Cochlea modelling: clinical challenges and tubular extraction

Authors:
Gavin Baker;Stephen O'Leary;Nick Barnes;Ed Kazmierczak
Affiliations:
Department of Computer Science and Software Engineering, The University of Melbourne, Australia;Department of Otolaryngology, The University of Melbourne, Australia;Department of Computer Science and Software Engineering, The University of Melbourne, Australia;Department of Computer Science and Software Engineering, The University of Melbourne, Australia
Venue:
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Year:
2004

Citing 6
Cited 0

Three-Dimensional Descriptions Based on the Analysis of the Invariant and Quasi-Invariant Properties of Some Curved-Axis Generalized Cylinders

IEEE Transactions on Pattern Analysis and Machine Intelligence
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
CEASAR: a smooth, accurate and robust centerline extraction algorithm

Proceedings of the conference on Visualization '00
Model-Based Multiscale Detection of 3D Vessels

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Principal Flow for Tubular Objects with Non-Circular Cross-Sections

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Three-dimensional modeling and visualization of the cochlea on the Internet

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

The cochlear ear implant has become a standard clinical intervention for the treatment of profound sensorineural hearing loss After 20 years of research into implant design, there are still many unanswered clinical questions that could benefit from new analysis and modelling techniques This research aims to develop techniques for extracting the cochlea from medical images to support clinical outcomes We survey the challenges posed by some of these clinical questions and the problems of cochlea modeling We present a novel algorithm for extracting tubular objects with non-circular cross-sections from medical images, including results from generated and clinical data We also describe a cochlea model, driven by clinical knowledge and requirements, for representation and analysis The 3-dimensional cochlea representation described herein is the first to explicitly integrate path and cross-sectional shape, specifically directed at addressing clinical outcomes The tubular extraction algorithm described is one of very few approaches capable of handling non-circular cross-sections The clinical results, taken from a human CT scan, show the first extracted centreline path and orthogonal cross-sections for the human cochlea.