Output details
11 - Computer Science and Informatics
University of Manchester
Automatic analysis of diabetic peripheral neuropathy using multi-scale quantitative morphology of nerve fibres in corneal confocal microscopy imaging
<23>Corneal confocal microscopy (CCM) imaging has the potential to be a much-needed non-invasive biomarker for peripheral neuropathy arising from diabetes and other conditions. This paper is significant because it introduces a novel and effective approach to detection of linear structures in noisy images, allowing quantitative measures of nerve-fibre morphology to be obtained automatically from CCM images. A quantitative evaluation demonstrates that the automatically generated measurements correlate strongly with measurements made manually that in turn have previously demonstrated significant association with the severity of neuropathy.