Abstract

Pathology foundation models (FMs) are models trained on vast amounts of typically unlabeled data and have been shown to yield regularized latent spaces that can be used effectively in downstream classification tasks. This is also true for the classification of mitotic figures vs. other cells. However, it is so far unclear if the latent space of current FMs provides features that are discriminant and spatially suitably resolved to also serve as a backbone for dense object detection paradigms. In this work, we investigate this question for common current pathology FMs (UNI, UNI2-h, Virchow, Virchow2, H-optimus-0, H-optimus-1) and compare their performance against a fully end-to-end trained baseline based on a ResNet50 architecture. We combine FM backbones with representatives of single stage, dual stage and self-attention-based detectors (RetinaNet, Faster R-CNN, Deformable DETR respectively) on the multi-domain MIDOG++ dataset, and on the TUPAC16 dataset as an out-of-domain case. We show that the H-optimus-0 and Virchow models yielded competitive performance, indicating that the latent spaces of current FMs—all trained on image-level self-supervision—are suitable for direct mitotic figure detection and were more robust than the endto- end trained baseline on our out-of-domain test case. All code is made available publicly at https://github.com/DeepMicroscopy/FM4MFdet.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/COMPAYL_023.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to Open Review

Open Review Page: https://openreview.net/forum?id=Y4T1z6fO4w&referrer=%5BProgram%20Chair%20Console%5D(%2Fgroup%3Fid%3DMICCAI.org%2F2026%2FWorkshop%2FCOMPAYL%2FProgram_Chairs%23submission-status)

BibTex

@InProceedings{BanSwe_Beyond_MICCAISAT2026,
        author = { Banerjee, Sweta AND Teimoury, Alireza AND Porsche, Nils AND Stoll, Alexandra K. AND Weiss, Viktoria AND Hargarter, Niklas AND Ammeling, Jonas AND Conrad, Thomas AND Stroblberger, Christoph AND Kaltnecker, Christopher AND Klopfleisch, Robert AND Bertram, Christof A. AND Breininger, Katharina AND Aubreville, Marc},
        title = { { Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17251},
        month = {pending},
        page = {pending}
}


back to top