Affordable Access

deepdyve-link
Publisher Website

A non-parametric segmentation methodology for oral videocapillaroscopic images

Authors
  • Bellavia, Fabio
  • Cacioppo, Antonino
  • Lupaşcu, Carmen Alina
  • Messina, Pietro
  • Scardina, Giuseppe
  • Tegolo, Domenico
  • Valenti, Cesare1, 2
  • 1 Dipartimento di Matematica e Informatica, Università degli Studi di Palermo
  • 2 Dipartimento di Scienze Stomatologiche, Università degli Studi di Palermo
Type
Published Article
Journal
Computer Methods and Programs in Biomedicine
Publisher
Elsevier
Publication Date
Jan 01, 2014
Accepted Date
Feb 14, 2014
Identifiers
DOI: 10.1016/j.cmpb.2014.02.009
Source
Elsevier
Keywords
License
Unknown

Abstract

We aim to describe a new non-parametric methodology to support the clinician during the diagnostic process of oral videocapillaroscopy to evaluate peripheral microcirculation. Our methodology, mainly based on wavelet analysis and mathematical morphology to preprocess the images, segments them by minimizing the within-class luminosity variance of both capillaries and background. Experiments were carried out on a set of real microphotographs to validate this approach versus handmade segmentations provided by physicians. By using a leave-one-patient-out approach, we pointed out that our methodology is robust, according to precision–recall criteria (average precision and recall are equal to 0.924 and 0.923, respectively) and it acts as a physician in terms of the Jaccard index (mean and standard deviation equal to 0.858 and 0.064, respectively).

Report this publication

Statistics

Seen <100 times