<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of tel-05027456</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-04T12:01:51+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Novel 3D Deep Learning Models for Knee Osteoarthritis Diagnosis and Prediction from MRI Data</title>
            <title xml:lang="fr">Nouveaux modèles 3D d'apprentissage profond pour le diagnostic et la prédiction de l'arthrose du genou à partir de données d'IRM</title>
            <author role="aut">
              <persName>
                <forename type="first">Mohamed</forename>
                <surname>Berrimi</surname>
              </persName>
              <idno type="idhal" notation="numeric">1530383</idno>
              <idno type="halauthorid" notation="string">3138237-1530383</idno>
              <idno type="IDREF">https://www.idref.fr/284232610</idno>
              <affiliation ref="#struct-523748"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>ABES</forename>
                <surname>STAR</surname>
              </persName>
              <email type="md5">f5aa7f563b02bb6adbba7496989af39a</email>
              <email type="domain">abes.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-04-09 15:53:06</date>
              <date type="whenModified">2026-04-09 00:44:07</date>
              <date type="whenReleased">2025-04-09 15:53:07</date>
              <date type="whenProduced">2024-11-13</date>
              <date type="whenEndEmbargoed">2025-04-09</date>
              <ref type="file" target="https://theses.hal.science/tel-05027456v1/document">
                <date notBefore="2025-04-09"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://theses.hal.science/tel-05027456v1/file/2024ORLE1085_vm.pdf" id="file-5027456-4355225">
                <date notBefore="2025-04-09"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="131274">
                <persName>
                  <forename>ABES</forename>
                  <surname>STAR</surname>
                </persName>
                <email type="md5">f5aa7f563b02bb6adbba7496989af39a</email>
                <email type="domain">abes.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">tel-05027456</idno>
            <idno type="halUri">https://theses.hal.science/tel-05027456</idno>
            <idno type="halBibtex">berrimi:tel-05027456</idno>
            <idno type="halRefHtml">Human health and pathology. Université d'Orléans, 2024. English. &lt;a target="_blank" href="https://www.theses.fr/2024ORLE1085"&gt;&amp;#x27E8;NNT : 2024ORLE1085&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Human health and pathology. Université d'Orléans, 2024. English. &amp;#x27E8;NNT : 2024ORLE1085&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-5027456-4355225"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-TOURS">Université François Rabelais</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-ORLEANS">Université d'Orléans</idno>
            <idno type="stamp" n="INSMI">CNRS-INSMI - INstitut des Sciences Mathématiques et de leurs Interactions</idno>
            <idno type="stamp" n="STAR">STAR - Dépôt national des thèses électroniques</idno>
            <idno type="stamp" n="IDP">Institut Denis Poisson</idno>
            <idno type="stamp" n="THESES-UO" corresp="UNIV-ORLEANS">Thèses de l'Université d'Orléans</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Novel 3D Deep Learning Models for Knee Osteoarthritis Diagnosis and Prediction from MRI Data</title>
                <title xml:lang="fr">Nouveaux modèles 3D d'apprentissage profond pour le diagnostic et la prédiction de l'arthrose du genou à partir de données d'IRM</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Mohamed</forename>
                    <surname>Berrimi</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1530383</idno>
                  <idno type="halauthorid" notation="string">3138237-1530383</idno>
                  <idno type="IDREF">https://www.idref.fr/284232610</idno>
                  <affiliation ref="#struct-523748"/>
                </author>
              </analytic>
              <monogr>
                <idno type="nnt">2024ORLE1085</idno>
                <imprint>
                  <date type="dateDefended">2024-11-13</date>
                </imprint>
                <authority type="institution">Université d'Orléans</authority>
                <authority type="school">École doctorale Mathématiques, Informatique, Physique Théorique et Ingénierie des Systèmes (Centre-Val de Loire ; 2012-....)</authority>
                <authority type="supervisor">Rachid Jennane</authority>
                <authority type="jury">Aladine Chetouani [Président]</authority>
                <authority type="jury">Alice Ahlem Othmani [Rapporteur]</authority>
                <authority type="jury">Mouloud Adel [Rapporteur]</authority>
                <authority type="jury">Mohamed Jarraya</authority>
                <authority type="jury">Sylvie Treuillet</authority>
                <authority type="jury">Mame Diarra Fall</authority>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Magnetic Resonance Imaging</term>
