Robust local estimation in anisotropic diffusion process

Refka RAGOUBI HOR; Valérie BURDIN; Olivier Rémy-Néris

hal-00725548, version 1

Robust local estimation in anisotropic diffusion process

Refka RAGOUBI HOR ()^a^, 1, Valérie BURDIN (, )^a^, 1, 3, Olivier Rémy-Néris ²

International Conference of the IEEE Engineering in Medicine and Biology Society (2011) 5710-5713

Abstract: In this work we propose to use an anisotropic diffusion process using robust statistics. We show that smoothing, while preserving edges, helps the segmentation of upper limb bones (shoulder) in MRI data bases. The anisotropic diffusion equation is mainly controlled using an automatic edge stopping function based on Tukey's biweight function, which depends on the values of gradients pixels. These values are divided into two classes: high gradients for pixels belonging to edges or noisy pixels, low ones otherwise. This process also depends on a threshold gradient parameter which splits both former classes. So a robust local estimation method is proposed to better eliminate the noise in the image while preserving edges. Firstly, the efficiency of the model in the noise reduction is quantified using an entropy criterion on synthetic data with different noise levels to evaluate the smoothing of the regions. Secondly, we use the Pratt's Figure of Merit (FOM) method to evaluate edges preservation. Eventually, a qualitative edge evaluation is given on a MRI volume of the shoulder joint.

a – Télécom Bretagne
1: Département Image et Traitement Information (ITI)
Institut Mines-Télécom – Télécom Bretagne – PRES Université Européenne de Bretagne [UEB]
2: CHU de Brest- service de rééducation fonctionnelle
CHU Brest
3: Laboratoire de Traitement de l'Information Medicale (LATIM)
INSERM : U650 – Université de Bretagne Occidentale [UBO] – Institut Mines-Télécom – Télécom Bretagne – CHU Brest – PRES Université Européenne de Bretagne [UEB]

hal-00725548, version 1
http://hal.archives-ouvertes.fr/hal-00725548
oai:hal.archives-ouvertes.fr:hal-00725548
From: Bibliothèque Télécom Bretagne <>
Submitted for: Brest Bibliotheque TELECOM Bretagne <>
Submitted on: Monday, 27 August 2012 13:15:30
Updated on: Monday, 27 August 2012 13:15:31

See detailed view

Export

Bibtex EndNote TEI RefWorks

%% hal-00725548, version 1
%% http://hal.archives-ouvertes.fr/hal-00725548
@inproceedings{ragoubihor:hal-00725548,
    hal_id = {hal-00725548},
    url = {http://hal.archives-ouvertes.fr/hal-00725548},
    title = {{Robust local estimation in anisotropic diffusion process}},
    author = {RAGOUBI HOR, Refka and BURDIN, Val{\'e}rie and R{\'e}my-N{\'e}ris, Olivier},
    abstract = {{In this work we propose to use an anisotropic diffusion process using robust statistics. We show that smoothing, while preserving edges, helps the segmentation of upper limb bones (shoulder) in MRI data bases. The anisotropic diffusion equation is mainly controlled using an automatic edge stopping function based on Tukey's biweight function, which depends on the values of gradients pixels. These values are divided into two classes: high gradients for pixels belonging to edges or noisy pixels, low ones otherwise. This process also depends on a threshold gradient parameter which splits both former classes. So a robust local estimation method is proposed to better eliminate the noise in the image while preserving edges. Firstly, the efficiency of the model in the noise reduction is quantified using an entropy criterion on synthetic data with different noise levels to evaluate the smoothing of the regions. Secondly, we use the Pratt's Figure of Merit (FOM) method to evaluate edges preservation. Eventually, a qualitative edge evaluation is given on a MRI volume of the shoulder joint.}},
    language = {English},
    affiliation = {D{\'e}partement Image et Traitement Information - ITI , CHU de Brest- service de r{\'e}{\'e}ducation fonctionnelle , Laboratoire de Traitement de l'Information Medicale - LATIM},
    booktitle = {{International Conference of the IEEE Engineering in Medicine and Biology Society}},
    pages = {5710-5713},
    address = {Boston, United States},
    journal = {International Conference of the IEEE Engineering in Medicine and Biology Society},
    note = {11363 11363 },
    audience = {international },
    year = {2011},
}

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="hal-00725548"><analytic>
<author><persName><forename>Refka</forename><surname>RAGOUBI HOR</surname></persName>
<affiliation>
<orgName type="laboratory">ITI</orgName>
<orgName type="team">Département Image et Traitement Information</orgName>
<country>FR</country>
<orgName type="institution">Institut Mines-Télécom</orgName>
<orgName type="institution">Télécom Bretagne</orgName>
<orgName type="institution">PRES Université Européenne de Bretagne [UEB]</orgName>
</affiliation>
</author>
<author><persName><forename>Valérie</forename><surname>BURDIN</surname></persName>
<affiliation>
<orgName type="laboratory">ITI</orgName>
<orgName type="team">Département Image et Traitement Information</orgName>
<country>FR</country>
<orgName type="institution">Institut Mines-Télécom</orgName>
<orgName type="institution">Télécom Bretagne</orgName>
<orgName type="institution">PRES Université Européenne de Bretagne [UEB]</orgName>
</affiliation>
<affiliation>
<orgName type="laboratory">LATIM</orgName>
<orgName type="team">Laboratoire de Traitement de l'Information Medicale</orgName>
<country>FR</country>
<orgName type="institution">INSERM : U650</orgName>
<orgName type="institution">Université de Bretagne Occidentale [UBO]</orgName>
<orgName type="institution">Institut Mines-Télécom</orgName>
<orgName type="institution">Télécom Bretagne</orgName>
<orgName type="institution">CHU Brest</orgName>
<orgName type="institution">PRES Université Européenne de Bretagne [UEB]</orgName>
</affiliation>
</author>
<author><persName><forename>Olivier</forename><surname>Rémy-Néris</surname></persName>
<affiliation>
<orgName type="team">CHU de Brest- service de rééducation fonctionnelle</orgName>
<country>FR</country>
<orgName type="institution">CHU Brest</orgName>
</affiliation>
</author>
<title type="main" level="a">Robust local estimation in anisotropic diffusion process</title></analytic><monogr><title level="m" type="main">International Conference of the IEEE Engineering in Medicine and Biology Society</title><meeting>International Conference of the IEEE Engineering in Medicine and Biology Society</meeting><title level="j" type="main">International Conference of the IEEE Engineering in Medicine and Biology Society</title><imprint><pubPlace><settlement>Boston</settlement><country>United States</country></pubPlace><biblScope type="publicationDate">2011-00-00</biblScope><biblScope type="pp">5710-5713</biblScope></imprint></monogr><idno type="HALid">http://hal.archives-ouvertes.fr/hal-00725548</idno></biblStruct>
</listBibl>
</listBibl>