Predicting the histology of colorectal lesions in a probabilistic framework

In this paper, we present a novel approach to predict the histological diagnosis of colorectal lesions from high-magnification colonoscopy images by means of Pit Pattern analysis. Motivated by the shortcomings of discriminant classifier approaches, we present a generative model based strategy which is closely related to content-based image retrieval (CBIR) systems. The ingredients of the approach are the Dual-Tree Complex Wavelet Transform (DTCWT) and the mathematical construct of copulas. Our experimental study on a set of 627 images confirms, that the joint statistical model leads to impressive prediction results compared to previous work.

[1]  M. Sklar.  Fonctions de repartition a n dimensions et leurs marges , 1959 .

[2]  Bayan S. Sharif,et al.  Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa , 1998, IEEE Transactions on Information Technology in Biomedicine.

[3]  Y. Sano,et al.  Chromoendoscopy using indigo carmine dye spraying with magnifying observation is the most reliable method for differential diagnosis between non-neoplastic and neoplastic colorectal lesions: a prospective study. , 2004, Endoscopy.

[4]  Andreas Uhl,et al.  Image similarity measurement by Kullback-Leibler divergences between complex wavelet subband statistics for texture retrieval , 2008, 2008 15th IEEE International Conference on Image Processing.

[5]  Andreas Uhl,et al.  Modeling the Marginal Distributions of Complex Wavelet Coefficient Magnitudes for the Classification of Zoom-Endoscopy Images , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  Nuno Vasconcelos,et al.  A probabilistic architecture for content-based image retrieval , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[8]  Minh N. Do,et al.  Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance , 2002, IEEE Trans. Image Process..

[9]  Yasushi Sano,et al.  Magnifying colonoscopy as a non-biopsy technique for differential diagnosis of non-neoplastic and neoplastic lesions. , 2006, World journal of gastroenterology.

[10]  H. Joe.  Multivariate models and dependence concepts , 1998 .

[11]  Andreas Uhl,et al.  A joint model of complex wavelet coefficients for texture retrieval , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[12]  H. Tajiri,et al.  Assessment of colorectal lesions using magnifying colonoscopy and mucosal dye spraying: can significant lesions be distinguished? , 2001, Endoscopy.

[13]  Ming-Yao Su,et al.  Magnifying colonoscopy in differentiating neoplastic from nonneoplastic colorectal lesions. , 2001 .

[14]  Dimitris A. Karras,et al.  Computer-aided tumor detection in endoscopic video using color wavelet features , 2003, IEEE Transactions on Information Technology in Biomedicine.

[15]  S. E. Ahmed,et al.  Handbook of Statistical Distributions with Applications , 2007, Technometrics.

[16]  Dimitris A. Karras,et al.  Detection of lesions in endoscopic video using textural descriptors on wavelet domain supported by artificial neural network architectures , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[17]  R. Kiesslich,et al.  Inter- and Intra-Observer Variability of Magnification Chromoendoscopy for Detecting Specialized Intestinal Metaplasia at the Gastroesophageal Junction , 2004, Endoscopy.

[18]  M. Hafner,et al.  Pit Pattern Classification of Zoom-Endoscopic Colon Images using Histogram Techniques , 2006, Proceedings of the 7th Nordic Signal Processing Symposium - NORSIG 2006.

[19]  Richard Baraniuk,et al.  The dual-tree complex wavelet transform , 2005, IEEE Signal Processing Magazine.

[20]  Padraig Cunningham,et al.  The problem of bias in training data in regression problems in medical decision support , 2002, Artif. Intell. Medicine.

[21]  Dimitris A. Karras,et al.  CoLD : a versatile detection system for colorectal lesions in endoscopy video-frames , 2002 .

[22]  Thomas G. Dietterich.  Approximate Statistical Tests for Comparing Supervised Classification Learning Algorithms , 1998, Neural Computation.

[23]  S S Cross,et al.  Efficacy of high magnification chromoscopic colonoscopy for the diagnosis of neoplasia in flat and depressed lesions of the colorectum: a prospective analysis , 2004, Gut.

[24]  S. Kudo,et al.  Colorectal tumours and pit pattern. , 1994, Journal of clinical pathology.

[25]  Andreas Uhl,et al.  Color eigen-subband features for endoscopy image classification , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[26]  Dimitrios K. Iakovidis,et al.  An intelligent system for automatic detection of gastrointestinal adenomas in video endoscopy , 2006, Comput. Biol. Medicine.

[27]  Ming-Yao Su,et al.  Magnifying colonoscopy in differentiating neoplastic from nonneoplastic colorectal lesions , 2001, American Journal of Gastroenterology.

[28]  Richard Baraniuk,et al.  The Dual-tree Complex Wavelet Transform , 2007 .

[29]  Susan A. Murphy,et al.  Monographs on statistics and applied probability , 1990 .

[30]  Shankar M. Krishnan,et al.  Intestinal abnormality detection from endoscopic images , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[31]  Andreas Uhl,et al.  Improving Pit-Pattern Classification of Endoscopy Images by a Combination of Experts , 2009, MICCAI.

[32]  David G. Stork,et al.  Pattern Classification , 1973 .

[33]  Dimitrios K. Iakovidis,et al.  A comparative study of texture features for the discrimination of gastric polyps in endoscopic video , 2005, 18th IEEE Symposium on Computer-Based Medical Systems (CBMS'05).

[34]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[35]  R. Nelsen.  An Introduction to Copulas (Springer Series in Statistics) , 2006 .

[36]  Raouf N. G. Naguib,et al.  Colour texture analysis using co-occurrence matrices for classification of colon cancer images , 2002, IEEE CCECE2002. Canadian Conference on Electrical and Computer Engineering. Conference Proceedings (Cat. No.02CH37373).

[37]  Paul Scheunders,et al.  Multiscale colour texture retrieval using the geodesic distance between multivariate generalized Gaussian models , 2008, 2008 15th IEEE International Conference on Image Processing.

[38]  Hisao Tajiri,et al.  A comparison of magnifying and nonmagnifying colonoscopy for diagnosis of colorectal polyps: A prospective study. , 2003, Gastrointestinal endoscopy.

[39]  R. Nelsen.  An Introduction to Copulas , 1998 .

[40]  DP Hurlstone,et al.  High-resolution magnification chromoendoscopy: common problems encountered in “pit pattern” interpretation and correct classification of flat colorectal lesions , 2002, American Journal of Gastroenterology.