mlsanityData to 14 Oct 2026

Enforcing connectivity of 3D linear structures using their 2D projections

arXiv 2207.06832 ↗First posted 14 Jul 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural networks trained by minimizing voxel-wise loss functions that do not capture the topological properties of these structures. As a result, the connectivity of the recovered structures is often wrong, which lessens their usefulness. In this paper, we propose to improve the 3D connectivity of our results by minimizing a sum of topology-aware losses on their 2D projections. This suffices to increase the accuracy and to reduce the annotation effort required to provide the required annotated training data. Code is available at https://github.com/doruk-oner/ConnectivityOnProjections.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 17 of its 34 references that are in the map. First posted on arXiv 14 Jul 2022.

Builds on

17 of 34 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2020clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentationcited by 294
  4. 2019Med3D: Transfer Learning for 3D Medical Image Analysiscited by 288
  5. 2019Topology-Preserving Deep Image Segmentationcited by 198
  6. 2018SpaceNet: A Remote Sensing Dataset and Challenge Seriescited by 179
  7. 2019A Topological Loss Function for Deep-Learning based Image Segmentation using Persistent Homologycited by 134
  8. 2017Beyond the Pixel-Wise Loss for Topology-Aware Delineationcited by 83
  9. 2021Topology-Aware Segmentation Using Discrete Morse Theorycited by 75
  10. 2016Deep Retinal Image Understandingcited by 35
  11. 2020Promoting Connectivity of Network-Like Structures by Enforcing Region Separationcited by 19
  12. 2018Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifiercited by 16
5 more
  1. 2014 N4 -Fields: Neural Network Nearest Neighbor Fields for Image Transformscited by 14
  2. 2020A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRIcited by 13
  3. 2019Joint Segmentation and Path Classification of Curvilinear Structurescited by 12
  4. 2018Tracing in 2D to Reduce the Annotation Effort for 3D Deep Delineationcited by 7
  5. 2019DeepCenterline: a Multi-task Fully Convolutional Network for Centerline Extractioncited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 20243D Vascular Segmentation Supervised by 2D Annotation of Maximum Intensity Projectioncited by 3
  2. 2025CAPE: Connectivity-Aware Path Enforcement Loss for Curvilinear Structure Delineationcited by 2
  3. 2023Morphology Edge Attention Network and Optimal Geometric Matching Connection model for vascular segmentationcited by 0