Adaptive deep learning model with anatomical priors for 3D segmentation of fine hepatic vasculature on CT
Radiology Advances · 04.11.2026 · 3 (6)
DOI: 10.1093/radadv/umag038 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology Advances, online erschienen am 03.11.2026. Verfasst von Zixuan Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: Physics and Biology in Medicine Graduate Program, David Geffen School of Medicine at UCLA, Los Angeles, CA 90065, United States. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
Accurate segmentation of fine hepatic vessels on CT remains challenging because peripheral branches are small and low contrast.
Purpose
To develop and test PriM Fusion Net, a deep learning model that adaptively integrates an optimized anatomical prior to improve 3D CT segmentation of portal and hepatic veins, emphasizing fine peripheral branches for preoperative 3D modeling. Materials and methods This retrospective study used the public Medical Segmentation Decathlon (MSD) Task08-HepaticVessel dataset of 303 abdominal CT volumes. PriM Fusion Net uses a dual-encoder architecture: a Swin Transformer processes CT images and a parallel convolutional pathway processes a dataset-optimized Frangi vesselness prior. Gated multimodal units act as spatially varying voxel-wise gates that fuse the 2 feature streams at multiple scales. A rule-based SimpleMind post-processing module refined anatomical plausibility. Performance was evaluated with 5-fold cross-validation and zero-shot external inference on 3DIRCADb (3D Image Reconstruction for Comparison of Algorithm Database).
Results
PriM Fusion Net achieved a mean Dice similarity coefficient (DSC) of 77.68% (95% confidence interval [CI]: 77.11, 78.25) and 95th percentile Hausdorff distance (HD95) of 11.55 mm (95% CI, 9.94, 13.16), outperforming all baselines (all adjusted P < .02). For vessels with radius ≤ 1.5 mm, DSC improved by 13.5% versus SwinUNETR (59.2% [95% CI, 54.48, 63.92] vs 45.7% [95% CI, 40.49, 50.91]). In ablation, replacing rigid concatenation with gated fusion improved DSC from 75.86% (95% CI, 75.31, 76.41) to 77.65% (95% CI, 76.92, 78.38), and SimpleMind post-processing reduced HD95 from 14.98 mm (95% CI, 10.91, 19.05) to 11.55 mm (95% CI, 9.94, 13.16). On 3DIRCADb, zero-shot inference yielded DSC of 68.42% (95% CI, 65.82, 71.02) and HD95 of 11.78 mm (95% CI, 8.50, 15.06).
Conclusion
Adaptive deep fusion of an optimized anatomical prior improved CT segmentation of portal and hepatic veins, especially fine peripheral branches, supporting further evaluation in 3D vascular modeling workflows for liver surgery and intervention.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Physics and Biology in Medicine Graduate Program, David Geffen School of Medicine at UCLA, Los Angeles, CA 90065, United States.
- Center for Computer Vision and Imaging Biomarkers, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA 90025, United States.
ORCID-Profile: Zixuan Zhao, Kyunghyun Sung, David S Lu, Grace H Kim, Matthew S Brown
Zitieren
APA
Zhao, Z., Vyapari, K., Sung, K., Lu, D. S., Kim, G. H., & Brown, M. S. (2026). Adaptive deep learning model with anatomical priors for 3D segmentation of fine hepatic vasculature on CT. Radiology Advances, 3(6). https://doi.org/10.1093/radadv/umag038
Vancouver
Zhao Z, Vyapari K, Sung K, Lu DS, Kim GH, Brown MS. Adaptive deep learning model with anatomical priors for 3D segmentation of fine hepatic vasculature on CT. Radiology Advances. 2026;3(6). doi:10.1093/radadv/umag038
BibTeX
@article{Zhao2026,
author = {Zhao, Zixuan and Vyapari, Kalyani and Sung, Kyunghyun and Lu, David S and Kim, Grace H and Brown, Matthew S},
title = {Adaptive deep learning model with anatomical priors for 3D segmentation of fine hepatic vasculature on CT},
journal = {Radiology Advances},
year = {2026},
volume = {3},
number = {6},
doi = {10.1093/radadv/umag038}
}
EUVIMED