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

Abstract

Misfolded tau and amyloid-beta (Abeta) are hallmark proteins of Alzheimer’s Disease (AD). Due to their clinical significance, rich datasets that track their temporal evolution have been created. For example, ADNI has hundreds of subjects with PET imaging of both these two proteins. Interpreting and combining this data beyond statistical correlations remains a challenge. Biophysical models offer a complementary avenue to assimilating such complex data and eventually helping us better understand disease progression. To this end, we introduce a mathematical model that tracks the dynamics of four species (normal and abnormal tau and Abeta) and uses a graph to approximate their spatial coupling. The graph nodes represent gray matter regions of interest (ROI), and the edges represent tractography-based connectivity between ROIs. We model interspecies interactions, migration, proliferation, and clearance. Our biophysical model has seven unknown scalar parameters plus unknown initial conditions for tau and Abeta. Using imaging scans, we can calibrate these parameters by solving an inverse problem. The scans comprise longitudinal tau and Abeta PET scans, along with MRI for subject specific anatomy. We propose an inversion algorithm that stably reconstructs the unknown parameters. We verify and test its numerical stability in the presence of noise using synthetic data. We discovered that the inversion is more stable when using multiple scans. Finally, we apply the overall methodology on 334 subjects from the ADNI dataset and compare it to a commonly used tau-only model calibrated by a single PET scan. We report the R2 and relative fitting error metrics. The proposed method achieves R2 = 0.82 compared to R2 = 0.64 of the tau-only single-scan reconstruction.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2024/paper/0453_paper.pdf

SharedIt Link: https://rdcu.be/dY6ia

SpringerLink (DOI): https://doi.org/10.1007/978-3-031-72083-3_2

Supplementary Material: https://papers.miccai.org/miccai-2024/supp/0453_supp.pdf

Link to the Code Repository

N/A

Link to the Dataset(s)

N/A

BibTex

@InProceedings{Wen_Biophysicsbased_MICCAI2024,
        author = { Wen, Zheyu and Ghafouri, Ali and Biros, George},
        title = { { Biophysics-based data assimilation of longitudinal tau and amyloid-β PET scans } },
        booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024},
        year = {2024},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 15004},
        month = {October},
        page = {14 -- 24}
}

Reviews

Review #1

  • Please describe the contribution of the paper

    They have constructed a model based on pet scans of two proteins relevant to alzheimer’s and their interactions. According to the authors this is the first to do so with both proteins.

  • 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.

    Their model outperforms previous Tau only models. To the best of my knowledge it is a novel approach. Good sample size.

  • 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.

    Other than finding it hard to follow at points I did not notice any major weaknesses.

  • 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?

    no

  • 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
    • I’d appreciate a more explicit lay term sentence near the start that explains the purpose of your model. I think I got it but it was difficult as someone not in alzheimer’s research.

    The last line of your conclusion that states your plan to tell if the model can predict would have given better context earlier.

  • 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?

    It is a novel progression over tau-only models so the paper does have value. I do not have any major suggestions for improvement that would result in a rejection. I do struggle to measure how important this model is though in the context of Alzheimers. It may be essential but I would appreciate more explanation of added value other than an increase in performance metrics. As the link between these proteins appears to be known I am not sure it deserves a 6. This may be a result of my lack of experience in Alzheimers though.

  • Reviewer confidence

    Somewhat confident (2)

  • [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

    The paper introduces a novel coupled biophysical model for tracking tau and amyloid-beta (Aβ) dynamics in Alzheimer’s Disease (AD) using longitudinal PET scans. It leverages a graph-based spatial coupling and a gradient-based inversion algorithm to assimilate these dynamics from clinical imaging data. The methodology was tested against 334 subjects from the ADNI dataset, demonstrating improved accuracy in modeling disease progression compared to existing tau-only models.

  • 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. Novelty of the Biophysical Model: The introduction of a coupled tau-A \beta model, incorporating both species in a single framework, is novel and addresses the complex interaction between these biomarkers more realistically than the previous models
    2. Clinical relevance and extensive validation: The application of this model to a large clinical dataset (ANDI) and demonstrated superiority over traditional models.
    3. The use of gradient-based inversion for parameter estimation could capture the underlying biological processes.
  • 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 model’s complexity and the computational demand of the inversion process might limit the applicability in routine clinical settings.
    2. Generalization concerns: the model’s performance across different stages of AD or the applicability to other neurodegenerative diseases remain a question.
  • Please rate the clarity and organization of this paper

    Very 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. Provide more details on the computational requirements and runtime of the model to better assess its feasibility in different settings.
    2. Explore the model’s performance across various stages of Alzheimer’s disease to understand its applicability and limitations more comprehensively.
  • 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 innovative modeling approach, combined with robust validation on a significant clinical dataset, highlights the potential of this work to advance the understanding of Alzheimer’s Disease progression.

  • 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

    1. Proposed a coupled tau-Aβ biophysical model using ordinary differential equations to infer reasoning ability in Alzheimer’s disease in the tau/Aβ process.

    2. Presentation of a gradient-based inversion algorithm for assimilating the model with longitudinal Tau-PET and Aβ-PET scans.

    3. The complete experiment involved using synthetic data simulations and validation with ADNI clinical data.

  • 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 paper demonstrates the great explanatory power of tau-Aβ disease dynamics analysis using ordinary differential equations.

    2. A vital strength of this paper is its ability to use ordinary differential equations to analyze the spatial spreading of abnormal tau and Aβ.

    3. The proposed inversion algorithm effectively calibrates unknown parameters and exhibits improved stability when using multiple scans.

  • 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.

    This paper tracks the temporal evolution of four species for each ROI, although there is a calculation of the tau/Aβ distribution of ROI and cerebellum. However, it does not explicitly indicate which ROI regions are abnormal.

  • Please rate the clarity and organization of this paper

    Very 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?

    No

  • 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

    Since the model involves multiple unknown parameters, the sensitivity of these parameters to the initial differential equation coefficients may affect the model’s predictive ability and stability. I suggested that ablation experiments be conducted, as shown in Table 1.

  • 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?

    I recommend accepting this paper for publication due to its significant clinical implications in furthering our understanding of Alzheimer’s disease and its clear and concise analysis of the tau/Aβ interaction inference process, which is effectively modeled using ordinary differential equations.

  • Reviewer confidence

    Somewhat confident (2)

  • [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