                <term xml:lang="en">Knee osteoarthritis</term>
                <term xml:lang="en">Deep Learning</term>
                <term xml:lang="fr">Imagerie par résonance magnétique</term>
                <term xml:lang="fr">Arthrose du genou</term>
                <term xml:lang="fr">Apprentissage profond</term>
              </keywords>
              <classCode scheme="halDomain" n="sdv.mhep">Life Sciences [q-bio]/Human health and pathology</classCode>
              <classCode scheme="halDomain" n="info.info-im">Computer Science [cs]/Medical Imaging</classCode>
              <classCode scheme="halDomain" n="info.info-ti">Computer Science [cs]/Image Processing [eess.IV]</classCode>
              <classCode scheme="halTypology" n="THESE">Theses</classCode>
              <classCode scheme="halOldTypology" n="THESE">Theses</classCode>
              <classCode scheme="halTreeTypology" n="THESE">Theses</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Knee Osteoarthritis (OA) is a widespread and debilitating condition affecting millions, with no cure currently available. Accurate and timely diagnosis is vital for effective management and better patient outcomes. Although MRI provides valuable insights into soft tissues, current diagnostic methods typically rely on single-view analysis, possibly missing important information. This thesis introduces advanced deep learning models for robust knee OA diagnosis from multi-view MRI data, incorporating multi-view, multi-label,multi-instance, multi-modal, and multi-task architectures. By leveraging multiple MRI views (axial, coronal,sagittal) and sequences, these 2D and 3D CNN models were trained on the public OAI database, achieving 93.20% to 96.70% accuracy, surpassing current benchmarks. Additionally, segmentation models were developed to highlight anatomical structures key to OA evaluation, underscoring the potential of deep learning to enhance diagnostic precision and patient care in knee OA.</p>
            </abstract>
            <abstract xml:lang="fr">
              <p>L'arthrose du genou, une condition sans remède, exige un diagnostic précis pour une gestion optimale. Bien que l’IRM offre des informations essentielles, les méthodes actuelles se limitent souvent à une vue unique, risquant de manquer des détails critiques. Cette thèse propose des modèles d'apprentissage profond intégrant des architectures multi-vues, multi-étiquettes, multi-instances, multi-modales et multi-tâches pour un diagnostic plus robuste. Entraînés sur la base publique OAI, ces modèles 2D et 3D, utilisant des vues axiales, coronales et sagittales avec diverses séquences IRM, atteignent une précision de 93,20% à 96,70%, surpassant les méthodes existantes. En plus de la classification, des modèles de segmentation anatomique ont été développés pour mieux évaluer l'arthrose, démontrant ainsi le potentiel de l’apprentissage profond à améliorer le diagnostic et ainsi optimiser la prise en charge des patients.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-523748" status="VALID">
          <idno type="IdRef">226407217</idno>
          <idno type="RNSR">201822709K</idno>
          <idno type="ROR">https://ror.org/05djhd259</idno>
          <idno type="Wikidata">Q52607329</idno>
          <orgName>Institut Denis Poisson</orgName>
          <orgName type="acronym">IDP</orgName>
          <date type="start">2018-01-01</date>
          <desc>
            <address>
              <addrLine>Université d'Orléans, Collégium Sciences et Techniques, Bâtiment de mathématiques - Route de Chartres, B.P. 6759 - 45067 Orléans cedex 2, FRANCE ; Université de Tours, UFR Sciences et Techniques, Parc de Grandmont, 37200 Tours - FRANCE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.idpoisson.fr</ref>
          </desc>
          <listRelation>
            <relation name="UMR 7013" active="#struct-300297" type="direct"/>
            <relation name="UMR 7013" active="#struct-300298" type="direct"/>
            <relation name="UMR7013" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300297" status="VALID">
          <idno type="IdRef">026402971</idno>
          <idno type="ISNI">0000 0001 2158 1666</idno>
          <idno type="ROR">https://ror.org/014zrew76</idno>
          <orgName>Université d'Orléans</orgName>
          <orgName type="acronym">UO</orgName>
          <desc>
            <address>
              <addrLine>Château de la Source - Avenue du Parc Floral - BP 6749 - 45067 Orléans cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-orleans.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300298" status="VALID">
          <idno type="IdRef">026404478</idno>
          <idno type="ISNI">0000000121608742</idno>
          <idno type="ROR">https://ror.org/02wwzvj46</idno>
          <orgName>Université de Tours</orgName>
          <orgName type="acronym">UT</orgName>
          <date type="start">1970-12-17</date>
          <desc>
            <address>
              <addrLine>60 rue du Plat d'Étain, 37020 Tours cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-tours.fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>