Kurzynski,et al.  Computer Recognition Systems 3 , 2009, Advances in Intelligent and Soft Computing.

[40]  Michal Wozniak,et al.  Computer Recognition Systems: Proceedings of 4th International Conference on Computer Recognition Systems CORES'05 (Advances in Soft Computing) , 2005 .

[41]  Sae Hwang,et al.  Polyp detection in Wireless Capsule Endoscopy videos based on image segmentation and geometric feature , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[42]  Leontios J. Hadjileontiadis,et al.  Capsule endoscopy image analysis using texture information from various colour models , 2012, Comput. Methods Programs Biomed..

[43]  Zvi Fireman,et al.  Initial experience of wireless-capsule endoscopy for evaluating occult gastrointestinal bleeding and suspected small bowel pathology. , 2002 .

[44]  Ram D. Sriram,et al.  A model of deformable rings for interpretation of wireless capsule endoscopic videos , 2006, Medical Image Anal..

[45]  Byung Ro Moon,et al.  Hybrid Genetic Algorithms for Feature Selection , 2004, IEEE Trans. Pattern Anal. Mach. Intell..