6533b82bfe1ef96bd128d73c
RESEARCH PRODUCT
A non-parametric segmentation methodology for oral videocapillaroscopic images
Cesare ValentiDomenico TegoloFabio BellaviaCarmen Alina LupascuGiuseppe Alessandro ScardinaAntonino CacioppoPietro Messinasubject
Jaccard indexComputer scienceHealth InformaticsWavelet analysisMathematical morphologyStandard deviationCross-validationOral videocapillaroscopyWaveletImage Processing Computer-AssistedHumansSegmentationComputer visionMouthSettore INF/01 - Informaticabusiness.industryMicrocirculationNonparametric statisticsReproducibility of ResultsModels TheoreticalCapillariesComputer Science ApplicationsMathematical morphologyLeave-one-out cross-validationArtificial intelligencebusinessPrecision and recallNon-parametric image segmentationAlgorithmsSoftwaredescription
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). © 2014 Elsevier Ireland Ltd.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2014-01-01 |