Abstract
Domainshiftacrossimagingmodalitiesandacquisitionsites remains a significant barrier to the clinical deployment of segmentation models.Source-freeunsuperviseddomainadaptation(SFUDA)addresses this by adapting a pretrained model to an unlabeled target domain without requiring access to sensitive source data. We introduce a novel SFUDA framework built on Symmetrical Flow Matching, a unified generative model that segments an input image and synthesizes a sourcelike image from a mask within the same learned flow. By initializing inference from a domain-agnostic Gaussian origin, the model preserves structuralconsistencyacrossdomainsandgroundspredictionsinlearned anatomyratherthanshiftedtexturestatistics.Ourpipelineleveragesthis symmetry to generate reliable pseudo-labels and corresponding sourcelike synthetic images from unlabeled target data, creating a generative replay buffer that anchors source knowledge during a generative selftraining stage that fine-tunes on a joint set of real target and synthetic source-like images. We evaluate on abdominal multi-organ and cardiac segmentation, covering cross-modality MRI↔CT shifts, and multi-site prostatesegmentation.OurapproachoutperformsSFUDAbaselinesand iscompetitivewithconventionalUDAmethods.Thecodeisavailableat github.com/tal-grossman/SymmAdapt.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SASHIMI_013.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=wQqbu6YiyH
BibTex
@InProceedings{GroTal_SymmAdapt_MICCAISAT2026,
author = { Grossman, Tal AND Cahan, Noa AND Greenspan, Hayit},
title = { { SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image Segmentation } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17258},
month = {pending},
page = {pending}
}
