Unsupervised Domain Adaptation with Target-Only Margin Disparity Discrepancy
This addresses the scarcity of annotated CBCT data for interventional radiology, enabling improved liver segmentation to assist practitioners during minimally invasive procedures, though it is incremental as it builds on existing MDD methods.
The paper tackles the problem of liver segmentation in Cone-Beam Computed Tomography (CBCT) by using unsupervised domain adaptation to bridge the modality gap with annotated CT data, achieving state-of-the-art performance in both UDA and few-shot settings.
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.