PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Dasdelen, M.F. ; Lim, H. ; Buck, M.* ; Götze, K.S.* ; Marr, C. ; Schneider, S.

CytoSAE: Interpretable Cell Embeddings for Hematology.

In: (28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025, 23-27 September 2025, Daejeon). Berlin [u.a.]: Springer, 2026. 77-86 (Lect. Notes Comput. Sc. ; 15973 LNCS)
DOI
Sparse autoencoders (SAEs) emerged as a promising tool for mechanistic interpretability of transformer-based foundation models. Recently, SAEs were also adopted for the visual domain, enabling the discovery of visual concepts and their patch-wise attribution to input images. While foundation models are increasingly applied to medical imaging, tools for interpreting their predictions remain limited. In this work, we propose CytoSAE, a sparse autoencoder trained on over 40,000 peripheral blood single-cell images. CytoSAE generalizes well to diverse and out-of-domain datasets, including bone marrow cytology. Here, it identifies morphologically relevant concepts which we validated with medical experts. Furthermore, we demonstrate scenarios in which CytoSAE can generate patient-specific and disease-specific concepts, enabling the detection of pathognomonic cells and localized cellular abnormalities at patch-level. We quantified the effect of concepts on a patient-level AML subtype classification task and show that CytoSAE concepts reach performance comparable to the state-of-the-art, while offering explainability on the sub-cellular level. Source code and model weights are available athttps://github.com/dynamical-inference/cytosae.
Altmetric
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Conference contribution
Keywords Disease Classification ; Explainability ; Sparse Autoencoders
Language english
Publication Year 2026
HGF-reported in Year 2026
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Conference Title 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
Conference Date 23-27 September 2025
Conference Location Daejeon
Journal Lecture Notes in Computer Science
Quellenangaben Volume: 15973 LNCS, Issue: , Pages: 77-86 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]
Institute(s) Institute of Computational Biology (ICB)
Institute of AI for Health (AIH)
POF-Topic(s) 30205 - Bioengineering and Digital Health
Research field(s) Enabling and Novel Technologies
PSP Element(s) G-503800-001
G-540007-001
DOI 10.1007/978-3-032-05185-1_8
Scopus ID 105018085373
Erfassungsdatum 2025-10-23
[➜Report correction]