Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 27, 2026Physics in Medicine and BiologyOpen Access

Topology-Aware Segmentation for Tubular Structure in 3D Microscopy

View Full Paper
Ask AI
Bookmark
Share

Authors

YSYiwen SunRZRanran ZhangFCFuqiang Chen

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved tubular structure segmentation in microscopy, indicating enhanced accuracy and connectivity.

Key Points

  • This work aims to improve the segmentation of tubular structures in 3D microscopy using a topology-supervised framework.
  • Proposed a fully 3D topology-supervised segmentation framework for tubular structures.
  • Introduced radius-aware topology integrating local radius estimates into connectivity constraints.
  • Validated the approach on three modalities: electron microscopy, optical microscopy, and fluorescent neuronal fibers.
  • Achieved highest Dice/clDice scores on SELMA3D (0.8839/0.9173), Mini-vessel (0.8842/0.9097), and FISBe (0.7803/0.8033).
  • Outperformed competing baselines consistently across all datasets.
  • Preserved global 3D connectivity while avoiding implausible radius jumps.

Cite This Study

Sun et al. (2026) studied this question.

synapsesocial.com/papers/6a3f6772aea7db3c1953ef85https://doi.org/10.1088/1361-6560/ae8216
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Skeleton-guided 3D convolutional neural network for tubular structure segmentation2024 · 7 citations
  2. 2Deep Closing: Enhancing Topological Connectivity in Medical Tubular Segmentation2024 · 17 citations
  3. 3Deep Learning for 3D Vascular Segmentation in Phase Contrast Tomography2024 · 1 citations
  4. 4tUbe net: a generalisable deep learning tool for 3D vessel segmentation2025
  5. 5TopoTome: Topology-informed unsupervised segmentation and analysis of 3D images2025