An unsupervised Bayesian approach for the joint reconstruction and classification of cutaneous reflectance confocal microscopy images

Abdelghafour Halimi, Hadj Batatia, Jimmy Le Digabel, Gwendal Josse, Jean-Yves Tourneret

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

This paper studies a new Bayesian algorithm for the joint reconstruction and classification of reflectance confocal microscopy (RCM) images, with application to the identification of human skin lentigo. The proposed Bayesian approach takes advantage of the distribution of the multiplicative speckle noise affecting the true reflectivity of these images and of appropriate priors for the unknown model parameters. A Markov chain Monte Carlo (MCMC) algorithm is proposed to jointly estimate the model parameters and the image of true reflectivity while classifying images according to the distribution of their reflectivity. Precisely, a Metropolis-within-Gibbs sampler is investigated to sample the posterior distribution of the Bayesian model associated with RCM images and to build estimators of its parameters, including labels indicating the class of each RCM image. The resulting algorithm is applied to synthetic data and to real images from a clinical study containing healthy and lentigo patients.

Original languageEnglish
Title of host publication2017 25th European Signal Processing Conference (EUSIPCO)
PublisherIEEE
Pages241-245
Number of pages5
ISBN (Electronic)9780992862671
DOIs
Publication statusPublished - 26 Oct 2017
Event25th European Signal Processing Conference 2017 - Kos, Greece
Duration: 28 Aug 20172 Sep 2017

Publication series

NameEuropean Signal Processing Conference
ISSN (Electronic)2076-1465

Conference

Conference25th European Signal Processing Conference 2017
Abbreviated titleEUSIPCO 2017
Country/TerritoryGreece
CityKos
Period28/08/172/09/17

Keywords

  • Bayesian algorithm
  • Classification
  • Metropolis-within-Gibbs sampler
  • Reflectance confocal microscopy

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'An unsupervised Bayesian approach for the joint reconstruction and classification of cutaneous reflectance confocal microscopy images'. Together they form a unique fingerprint.

Cite this