<?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 hal-05251649</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="2026-05-15T15:20:03+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Divergence-Aware Training with Automatic Subgroup Mitigation for Breast Tumor Segmentation</title>
            <author role="aut">
              <persName>
                <forename type="first">Eleonora</forename>
                <surname>Poeta</surname>
              </persName>
              <email type="md5">76e2019ef5c6ee910a62e8cf187f3c89</email>
              <email type="domain">polito.it</email>
              <idno type="idhal" notation="numeric">1581676</idno>
              <idno type="halauthorid" notation="string">2265927-1581676</idno>
              <idno type="ORCID">https://orcid.org/0009-0001-7289-0036</idno>
              <affiliation ref="#struct-6571"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Luisa</forename>
                <surname>Vargas</surname>
              </persName>
              <idno type="idhal" notation="numeric">1588932</idno>
              <idno type="halauthorid" notation="string">2745920-1588932</idno>
              <idno type="ORCID">https://orcid.org/0009-0006-5741-8485</idno>
              <affiliation ref="#struct-421532"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Daniele</forename>
                <surname>Falcetta</surname>
              </persName>
              <email type="md5">dc9e42fe95dd7e3ace6ab39a0f4c5245</email>
              <email type="domain">eurecom.fr</email>
              <idno type="idhal" notation="numeric">1558978</idno>
              <idno type="halauthorid" notation="string">2888841-1558978</idno>
              <affiliation ref="#struct-421532"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Vincenzo</forename>
                <surname>Marciano’</surname>
              </persName>
              <idno type="idhal" notation="numeric">1588933</idno>
              <idno type="halauthorid" notation="string">3805498-1588933</idno>
              <idno type="ORCID">https://orcid.org/0009-0000-2238-8040</idno>
              <affiliation ref="#struct-421532"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Eliana</forename>
                <surname>Pastor</surname>
              </persName>
              <idno type="idhal" notation="numeric">1588934</idno>
              <idno type="halauthorid" notation="string">3766896-1588934</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3664-4137</idno>
              <affiliation ref="#struct-6571"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Tania</forename>
                <surname>Cerquitelli</surname>
              </persName>
              <email type="md5">7c28da45352199fd1a9a7c8582b0702c</email>
              <email type="domain">polito.it</email>
              <idno type="idhal" notation="numeric">1131072</idno>
              <idno type="halauthorid" notation="string">1489380-1131072</idno>
              <affiliation ref="#struct-6571"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Elena</forename>
                <surname>Baralis</surname>
              </persName>
              <idno type="idhal" notation="numeric">1588935</idno>
              <idno type="halauthorid" notation="string">1049892-1588935</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-9231-467X</idno>
              <affiliation ref="#struct-6571"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Maria A.</forename>
                <surname>Zuluaga</surname>
              </persName>
              <email type="md5">d12961bfcaf8367ee8defbc79a2dd1c3</email>
              <email type="domain">eurecom.fr</email>
              <idno type="idhal" notation="string">maria-a-zuluaga</idno>
              <idno type="idhal" notation="numeric">748500</idno>
              <idno type="halauthorid" notation="string">54716-748500</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1147-766X</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=en&amp;user=0SaJdxQAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/171363035</idno>
              <affiliation ref="#struct-421532"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Centre De Documentation</forename>
                <surname>Eurecom</surname>
              </persName>
              <email type="md5">808fb6c747947adf4fb3953c09dd1636</email>
              <email type="domain">eurecom.fr</email>
            </editor>
            <funder ref="#projanr-98112"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-09-12 11:35:10</date>
              <date type="whenModified">2025-10-01 14:33:54</date>
              <date type="whenReleased">2025-09-25 07:40:34</date>
              <date type="whenProduced">2025-09-23</date>
              <date type="whenEndEmbargoed">2025-09-12</date>
              <ref type="file" target="https://hal.science/hal-05251649v1/document">
                <date notBefore="2025-09-12"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05251649v1/file/publi-8347.pdf" id="file-5251649-4512056">
                <date notBefore="2025-09-12"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="118606">
                <persName>
                  <forename>Centre De Documentation</forename>
                  <surname>Eurecom</surname>
                </persName>
                <email type="md5">808fb6c747947adf4fb3953c09dd1636</email>
                <email type="domain">eurecom.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05251649</idno>
            <idno type="halUri">https://hal.science/hal-05251649</idno>
            <idno type="halBibtex">poeta:hal-05251649</idno>
            <idno type="halRefHtml">&lt;i&gt;Deep-Breath 2025, 2nd Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care&lt;/i&gt;, Springer, Sep 2025, Daejeon, South Korea. pp.52-62, &lt;a target="_blank" href="https://dx.doi.org/10.1007/978-3-032-05559-0_6"&gt;&amp;#x27E8;10.1007/978-3-032-05559-0_6&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Deep-Breath 2025, 2nd Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care, Springer, Sep 2025, Daejeon, South Korea. pp.52-62, &amp;#x27E8;10.1007/978-3-032-05559-0_6&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5251649-4512056"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="EURECOM">EURECOM</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ANR-IA-22" corresp="ANR-IA">ANR-IA-22</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Divergence-Aware Training with Automatic Subgroup Mitigation for Breast Tumor Segmentation</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Eleonora</forename>
                    <surname>Poeta</surname>
                  </persName>
                  <email type="md5">76e2019ef5c6ee910a62e8cf187f3c89</email>
                  <email type="domain">polito.it</email>
                  <idno type="idhal" notation="numeric">1581676</idno>
                  <idno type="halauthorid" notation="string">2265927-1581676</idno>
