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

Abstract

Accurate biventricular segmentation of cardiac magnetic resonance (CMR) cine images is essential for the clinical evaluation of heart function. Deep-learning-based methods have achieved highly accurate segmentation performance, however, compared to left ventricle (LV), right ventricle (RV) segmentation is still more challenging and less reproducible. The degenerated performance frequently occurs at the RV base, where the in-plane anatomical structures are complex (with atria, valve, and aorta), and varying due to the strong inter-planar motion. In this work, we propose to tackle the currently unsolved issues in CMR segmentation, specifically at the RV base, with two strategies: first, we complemented the public resource by re-annotating the RV base in the ACDC dataset, with refined delineation of the right ventricle outflow tract (RVOT), under the guidance of an expert cardiologist. Second, we proposed a novel Dual-Encoder U-Net architecture that leverages temporal incoherence to inform the segmentation when inter-planar motions occur. The inter-planar motion is characterized by loss-of-tracking, via Bayesian uncertainty of a motion-tracking model. Our experiments showed that our method significantly improved the RV base segmentation by taking temporal incoherence into account. Additionally, we investigated the reproducibility of deep-learning-based segmentation and showed that the combination of consistent annotation and loss-of-tracking could enhance RV segmentation reproducibility, potentially facilitating a large number of clinical studies focusing on RV.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2024/paper/2877_paper.pdf

SharedIt Link: https://rdcu.be/dV51r

SpringerLink (DOI): https://doi.org/10.1007/978-3-031-72114-4_40

Supplementary Material: N/A

Link to the Code Repository

N/A

Link to the Dataset(s)

N/A

BibTex

@InProceedings{Zha_Lost_MICCAI2024,
        author = { Zhao, Yidong and Zhang, Yi and Simonetti, Orlando and Han, Yuchi and Tao, Qian},
        title = { { Lost in Tracking: Uncertainty-guided Cardiac Cine MRI Segmentation at Right Ventricle Base } },
        booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024},
        year = {2024},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 15009},
        month = {October},
        page = {415 -- 424}
}

Reviews

Review #1

  • Please describe the contribution of the paper

    This study utilizes the Bayesian uncertainty of motion tracking models to describe the tracking loss due to inter-plane motion, and it involves the re-annotation of ACDC to achieve more refined segmentation of the RV.

  • Please list the main strengths of the paper; you should write about 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.This study re-annotated the RV base within the ACDC dataset, potentially enabling more accurate clinical assessments of cardiac function. 2.By utilizing temporal incoherence (loss-of-tracking) to detect inter-plane motion, the accuracy of RV segmentation is enhanced. 3.The reproducibility of RV segmentation was assessed using both standard ACDC and the additional ACDC annotations to demonstrate the effectiveness of the proposed method.

  • Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.
    1. The comparative experiments appear insufficiently convincing; in addition to the baseline, comparisons with other widely-used cardiac segmentation models in the medical field should be included.
    2. The improvement attributed to the proposed “Lost in Tracking” methodology does not seem substantial, with the segmentation results’ enhancement mainly due to the new annotations.
  • 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.

  • Do you have any additional comments regarding the paper’s reproducibility?

    N/A

  • Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review. Pay specific attention to the different assessment criteria for the different paper categories (MIC, CAI, Clinical Translation of Methodology, Health Equity): https://conferences.miccai.org/2024/en/REVIEWER-GUIDELINES.html
    1. Please clarify the impacts of (u_s) and (u_b) on the segmentation results, respectively, and discuss why both are necessary.
    2. There are inaccuracies in the citation of ST-GRU; these should be corrected.
    3. The Segmentation Reproducibility experiment was conducted solely on the ACDC dataset, which may not suffice to validate the effectiveness of the proposed method comprehensively. Additional experiments for further validation are recommended.
  • 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

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

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

    The approach of improving right ventricle segmentation through motion tracking is commendable. However, the effectiveness of the proposed method is difficult to ascertain due to the limited scope of comparative experiments.

