# 3D Vessel Segmentation with Limited Guidance of 2D Structure-agnostic Vessel Annotations

arXiv: https://arxiv.org/abs/2302.03299 · HTML: https://mlsanity.com/paper/2302.03299/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 7 Feb 2023.

## Builds on (most cited first, 18 of 18)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation](https://mlsanity.com/paper/1907.07034/) (2019)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Unsupervised Embedding Learning via Invariant and Spreading Instance Feature](https://mlsanity.com/paper/1904.03436/) (2019)
- [SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth](https://mlsanity.com/paper/1810.06498/) (2018)
- [DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes](https://mlsanity.com/paper/1803.09340/) (2018)
- [Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2110.08762/) (2021)
- [Unsupervised Domain Adaptation with Variational Approximation for Cardiac Segmentation](https://mlsanity.com/paper/2106.08752/) (2021)
- [Human Treelike Tubular Structure Segmentation: A Comprehensive Review and Future Perspectives](https://mlsanity.com/paper/2207.11203/) (2022)
- [Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction](https://mlsanity.com/paper/2012.07262/) (2020)
- [Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineation](https://mlsanity.com/paper/1811.10508/) (2018)
- [Unsupervised Learning of Local Discriminative Representation for Medical Images](https://mlsanity.com/paper/2012.09333/) (2020)
- [Unsupervised Local Discrimination for Medical Images](https://mlsanity.com/paper/2108.09440/) (2021)

## Built on by (most cited first, 5 of 5)

- [3D Arterial Segmentation via Single 2D Projections and Depth Supervision in Contrast-Enhanced CT Images](https://mlsanity.com/paper/2309.08481/) (2023)
- [3D Vascular Segmentation Supervised by 2D Annotation of Maximum Intensity Projection](https://mlsanity.com/paper/2402.12128/) (2024)
- [Top-K Maximum Intensity Projection Priors for 3D Liver Vessel Segmentation](https://mlsanity.com/paper/2503.03367/) (2025)
- [Bridging 3D Deep Learning and Curation for Analysis and High-Quality Segmentation in Practice](https://mlsanity.com/paper/2511.22236/) (2025)
- [VEELA: A Clinically-Constrained Benchmark for Liver Vessel Segmentation in Computed Tomography Angiography](https://mlsanity.com/paper/2605.22357/) (2026)

## Abstract (arXiv)

Delineating 3D blood vessels is essential for clinical diagnosis and treatment, however, is challenging due to complex structure variations and varied imaging conditions. Supervised deep learning has demonstrated its superior capacity in automatic 3D vessel segmentation. However, the reliance on expensive 3D manual annotations and limited capacity for annotation reuse hinder the clinical applications of supervised models. To avoid the repetitive and laborious annotating and make full use of existing vascular annotations, this paper proposes a novel 3D shape-guided local discrimination model for 3D vascular segmentation under limited guidance from public 2D vessel annotations. The primary hypothesis is that 3D vessels are composed of semantically similar voxels and exhibit tree-shaped morphology. Accordingly, the 3D region discrimination loss is firstly proposed to learn the discriminative representation measuring voxel-wise similarities and cluster semantically consistent voxels to form the candidate 3D vascular segmentation in unlabeled images; secondly, based on the similarity of the tree-shaped morphology between 2D and 3D vessels, the Crop-and-Overlap strategy is presented to generate reference masks from 2D structure-agnostic vessel annotations, which are fit for varied vascular structures, and the adversarial loss is introduced to guide the tree-shaped morphology of 3D vessels; thirdly, the temporal consistency loss is proposed to foster the training stability and keep the model updated smoothly. To further enhance the model's robustness and reliability, the orientation-invariant CNN module and Reliability-Refinement algorithm are presented. Experimental results from the public 3D cerebrovascular and 3D arterial tree datasets demonstrate that our model achieves comparable effectiveness against nine supervised models.