List of Papers Browse by Subject Areas Author List
Abstract
Optical coherence Doppler tomography (ODT) is an emerging blood flow imaging technique. The fundamental unit of ODT is the 1D depth-resolved trace named raw A-scans (or A-line). A 2D ODT image (B-scan) is formed by reconstructing a cross-sectional flow image via Doppler phase-subtraction of raw A-scans along B-line. To obtain a high-fidelity B-scan, densely sampled A-scans are required currently, leading to prolonged scanning time and increased storage demands. Addressing this issue, we propose a novel sparse ODT reconstruction framework with an Alternative State Space Attention Network (ASSAN) that effectively reduces raw A-scans needed. Inspired by the distinct distributions of information along A-line and B-line, ASSAN applies 1D State Space Model (SSM) to each A-line to learn the intra-A-scan representation, while using 1D gated self-attention along B-line to capture the inter-A-scan features. In addition, an effective feedforward network based on sequential 1D convolutions along different axes is employed to enhance the local feature. In validation experiments on real animal data, ASSAN shows clear effectiveness in the reconstruction in comparison with state-of-the-art reconstruction methods.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2025/paper/0333_paper.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to the Code Repository
https://github.com/ZhenghLi/ASSAN
Link to the Dataset(s)
N/A
BibTex
@InProceedings{LiZhe_Sparse_MICCAI2025,
author = { Li, Zhenghong and Ren, Jiaxiang and Cheng, Wensheng and Liu, Yanzuo and Du, Congwu and Pan, Yingtian and Ling, Haibin},
title = { { Sparse Reconstruction of Optical Doppler Tomography with Alternative State Space Model and Attention } },
booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2025},
year = {2025},
publisher = {Springer Nature Switzerland},
volume = {LNCS 15975},
month = {September},
page = {529 -- 539}
}
Reviews
Review #1
- Please describe the contribution of the paper
This work proposes a novel Alternative State Space Attention Network (ASSAN) for Optical Coherence Doppler Tomography. The network is composed of three main components: 1) A-line State Space Block, 2) B-line Gated Attention Block, and 3) Local Enhancement Feedforward Network.
The authors provide a thorough analysis of the results and have tested all components of the proposed network. - 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 experiments are well designed, and the results are compelling. The ablation study is comprehensive, and the authors offer a solid analysis of each component. The paper is well written and easy to follow. Additionally, the problem is clearly formulated, making it accessible even to readers who may not be familiar with the specific domain.
- 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.
The main weakness is the lack of comparison with other state-of-the-art methods in terms of inference time and memory consumption — both of which are crucial metrics in the medical imaging field. Furthermore, evaluation under more challenging scenarios, such as with x8 or x16 sparsity factors, would significantly strengthen the paper.
- Please rate the clarity and organization of this paper
Satisfactory
- 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 submission does not mention open access to source code or data but provides a clear and detailed description of the algorithm to ensure reproducibility.
- 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?
The paper initially caught my attention, and I genuinely enjoyed reading it. However, the lack of comparison with other state-of-the-art methods in terms of inference time and memory usage was disappointing. These aspects are particularly important for the medical imaging community. I strongly recommend that the authors include such comparisons in the rebuttal. Additionally, evaluating the method under more challenging sparsity levels (e.g., x8 or x16) would further validate its robustness.
- Reviewer confidence
Very confident (4)
- [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
The authors propose a novel sparse ODT reconstruction framework with an Alternative State Space Attention Network (ASSAN) that effectively reduces raw A-scans needed.
- 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.
ASSAN applies 1D State Space Model (SSM) to each A-line to learn the intra-A-scan representation, while using 1D gated self-attention along B-line to capture the inter-A-scan features. In addition, an effective feedforward network based on sequential 1D convolutions along different axes is employed to enhance the local feature.
- 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.
Robustness: Have authors tried their method on other species instead of mouse and larger sparse sampling factors? Code: I did not see any open-source code that I can reproduce the results.
- 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 submission does not mention open access to source code or data but provides a clear and detailed description of the algorithm to ensure reproducibility.
- 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?
The authors proposed a novel method for ODT sparse reconstruction and the performance is better than other methods. But due to the concerns regarding robustness and open-source code, I gave this recoomenation.
- Reviewer confidence
Very confident (4)
- [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
The paper presents a novel method for sparse reconstruction of Optical Doppler Tomography (ODT) images, utilizing an Alternative State Space Attention Network (ASSAN). The proposed framework reduces the number of raw A-scans needed for image reconstruction, thus minimizing scanning time and storage requirements. By leveraging a combination of a state space model (SSM) for handling depth-correlated data and a self-attention mechanism for capturing inter-A-scan features, the method offers a significant improvement over traditional dense ODT imaging. The experimental results on real animal data demonstrate the effectiveness of ASSAN in generating high-fidelity images with reduced scan time and memory usage compared to state-of-the-art methods.
- 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.
This article is interesting, first suggesting the sparse reconstruction pipeline for ODT image generation. The solutions introduced are also innovative, effectively combining the advantages of CNN and SSM. The final experimental results also verify its reliability.
- 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.
- This article proposes a new task. I am not sure whether this improvement in efficiency is indeed a clinical problem.
- There does not seem to be a quantitative analysis of efficiency improvement in the article
- 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 submission does not provide sufficient information for reproducibility.
- 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?
Overall, the content of the article is complete, the proposed method is innovative, and the diagrams are clear. The experimental results are competitive.
- 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
Author Feedback
Reviewer #1: (1) Inference time and memory consumption: A: To infer a single 512x64 input patch under x2 sparsity on an RTX3090 GPU, ASSAN takes 99.0ms and 966MB GPU memory. In contrast, MambaIR takes 85.4ms and 988MB GPU memory. Therefore, our proposed ASSAN is competitive with MambaIR, and the small GPU memory usage makes it easy to be deployed. (2) More challenging scenarios with higher sparsities: A: Thanks for your suggestion. Since the higher sparsities are very challenging due to the bigger gaps between the raw A-scans, we will make this a future work.
Reviewer #2: (1) Robustness on other species and higher sparsities: A: Since collecting data from other animals requires other specific authorization and more expertise skills, we have not conducted such experiments. As for higher sparsities, due to the challenges introduced by the bigger gaps between sampled A-lines, more specific modeling may be needed. We will try to conduct related experiments in the future. (2) Release of code: A: Source code will be released soon.
Reviewer #4: (1) Efficiency in clinical: A: Faster scanning has various benefits. For example, it can help capture blood flow dynamics to various brain stimulation and facilitate related studies. (2) Efficiency improvement: A: The efficiency of the proposed ASSAN is competitive with MambaIR as mentioned in the response to Reviewer #1 (1).
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