A non-parametric segmentation methodology for oral videocapillaroscopic images |
| |
Authors: | Fabio Bellavia Antonino Cacioppo Carmen Alina Lupa?cu Pietro Messina Giuseppe Scardina Domenico Tegolo Cesare Valenti |
| |
Affiliation: | 1. Dipartimento di Matematica e Informatica, Università degli Studi di Palermo, Italy;2. Dipartimento di Scienze Stomatologiche, Università degli Studi di Palermo, Italy |
| |
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). |
| |
Keywords: | Non-parametric image segmentation Oral videocapillaroscopy Wavelet analysis Mathematical morphology Leave-one-out cross-validation |
本文献已被 ScienceDirect 等数据库收录! |