Saved in:
Bibliographic Details
Main Authors: Miralles, Gauthier, Folgoc, Loïc Le, Jugnon, Vincent, Gori, Pietro
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09932
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912959509299200
author Miralles, Gauthier
Folgoc, Loïc Le
Jugnon, Vincent
Gori, Pietro
author_facet Miralles, Gauthier
Folgoc, Loïc Le
Jugnon, Vincent
Gori, Pietro
contents In interventional radiology, Cone-Beam Computed Tomography (CBCT) is a helpful imaging modality that provides guidance to practicians during minimally invasive procedures. CBCT differs from traditional Computed Tomography (CT) due to its limited reconstructed field of view, specific artefacts, and the intra-arterial administration of contrast medium. While CT benefits from abundant publicly available annotated datasets, interventional CBCT data remain scarce and largely unannotated, with existing datasets focused primarily on radiotherapy applications. To address this limitation, we leverage a proprietary collection of unannotated interventional CBCT scans in conjunction with annotated CT data, employing domain adaptation techniques to bridge the modality gap and enhance liver segmentation performance on CBCT. We propose a novel unsupervised domain adaptation (UDA) framework based on the formalism of Margin Disparity Discrepancy (MDD), which improves target domain performance through a reformulation of the original MDD optimization framework. Experimental results on CT and CBCT datasets for liver segmentation demonstrate that our method achieves state-of-the-art performance in UDA, as well as in the few-shot setting.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09932
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Unsupervised Domain Adaptation with Target-Only Margin Disparity Discrepancy
Miralles, Gauthier
Folgoc, Loïc Le
Jugnon, Vincent
Gori, Pietro
Computer Vision and Pattern Recognition
In interventional radiology, Cone-Beam Computed Tomography (CBCT) is a helpful imaging modality that provides guidance to practicians during minimally invasive procedures. CBCT differs from traditional Computed Tomography (CT) due to its limited reconstructed field of view, specific artefacts, and the intra-arterial administration of contrast medium. While CT benefits from abundant publicly available annotated datasets, interventional CBCT data remain scarce and largely unannotated, with existing datasets focused primarily on radiotherapy applications. To address this limitation, we leverage a proprietary collection of unannotated interventional CBCT scans in conjunction with annotated CT data, employing domain adaptation techniques to bridge the modality gap and enhance liver segmentation performance on CBCT. We propose a novel unsupervised domain adaptation (UDA) framework based on the formalism of Margin Disparity Discrepancy (MDD), which improves target domain performance through a reformulation of the original MDD optimization framework. Experimental results on CT and CBCT datasets for liver segmentation demonstrate that our method achieves state-of-the-art performance in UDA, as well as in the few-shot setting.
title Unsupervised Domain Adaptation with Target-Only Margin Disparity Discrepancy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.09932