DGRTA: Cross-Modality Unsupervised Domain Adaptation for Intracranial Vessel Segmentation via Dual-Gated Refinement and Topology-Aware Weighting
- 9 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-11
Abstract
TOF-MRA intracranial vessel segmentation is critical in clinical practice but challenged by limited annotations and significant cross-modality domain shifts. To address these issues, this study proposes DGRTA, an unsupervised domain adaptation framework that integrates cross-modality pseudo-label generation, a dual-gated pseudo-label refinement strategy (DGR), and a topology aware weighting mechanism (TA). Initially, rigid and non-rigid registration are used to transfer CTA predictions to TOF-MRA to generate initial pseudo-labels. DGR then refines these labels using prediction probabilities and image intensity, enhancing sensitivity and specificity, while TA leverages Persistence Diagrams (PD) to quantify topological discrepancies and dynamically adjust loss weights. Experiments on 185 paired CTA/TOF-MRA cases demonstrated that DGRTA consistently improved performance across four backbone architectures (UNet, Attention UNet, UNETR, Swin UNETR). The Attention UNet DGRTA achieved the best results, with a Dice of 0.810, clDice of 0.800, and an AHD of 0.353 mm on the validation set, significantly outperforming the baseline model (p < 0.001). DGRTA offers a feasible solution that reduces reliance on extensive manual annotations, underscoring the potential of unsupervised cross-modality segmentation in various vascular imaging applications.Keywords
Funding Information
- China Postdoctoral Science Foundation (2024M751729)
- 75th General Program
- National Natural Science Foundation of China (82441022)
This publication has 44 references indexed in Scilit:
- Medical Image Segmentation Using Deep Learning: A Survey2023
- Integration- and separation-aware adversarial model for cerebrovascular segmentation from TOF-MRAComputer Methods and Programs in Biomedicine, 2023
- Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images2022
- Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling2021
- Cerebrovascular segmentation from TOF-MRA based on multiple-U-net with focal loss functionComputer Methods and Programs in Biomedicine, 2021
- JointVesselNet: Joint Volume-Projection Convolutional Embedding Networks for 3D Cerebrovascular Segmentation2020
- Blood vessel segmentation algorithms — Review of methods, datasets and evaluation metricsComputer Methods and Programs in Biomedicine, 2018
- Domain-Adversarial Training of Neural Networks2017
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015