Dual-model automatic detection of nerve-fibres in corneal confocal microscopy images

Authors:
M. A. Dabbah;J. Graham;I. Petropoulos;M. Tavakoli;R. A. Malik
Affiliations:
Imaging Sciences and Biomedical Engineering, The University of Manchester, Manchester, UK;Imaging Sciences and Biomedical Engineering, The University of Manchester, Manchester, UK;Cardiovascular Research Group, The University of Manchester, Manchester, UK;Cardiovascular Research Group, The University of Manchester, Manchester, UK;Cardiovascular Research Group, The University of Manchester, Manchester, UK
Venue:
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I
Year:
2010

Citing 5
Cited 0

A taxonomy for texture description and identification

A taxonomy for texture description and identification
Unsupervised texture segmentation using Gabor filters

Pattern Recognition
Fingerprint Image Enhancement: Algorithm and Performance Evaluation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Muliscale Vessel Enhancement Filtering

MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
The monogenic signal

IEEE Transactions on Signal Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Corneal Confocal Microscopy (CCM) imaging is a non-invasive surrogate of detecting, quantifying and monitoring diabetic peripheral neuropathy. This paper presents an automated method for detecting nerve-fibres from CCM images using a dual-model detection algorithm and compares the performance to well-established texture and feature detection methods. The algorithm comprises two separate models, one for the background and another for the foreground (nerve-fibres), which work interactively. Our evaluation shows significant improvement (p ≅ 0) in both error rate and signal-to-noise ratio of this model over the competitor methods. The automatic method is also evaluated in comparison with manual ground truth analysis in assessing diabetic neuropathy on the basis of nerve-fibre length, and shows a strong correlation (r = 0.92). Both analyses significantly separate diabetic patients from control subjects (p ≅ 0).