                  <idno type="ORCID">https://orcid.org/0009-0001-7289-0036</idno>
                  <affiliation ref="#struct-6571"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Luisa</forename>
                    <surname>Vargas</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1588932</idno>
                  <idno type="halauthorid" notation="string">2745920-1588932</idno>
                  <idno type="ORCID">https://orcid.org/0009-0006-5741-8485</idno>
                  <affiliation ref="#struct-421532"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Daniele</forename>
                    <surname>Falcetta</surname>
                  </persName>
                  <email type="md5">dc9e42fe95dd7e3ace6ab39a0f4c5245</email>
                  <email type="domain">eurecom.fr</email>
                  <idno type="idhal" notation="numeric">1558978</idno>
                  <idno type="halauthorid" notation="string">2888841-1558978</idno>
                  <affiliation ref="#struct-421532"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Vincenzo</forename>
                    <surname>Marciano’</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1588933</idno>
                  <idno type="halauthorid" notation="string">3805498-1588933</idno>
                  <idno type="ORCID">https://orcid.org/0009-0000-2238-8040</idno>
                  <affiliation ref="#struct-421532"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Eliana</forename>
                    <surname>Pastor</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1588934</idno>
                  <idno type="halauthorid" notation="string">3766896-1588934</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3664-4137</idno>
                  <affiliation ref="#struct-6571"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Tania</forename>
                    <surname>Cerquitelli</surname>
                  </persName>
                  <email type="md5">7c28da45352199fd1a9a7c8582b0702c</email>
                  <email type="domain">polito.it</email>
                  <idno type="idhal" notation="numeric">1131072</idno>
                  <idno type="halauthorid" notation="string">1489380-1131072</idno>
                  <affiliation ref="#struct-6571"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Elena</forename>
                    <surname>Baralis</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">1588935</idno>
                  <idno type="halauthorid" notation="string">1049892-1588935</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-9231-467X</idno>
                  <affiliation ref="#struct-6571"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Maria A.</forename>
                    <surname>Zuluaga</surname>
                  </persName>
                  <email type="md5">d12961bfcaf8367ee8defbc79a2dd1c3</email>
                  <email type="domain">eurecom.fr</email>
                  <idno type="idhal" notation="string">maria-a-zuluaga</idno>
                  <idno type="idhal" notation="numeric">748500</idno>
                  <idno type="halauthorid" notation="string">54716-748500</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1147-766X</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?hl=en&amp;user=0SaJdxQAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/171363035</idno>
                  <affiliation ref="#struct-421532"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Deep-Breath 2025, 2nd Deep Breast Workshop on AI and Imaging for Diagnostic and Treatment Challenges in Breast Care</title>
                  <date type="start">2025-09-23</date>
                  <date type="end">2025-09-27</date>
                  <settlement>Daejeon</settlement>
                  <country key="KR">South Korea</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Springer</name>
                </respStmt>
                <imprint>
                  <publisher>Springer Nature Switzerland</publisher>
                  <pubPlace>Cham</pubPlace>
                  <biblScope unit="serie">Lecture Notes in Computer Science</biblScope>
                  <biblScope unit="volume">16142</biblScope>
                  <biblScope unit="pp">52-62</biblScope>
                  <date type="datePub">2026-09-21</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/978-3-032-05559-0_6</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Subgroup Analysis</term>
                <term xml:lang="en">Bias Mitigation</term>
                <term xml:lang="en">Breast Tumor Segmentation</term>
                <term xml:lang="en">Fairness</term>
              </keywords>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Deep learning models for breast tumor segmentation in DCE-MRI may exhibit disparities in performance across demographic and clinical subgroups, raising concerns about fairness and clinical trustworthiness. In this work, we propose a subgroup-aware in-processing mitigation strategy that integrates divergence-based regularization directly into the training loop. By leveraging interpretable metadata (e.g., age, menopausal status, breast density), we identify subgroups where the model underperforms and assign higher loss weights to these samples in proportion to their divergence from average performance. Our method enables the model to focus training on underrepresented or harder-to-segment subpopulations, without requiring external data or post-processing correction. We evaluate our approach on the MAMA-MIA 2025 challenge dataset, demonstrating improvements in both overall segmentation quality and fairness score. Our results highlight the potential of in-processing mitigation as an effective and practical pathway toward equitable medical image segmentation.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-6571" status="VALID">
          <idno type="IdRef">034390626</idno>
          <idno type="ISNI">0000000419370343</idno>
          <idno type="ROR">https://ror.org/00bgk9508</idno>
          <orgName>Politecnico di Torino = Polytechnic of Turin</orgName>
          <orgName type="acronym">Polito</orgName>
          <date type="start">1859-01-01</date>
          <desc>
            <address>
              <addrLine>Politecnico di Torino - Corso Duca degli Abruzzi, 24 10129 Torino</addrLine>
              <country key="IT"/>
            </address>
            <ref type="url">http://www.polito.it/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-421532" status="VALID">
          <orgName>Eurecom [Sophia Antipolis]</orgName>
          <desc>
            <address>
              <addrLine>Campus SophiaTech, 450 Route des Chappes, CS 50193 - 06904 Biot Sophia Antipolis cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.eurecom.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-98112" status="VALID">
          <idno type="anr">ANR-22-FAI1-0003</idno>
          <orgName>TRAIN</orgName>
          <desc>Intelligence Artificielle Fiable et Robuste</desc>
          <date type="start">2022</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>