PuSH - Publikationsserver des Helmholtz Zentrums München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Zedda, L.* ; Loddo, A.* ; Di Ruberto, C.* ; Marr, C.

RedDino: A Foundation Model for Red Blood Cell Analysis.

In: (28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025, 23-27 September 2025, Daejeon). Berlin [u.a.]: Springer, 2026. 445-455 (Lect. Notes Comput. Sc. ; 15963 LNCS)
DOI
Red blood cells (RBCs) are fundamental to human health, and precise morphological analysis is critical for diagnosing hematological disorders. Despite the potential of foundation models for medical diagnostics, comprehensive AI solutions for RBC analysis remain limited. We introduce RedDino, a self-supervised foundation model specifically designed for RBC image analysis. Leveraging a RBC-tailored version of the DINOv2 self-supervised learning framework, RedDino is trained on an extensive, meticulously curated dataset comprising over 1.25 million RBC images from diverse acquisition modalities and sources. Comprehensive evaluations demonstrate that RedDino significantly outperforms existing state-of-the-art models in the RBC shape classification. Through systematic assessments, including linear probing and nearest neighbor classification, we validate the model’s robust feature representation and strong generalization capabilities. Our key contributions are (1) a dedicated foundation model tailored for RBC analysis, (2) detailed ablation studies exploring DINOv2 configurations for RBC modeling, and (3) comprehensive generalization performance evaluation. RedDino captures nuanced morphological characteristics and represents a substantial advancement in developing reliable diagnostic tools. Source code and pretrained models for RedDino are available at https://github.com/Snarci/RedDino.
Altmetric
Tags
Anmerkungen
Besondere Publikation
Auf Hompepage verbergern

Zusatzinfos bearbeiten
Eigene Tags bearbeiten
Privat
Eigene Anmerkung bearbeiten
Privat
Auf Publikationslisten für
Homepage nicht anzeigen
Als besondere Publikation
markieren
Publikationstyp Artikel: Konferenzbeitrag
Schlagwörter Dinov2 ; Foundation Models ; Hematology ; Medical Imaging ; Red Blood Cell Analysis ; Self-supervised Learning
Sprache englisch
Veröffentlichungsjahr 2026
HGF-Berichtsjahr 2026
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Konferenztitel 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Konferzenzdatum 23-27 September 2025
Konferenzort Daejeon
Zeitschrift Lecture Notes in Computer Science
Quellenangaben Band: 15963 LNCS, Heft: , Seiten: 445-455 Artikelnummer: , Supplement: ,
Verlag Springer
Verlagsort Berlin [u.a.]
Institut(e) Institute of AI for Health (AIH)
POF Topic(s) 30205 - Bioengineering and Digital Health
Forschungsfeld(er) Enabling and Novel Technologies
PSP-Element(e) G-540007-001
DOI 10.1007/978-3-032-04965-0_42
Scopus ID 105017852001
Erfassungsdatum 2025-10-23
[➜Korrektur melden]