  • Reviewer confidence

    Confident but not absolutely certain (3)

  • [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed

    N/A

  • [Post rebuttal] Please justify your decision

    N/A



Review #2

  • Please describe the contribution of the paper

    In cardiac MRI segmentation the right ventricle (RV) delineation is more challenging and less reproducible. The degenerated performance frequently occurs at the RV base. To tackle this problem two strategies are proposed. First, the right ventricle outflow tract (RVOT) is also annotated. Second, a novel Dual-Encoder U-Net architecture is proposed in order to leverage the temporal incoherence to inform the segmentation when the tracking is lost, via Bayesian uncertainty of a motion-tracking model. The RV base segmentation is improved and the reproducibility is enhanced.

  • Please list the main strengths of the paper; you should write about 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.

    Hereafter the main original contributions of the paper:

    • The spatio-tempolar approach for removing uncertainty in RV segmentation
    • The use of a Bayesian motion tracking framework to estimate loss-of-tracking, which can identify the inter-planer cardiac motion in an unsupervised manner
    • The integration of the tracking uncertainty module into a Dual-Encoder UNet architecture to enhance the segmentation performance at RV base
  • Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.

    Νo noteworthy observation

  • Please rate the clarity and organization of this paper

    Excellent

  • 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.

  • Do you have any additional comments regarding the paper’s reproducibility?

    N/A

  • Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review. Pay specific attention to the different assessment criteria for the different paper categories (MIC, CAI, Clinical Translation of Methodology, Health Equity): https://conferences.miccai.org/2024/en/REVIEWER-GUIDELINES.html

    No comment, as the work is an essential contribution in the field of cardiac MRI segmentation and very well presented.

  • 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

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

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

    The original contributions of the work (see above) and the experimental results on a known dataset lead to the acceptance of this paper.

  • Reviewer confidence

    Confident but not absolutely certain (3)

  • [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed

    N/A

  • [Post rebuttal] Please justify your decision

    N/A



Review #3

  • Please describe the contribution of the paper

    The proposed method addresses the challenges of accurate right ventricle (RV) segmentation by refining annotations in the ACDC dataset and introducing a Dual-Encoder U-Net that integrates loss-of-tracking uncertainty estimation, specifically targeting the inter-planar motion issues commonly observed in cardiac MRIs.

  • Please list the main strengths of the paper; you should write about 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.

    Accurate right ventricle (RV) segmentation faces challenges due to inter-planar motion, limited training data, and a lack of proven methods. However, this paper proposes a promising solution. It explores the less studied hypothesis that poor segmentation consistency can degrade network performance at the RV base. The proposed method is clearly defined and introduces the novel concept of tracking uncertainty. It demonstrates significant improvement with the use of uncertainty estimation.

  • Please list the main weaknesses of the paper. Please provide details, for instance, if you think a method is not novel, explain why and provide a reference to prior work.

    Details on the network structure and parameters are missing, which are necessary for easy reproduction.

  • Please rate the clarity and organization of this paper

    Excellent

  • 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.

  • Do you have any additional comments regarding the paper’s reproducibility?

    N/A

  • Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review. Pay specific attention to the different assessment criteria for the different paper categories (MIC, CAI, Clinical Translation of Methodology, Health Equity): https://conferences.miccai.org/2024/en/REVIEWER-GUIDELINES.html
    1. In equation 2, the notation (\phi_t) should be used instead of (\phi).
    2. In section three, under experiment settings, the nnU-Net is referred to as one of the baselines. However, it is subsequently abbreviated as U-Net throughout the rest of the section, which can be confusing.
  • 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

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

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

    The paper is clearly written and presents a promising solution, as evidenced by solid experimental results. It effectively demonstrates that improvements in right ventricle (RV) segmentation can be achieved through better segmentation consistency.

  • Reviewer confidence

    Very confident (4)

  • [Post rebuttal] After reading the author’s rebuttal, state your overall opinion of the paper if it has been changed

    N/A

  • [Post rebuttal] Please justify your decision

    N/A



Author Feedback

N/A



Meta-Review

Meta-review not available, early accepted paper.



back to top