Paper Info Reviews Author Feedback Meta-Review Back to top
List of Papers Browse by Subject Areas Author List

Abstract

Accurate segmentation of tubular structures, such as vascular networks, plays a critical role in various medical domains. A remaining significant challenge in this task is structural fragmentation, which can adversely impact downstream applications. Existing methods primarily focus on designing various loss functions to constrain global topological structures. However, they often overlook local discontinuity regions, leading to suboptimal segmentation results. To overcome this limitation, we propose a novel Global-to-Local Connectivity Preservation (GLCP) framework that can simultaneously perceive global and local structural characteristics of tubular networks. Specifically, we propose an Interactive Multi-head Segmentation (IMS) module to jointly learn global segmentation, skeleton maps, and local discontinuity maps, respectively. This enables our model to explicitly target local discontinuity regions while maintaining global topological integrity. In addition, we design a lightweight Dual-Attention-based Refinement (DAR) module to further improve segmentation quality by refining the resulting segmentation maps. Extensive experiments on both 2D and 3D datasets demonstrate that our GLCP achieves superior accuracy and continuity in tubular structure segmentation compared to several state-of-the-art approaches. The source codes will be available at https://github.com/FeixiangZhou/GLCP.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2025/paper/1868_paper.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to the Code Repository

https://github.com/FeixiangZhou/GLCP

Link to the Dataset(s)

N/A

BibTex

@InProceedings{ZhoFei_GLCP_MICCAI2025,
        author = { Zhou, Feixiang and Gao, Zhuangzhi and Zhao, He and Xie, Jianyang and Meng, Yanda and Zhao, Yitian and Lip, Gregory Y.H. and Zheng, Yalin},
        title = { { GLCP: Global-to-Local Connectivity Preservation for Tubular Structure Segmentation } },
        booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2025},
        year = {2025},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 15975},
        month = {September},
        page = {237 -- 247}
}

Reviews

Review #1

  • Please describe the contribution of the paper

    The authors present a module to improve vascular segmentation. This module is available in 2D and 3D and validated on public datasets.

  • Please list the major strengths of the paper: you should highlight a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.
    • the metrics used in the validation part are adapted and various
    • the method can be adapted on different frameworks
  • Please list the major weaknesses of the paper. Please provide details: for instance, if you state that a formulation, way of using data, demonstration of clinical feasibility, or application is not novel, then you must provide specific references to prior work.
    • there is no statistical analysis
    • the top-methods of the challenges of the databases are not used in the comparison part
    • the choice of the methods used in the validation part is not justified.
  • Please rate the clarity and organization of this paper

    Good

  • Please comment on the reproducibility of the paper. Please be aware that providing code and data is a plus, but not a requirement for acceptance.

    The authors claimed to release the source code and/or dataset upon acceptance of the submission.

  • Optional: If you have any additional comments to share with the authors, please provide them here. Please also refer to our Reviewer’s guide on what makes a good review and pay specific attention to the different assessment criteria for the different paper categories: https://conferences.miccai.org/2025/en/REVIEWER-GUIDELINES.html

    N/A

  • Rate the paper on a scale of 1-6, 6 being the strongest (6-4: accept; 3-1: reject). Please use the entire range of the distribution. Spreading the score helps create a distribution for decision-making.

    (4) Weak Accept — could be accepted, dependent on rebuttal

  • Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

    This article suffers from a lack of précision in the validation part, even if the authors use a lot of metrics that are adapted to vessel segmentation evaluation.

  • Reviewer confidence

    Confident but not absolutely certain (3)

  • [Post rebuttal] After reading the authors’ rebuttal, please state your final opinion of the paper.

    N/A

  • [Post rebuttal] Please justify your final decision from above.

    N/A



Review #2

  • Please describe the contribution of the paper

    This work focuses on tubular structure segmentation. The authors propose to train a model on multiple tasks to preserve the connectivity of these structures during segmentation. In their method, a multi-head segmentation module is designed to simultaneously produce segmentation, skeleton, and discontinuity maps. The outputs of the skeleton and discontinuity maps are then used as attention maps to further refine the initial segmentation. The model is trained end-to-end, and a specific method based on the analysis of endpoints is developed to generate ground-truth discontinuity maps. The paper presents multiple contributions, including the concept and design of the multi-head architecture, the refinement module, the design of a multi-component loss function, and the method for creating ground-truth discontinuity maps.

  • Please list the major strengths of the paper: you should highlight a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.

    1. The proposed approach is novel. Most recent work has focused on designing new loss functions rather than on model architecture or training techniques.

    2. The authors conducted an extensive validation of their method, incorporating both 2D and 3D data and addressing both binary and multiclass problems. It also includes comparisons to a variety of state-of-the-art methods, including several very recent ones.

    3. The validation results show a systematic improvement of the performance (Tables 1 and 2), demonstrating the effectiveness of the proposed method. The validation is supplemented by an ablation study showing the individual contribution of each component of the model.

  • Please list the major weaknesses of the paper. Please provide details: for instance, if you state that a formulation, way of using data, demonstration of clinical feasibility, or application is not novel, then you must provide specific references to prior work.

