Back to all papers

Deep generative models for vessel segmentation in CT angiography of the brain.

January 5, 2026pubmed logopapers

Authors

van Voorst H,Su J,Konduri PR,Majoie CBLM,Roos YBWEM,Emmer BJ,Marquering HA,de Vos BD,Caan MWA,Išgum I

Affiliations (7)

  • Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, the Netherlands; Department of Biomedical Engineering and Physics, Amsterdam UMC, Amsterdam, the Netherlands. Electronic address: [email protected].
  • Department of Radiology, Erasmus MC, Rotterdam, the Netherlands.
  • Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, the Netherlands; Department of Biomedical Engineering and Physics, Amsterdam UMC, Amsterdam, the Netherlands.
  • Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, the Netherlands.
  • Department of Neurology, Amsterdam UMC, Amsterdam, the Netherlands.
  • Department of Biomedical Engineering and Physics, Amsterdam UMC, Amsterdam, the Netherlands.
  • Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, the Netherlands; Department of Biomedical Engineering and Physics, Amsterdam UMC, Amsterdam, the Netherlands; Informatics Institute, Faculty of Science, University of Amsterdam, Amsterdam, the Netherlands.

Abstract

Automated vessel segmentation in brain CT angiography (CTA) remains challenging despite the potential benefits of its applications. Expert acquisition of reference vessel segmentations is a laborious task. We propose an unsupervised generative deep learning approach that can be trained for vessel segmentation in brain CTA using a large dataset (n=908) of unlabelled brain CTAs and non-contrast enhanced CTs (NCCTs). Our semi-supervised approach uses a conditional generative adversarial network (GAN) for CTA to NCCT translation by generating a contrast map that allows for automatic extraction of vessel segmentations. Furthermore, we propose a 3D Frangi filter-based loss function to enhance tubular structures in the contrast map to improve vessel segmentations. We used a hold-out test set of 9 CTA volumes with manually annotated reference segmentations. We compared our semi-supervised approach with a state-of-the-art supervised nnUnet, trained and evaluated with test set using 9-fold nested cross-validation. Evaluation metrics included voxel-wise Dice similarity coefficient (DSC), true positive rate (TPR), and false positive rate (FPR). The DSC was 4 % lower for the semi-supervised approach (DSC: 0.74) compared to the supervised nnUnet (DSC: 0.78). Both the TPR and FPR were higher for the semi-supervised approach (TPR: 0.75, FPR/1000 voxels:2.05) compared to the supervised nnUnet (TPR:0.71, FPR/1000 voxels:0.87). Hence, the quantitative results showed that our semi-supervised method approaches a supervised state-of-the-art segmentation network. The results demonstrate that a semi-supervised generative deep learning approach for the segmentation of intracranial vessels is feasible without laborious manual segmentations.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 8,000+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.