Organizations: LaTIM UMR 1101, Inserm, Brest, France · University of Western Brittany, Brest, France · University Hospital of Brest, Brest, France · University Hospital of Poitiers, Poitiers, France · ICube UMR 7357, CNRS, Strasbourg, France · IMT Atlantique, Brest, France
Extracting hepatic vessels from abdominal images is of high interest for clinicians since it allows to divide the liver into functionally-independent Couinaud segments. In this respect, an automated liver blood vessel extraction is widely summoned. Despite the significant growth in performance of semantic segmentation methodologies, preserving the complex multi-scale geometry of main vessels and ramifications remains a major challenge. This paper provides a new deep supervised approach for vessel segmentation, with a strong focus on representations arising from the different scales inherent to the vascular tree geometry. In particular, we propose a new clustering technique to decompose the tree into various scale levels, from tiny to large vessels. Then, we extend standard 3D UNet to multi-task learning by incorporating scale-specific auxiliary tasks and contrastive learning to encourage the discrimination between scales in the shared representation. Promising results, depicted in several evaluation metrics, are revealed on the public 3D-IRCADb dataset.
Figures & tables
Figure 1: Proposed pipeline for deep liver vessel segmentation using scale-specific auxiliary multi-task contrastive learning.
Figure 2: ( a ) Visual aid to interpret notations related to multi-scale vessel clustering (Sect. 2.1 ). ( b ) Example of 3-scale vasculature clustering applied on a synthetic vasculature [ 8 ] .
Figure 3: Encoder-decoder architecture involved in our multi-task contrastive pipeline. PReLu stands for Parametric ReLU.
Models
DSC ↑ score ( % )
Jacc ↑ score ( % )
clDSC ↑ score ( % )
HD ↓ dist. ( mm )
3D ResUNet
binary
54.25±3.65
37.65±3.46
46.84±3.63
80.09±4.83
multi-class
50.31±4.43
34.13±3.98
44.34±2.89
114.3±10.9
Ours
λc=0
54.27±4.16
37.73±3.87
46.90±2.44
86.07±8.07
λc=0
55.04±2.79
38.50±2.71
48.13±3.52
82.36±12.3
Table 1: Liver vessel segmentation on CT scans from the 3D-IRCADb [ 16 ] dataset using 3D ResUNet in binary and multi-class settings as well as the proposed approach without and with contrastive learning. Best results are displayed in bold.
Figure 4: Letter-value plot of branch radii r^j(mm) per ground truth volume yi from the 3D-IRCADb [ 16 ] dataset.
Figure 5: Qualitative liver vessel segmentation results on CT scans from the 3D-IRCADb [ 16 ] dataset.
Accurate Couinaud liver segmentation is critical for preoperative surgical planning and tumor localization.However, existing methods primarily rely on image intensity and spatial location cues, without explicitly modeling vascular topology. As a result, they often produce indistinct boundaries near vessels and show limited generalization under anatomical variability.We propose VasGuideNet, the first Couinaud segmentation framework explicitly guided by vascular topology. Specifically, skeletonized vessels, Euclidean distance transform (EDT)--derived geometry, and k-nearest neighbor (kNN) connectivity are encoded into topology features using Graph Convolutional Networks (GCNs). These features are then injected into a 3D encoder--decoder backbone via a cross-attention fusion module. To further improve inter-class separability and anatomical consistency, we introduce a Structural Contrastive Loss (SCL) with a global memory bank.On Task08_HepaticVessel and our private LASSD dataset, VasGuideNet achieves Dice scores of 83.68% and 76.65% with RVDs of 1.68 and 7.08, respectively. It consistently outperforms representative baselines including UNETR, Swin UNETR, and G-UNETR++, delivering higher Dice/mIoU and lower RVD across datasets, demonstrating its effectiveness for anatomically consistent segmentation. Code is available at https://github.com/Qacket/VasGuideNet.git.
Chaojie Shen, Jingjun Gu, Zihao Zhao +4
Pujian Medical Technology Co., Ltd., Hangzhou, China · Keyi College of Zhejiang Sci-tech University, ShaoXing, China · College of Computer Science and Technology, Zhejiang University, Hangzhou, China
Accurate segmentation of hepatic and portal vessels in contrast-enhanced computed tomography angiography (CTA) remains challenging due to complex vascular topology, peripheral visibility limitations, and acquisition-induced ambiguities. While existing public datasets offer valuable benchmarks, few include clinically realistic annotation constraints. We introduce VEELA (Vessel Extraction and Extrication for Liver Analysis), a rigorously curated liver vessel dataset derived from 40 CTA scans inherited from the CHAOS grand-challenge cohort. All vessels were manually delineated slice-by-slice under multi-expert consensus, using a strict visibility-driven annotation policy and avoiding anatomically inferred interpolation. This design explicitly captures anatomical variability and imaging-related uncertainty. As a continuation of the CHAOS challenge, VEELA enables reproducible cross-benchmark evaluation while extending the scope to fine-grained hepatic and portal vessel segmentation. We further establish a standardized benchmarking framework and analyze complementary evaluation metrics, including topology-aware (clDice), overlap-based (IoU), boundary-sensitive (NSD), and geometry-aware (area, length) measures. Our results demonstrate that different metrics capture distinct aspects of vascular integrity, underscoring the necessity of multi-perspective evaluation for clinically meaningful vessel segmentation. VEELA is publicly released to facilitate reproducible research and support the development of robust vascular segmentation methods. Researchers can access the evaluation metrics, dataset, and submission platform at https://www.synapse.org/Synapse:syn65471967.
Ziya Ata Yazıcı, N. Sinem Gezer, İlkay Öksüz +19
Huawei Türkiye R&D Center, Istanbul, 34768, Türkiye · Department of Radiology, Dokuz Eylul University, Izmir, 35100, Türkiye · Department of Computer Engineering, Istanbul Technical University, Istanbul, 34469, Türkiye +8
Hepatic vessels in computed tomography scans often suffer from image fragmentation and noise interference, making it difficult to maintain vessel integrity and posing significant challenges for vessel segmentation. To address this issue, we propose an innovative model: SegKAN. First, we improve the conventional embedding module by adopting a novel convolutional network structure for image embedding, which smooths out image noise and prevents issues such as gradient explosion in subsequent stages. Next, we transform the spatial relationships between Patch blocks into temporal relationships to solve the problem of capturing positional relationships between Patch blocks in traditional Vision Transformer models. We conducted experiments on a Hepatic vessel dataset, and compared to the existing state-of-the-art model, the Dice score improved by 1.78%. These results demonstrate that the proposed new structure effectively enhances the segmentation performance of high-resolution extended objects. Code will be available at https://github.com/goblin327/SegKAN
Shengbo Tan, Rundong Xue, Shipeng Luo +7
College of Computer Science and Artificial Intelligence, Southwest Minzu University, Chengdu 610225, China · Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an 710049, China · College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China +4