Predicting the histology of colorectal lesions in a probabilistic framework

  title={Predicting the histology of colorectal lesions in a probabilistic framework},
  author={Roland Kwitt and Andreas Uhl and Michael H{\"a}fner and Alfred Gangl and Friedrich Wrba and Andreas V{\'e}csei},
  journal={2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops},
  • R. Kwitt, A. Uhl, A. Vécsei
  • Published 13 June 2010
  • Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops
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… 

Figures and Tables from this paper

The Classification of Endoscopy Images with Persistent Homology
  • O. Dunaeva, H. Edelsbrunner, S. Kashin
  • Medicine, Computer Science
    2014 16th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing
  • 2014
The Classification of Endoscopy Images with Persistent Homology
Aiming at the automatic diagnosis of tumors from narrow band imaging (NBI) magnifying endoscopy (ME) images of the stomach, we combine methods from image processing, computational topology, and
Learning Pit Pattern Concepts for Gastroenterological Training
This article proposes an approach to learn the characteristics of colonic mucosal surface structures, the so called pit patterns, commonly observed during high-magnification colonoscopy, using recent research on semantic image retrieval and annotation.
Computer-aided colorectal tumor classification in NBI endoscopy using local features
Multimodal Information Integration and Fusion for Histology Image Classification
This study proposes a novel framework of histology image classification based on an array of C-RSPM Collateral Representative Subspace Projection Modeling models that performs significantly better than other classifiers in the comparison.
Stabilization and Image Labeling for NBI Endoscopic Image Recognition
Three methods to overcome two problems of the prototype computer-aided diagnosis system for colorectal endoscopy, which recognize the center of video frame of endoscope and provide classification results to endoscopists in a frame by frame manner are proposed.
A survey of feature extraction and fusion of deep learning for detection of abnormalities in video endoscopy of gastrointestinal-tract
A comprehensive review of feature extraction techniques and deep learning methods which were specifically developed for automatic analysis of endoscopic videos and categorize features extraction techniques according to image processing domains and further classify them based on their visual descriptions.
Computer-Aided Decision Support Systems for Endoscopy in the Gastrointestinal Tract: A Review
An introduction to computer-aided decision support systems specifically targeted at endoscopy in the gastrointestinal tract and a discussion of some common issues concerning the approaches reviewed and suggestions of possible ways to resolve them.
Image Classification of Human Carcinoma Cells Using Complex Wavelet-Based Covariance Descriptors
The tool provides an automated, time- and cost-efficient analysis of cancer cell morphology to classify different cancer cell lines using image-processing techniques, which can be used as an alternative to the costly short tandem repeat (STR) analysis.
Transfer Learning for Endoscopic Image Classification
The proposed MMDTL2 outperforms MMDT for real data sets taken by different endoscopes and the dual formulation of the optimization problem is developed in order to reduce the computation cost.


Improving Pit-Pattern Classification of Endoscopy Images by a Combination of Experts
This work discusses computer-aided pit-pattern classification of surface structures observed during high-magnification colonoscopy in order to support dignity assessment of colonic polyps and proposes a novel classifier combination approach which is similar to a combination of experts.
A comparative study of texture features for the discrimination of gastric polyps in endoscopic video
The results advocate the feasibility of a computer-based system for polyp detection in video gastroscopy that exploits the textural characteristics of the gastric mucosa in conjunction with its color appearance.
Computer-aided tumor detection in endoscopic video using color wavelet features
An approach to the detection of tumors in colonoscopic video based on a new color feature extraction scheme to represent the different regions in the frame sequence based on the wavelet decomposition, reaching 97% specificity and 90% sensitivity.
CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames
An intelligent system for automatic detection of gastrointestinal adenomas in video endoscopy
Detection of lesions in endoscopic video using textural descriptors on wavelet domain supported by artificial neural network architectures
A framework for classification of suspicious lesions using the video produced during an endoscopic session is presented, based on a feature extraction scheme that uses second order statistical information of the wavelet transformation.
Magnifying colonoscopy in differentiating neoplastic from nonneoplastic colorectal lesions
The pit pattern analysis of colorectal lesions by magnifying colonoscope combined with indigocarmine dye is a useful and objective tool for differentiating neoplastic from nonneoplastic lesions of the large bowel.
Pit Pattern Classification of Zoom-Endoscopic Colon Images using Histogram Techniques
Histogram-based techniques for an automated classification of magnifying endoscope images with respect to pit patterns of colon lesions are discussed and compared. Currently, the results only allow a
Colorectal tumours and pit pattern.
There were associations between individual pits and crypts in colorectal tumours and there was a correlation between pit pattern and the structure of the underlying crypt or gland.