Automatic colposcopy video tissue classification using higher order entropy-based image registration

Authors:
Juan D. GarcíA-Arteaga;Jan Kybic;Wenjing Li
Affiliations:
Center for Machine Perception, Czech Technical University, Department of Cybernetics, Faculty of Electrical Engineering, Prague, Czech Republic;Center for Machine Perception, Czech Technical University, Department of Cybernetics, Faculty of Electrical Engineering, Prague, Czech Republic;STI Medical Systems, 4275 Executive Square #825, La Jolla, California 92037, USA
Venue:
Computers in Biology and Medicine
Year:
2011

Citing 13
Cited 0

A survey of image registration techniques

ACM Computing Surveys (CSUR)
Validation of registration accuracy

Handbook of medical imaging
Image Registration by Maximization of Combined Mututal Information and Gradient Information

MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
A Generic Framework for Non-rigid Registration Based on Non-uniform Multi-level Free-Form Deformations

MICCAI '01 Proceedings of the 4th International Conference on Medical Image Computing and Computer-Assisted Intervention
Color spaces for computer graphics

SIGGRAPH '78 Proceedings of the 5th annual conference on Computer graphics and interactive techniques
An Automated, Segmentation-Based, Rigid Registration System for Cervigram" Images Utilizing Simple Clustering and Active Contour Techniques

CBMS '04 Proceedings of the 17th IEEE Symposium on Computer-Based Medical Systems
Identifying Precursory Cancer Lesions Using Temporal Texture Analysis

CRV '05 Proceedings of the 2nd Canadian conference on Computer and Robot Vision
Cervical Cancer Detection Using Colposcopic Images: a Temporal Approach

ENC '05 Proceedings of the Sixth Mexican International Conference on Computer Science
Registration of Challenging Image Pairs: Initialization, Estimation, and Decision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Modeling Aceto-White Temporal Patterns to Segment Colposcopic Images

IbPRIA '07 Proceedings of the 3rd Iberian conference on Pattern Recognition and Image Analysis, Part II
Aceto-white temporal pattern classification using k-NN to identify precancerous cervical lesion in colposcopic images

Computers in Biology and Medicine
Multi-dimensional mutual information based robust image registration using maximum distance-gradient-magnitude

IPMI'05 Proceedings of the 19th international conference on Information Processing in Medical Imaging
Fast parametric elastic image registration

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Colposcopy is a well-established method to detect and diagnose intraepithelial lesions and uterine cervical cancer in early stages. During the exam color and texture changes are induced by the application of a contrast agent (e.g.3-5% acetic acid solution or iodine). Our aim is to densely quantify the change in the acetowhite decay level for a sequence of images captured during a colposcopy exam to help the physician in his diagnosis providing new tools that overcome subjectivity and improve reproducibility. As the change in acetowhite decay level must be calculated from the same tissue point in all images, we present an elastic image registration scheme able to compensate patient, camera and tissue movement robustly in cervical images. The image registration is based on a novel multi-feature entropy similarity criterion. Temporal features are then extracted using the color properties of the aligned image sequence and a dual compartment tissue model of the cervix. An example of the use of the temporal features for pixel-wise classification is presented and the results are compared against ground truth histopathological annotations.