    All the figures are too small to see, especially Fig. 1 and 3, please make them bigger.

  • Please rate the clarity and organization of this paper

    Good

  • Please comment on the reproducibility of the paper. Please be aware that providing code and data is a plus, but not a requirement for acceptance.

    The authors claimed to release the source code and/or dataset upon acceptance of the submission.

  • Optional: If you have any additional comments to share with the authors, please provide them here. Please also refer to our Reviewer’s guide on what makes a good review and pay specific attention to the different assessment criteria for the different paper categories: https://conferences.miccai.org/2025/en/REVIEWER-GUIDELINES.html

    N/A

  • Rate the paper on a scale of 1-6, 6 being the strongest (6-4: accept; 3-1: reject). Please use the entire range of the distribution. Spreading the score helps create a distribution for decision-making.

    (5) Accept — should be accepted, independent of rebuttal

  • Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

    The paper introduces several original contributions leading to an improvement of the segmentation performance over other state-of-the-art methods.

  • Reviewer confidence

    Confident but not absolutely certain (3)

  • [Post rebuttal] After reading the authors’ rebuttal, please state your final opinion of the paper.

    N/A

  • [Post rebuttal] Please justify your final decision from above.

    N/A



Review #3

  • Please describe the contribution of the paper

    This paper introduces a framework for tubular structure segmentation, specifically to improve both the global and local connectivity of the segmentation. The authors propose an interactive multi-head segmentation to jointly predict the global segmentation, the skeleton map and a local discontinuity map of the segmentation. Then a dual-attention refinement helps to integrate both the global and local attention mechanisms based on the skeleton and discontinuity maps.

  • Please list the major strengths of the paper: you should highlight a novel formulation, an original way to use data, demonstration of clinical feasibility, a novel application, a particularly strong evaluation, or anything else that is a strong aspect of this work. Please provide details, for instance, if a method is novel, explain what aspect is novel and why this is interesting.
    • The paper adresses a critical challenge for the segmentation of tubular structure, specifically its connectivity.
    • The method is clear to follow and lightweight as it seems to add minimal computational overhead to an existing segmentation backbone.
    • Relevant topological metrics are used to demonstrate the improvement of the results using the proposed method.
    • The results demonstrate on three different datasets that the proposed method outperforms the state-of-the-art, comparing with many other methods and baseline.
    • A solid ablation study is performed to highlight the contribution of each component of the method.
    • The method is well-generalizable at it can be plugged into different segmentation architectures.
  • Please list the major weaknesses of the paper. Please provide details: for instance, if you state that a formulation, way of using data, demonstration of clinical feasibility, or application is not novel, then you must provide specific references to prior work.

    I only have minor concerns reguarding this paper. An analysis on the computational cost would have been valuable to demonstrate its applicability and a few mispelling and ambiguous figure titles could be fixed to improve clarity. One last point that is unclear is that the discontinuity prediction head is trained on masks derived from skeletonized predictions and ground truth, but this assumes you already know where your method is failing, if the model is trained to fix its own previous predictions?

  • Please rate the clarity and organization of this paper

    Good

  • Please comment on the reproducibility of the paper. Please be aware that providing code and data is a plus, but not a requirement for acceptance.

    The authors claimed to release the source code and/or dataset upon acceptance of the submission.

  • Optional: If you have any additional comments to share with the authors, please provide them here. Please also refer to our Reviewer’s guide on what makes a good review and pay specific attention to the different assessment criteria for the different paper categories: https://conferences.miccai.org/2025/en/REVIEWER-GUIDELINES.html

    The sentence in the introduction “we proposed Interactive Multi-head Segmentation (IMS) jointly learns..” there seems to be a grammatical issue that could be fixed.

  • Rate the paper on a scale of 1-6, 6 being the strongest (6-4: accept; 3-1: reject). Please use the entire range of the distribution. Spreading the score helps create a distribution for decision-making.

    (5) Accept — should be accepted, independent of rebuttal

  • Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

    This paper presents a thoughtful and practical contribution to improve the connectivity of the segmentation of tubular structures. The experiments are well conducted, comparing with many state-of-the-art methods across 3 datasets both in 2D and 3D settings, along with an ablation study. The results demonstrate the efficiency of the method to improve specifically topological results of the segmentation.

  • Reviewer confidence

    Somewhat confident (2)

  • [Post rebuttal] After reading the authors’ rebuttal, please state your final opinion of the paper.

    N/A

  • [Post rebuttal] Please justify your final decision from above.

    N/A



Author Feedback

We sincerely thank the AC and reviewers for their efforts and will make further improvements in the revised version.



Meta-Review

Meta-review #1

  • Your recommendation

    Provisional Accept

  • If your recommendation is “Provisional Reject”, then summarize the factors that went into this decision. In case you deviate from the reviewers’ recommendations, explain in detail the reasons why. You do not need to provide a justification for a recommendation of “Provisional Accept” or “Invite for Rebuttal”.

    N/A



back to top