Abstract

The electroencephalogram (EEG) acquisition paradigm is fundamental to brain-computer interface (BCI) research as it directly determines the mechanisms of brain activity evoked, significantly influencing the quality of collected EEG signals. Traditional static cueing paradigms often struggle to effectively induce the motor imagery (MI) state, which can lead to inconsistent task execution and degraded EEG signal quality. This study proposes an innovative MI data acquisition paradigm employing dynamic visual cues depicting real human movements to enhance engagement and more effectively induce the MI state. We build the first novel dynamic visual cueing MI dataset, comprising EEG data acquired using both dynamic and static paradigms from five subjects. We analyze our dynamic visual cueing paradigm using questionnaire, qualitative, and quantitative analyses, evaluating it from subjective experience, physiological phenomena, and EEG signal decoding accuracy perspectives. Experiments show that our dynamic cueing paradigm significantly enhances subjects’ task understanding and concentration, leading to greater brain activation and, consequently, improved decoding accuracy of brain states in MI-BCI tasks. By eliciting more pronounced brain state activity, our method fundamentally improves the quality of acquired EEG signals, laying the foundation for accurate decoding of brain states, and provides an innovative perspective for the development and improvement of MI-BCI.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2025/paper/3695_paper.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to the Code Repository

N/A

Link to the Dataset(s)

N/A

BibTex

@InProceedings{YueChe_Improving_MICCAI2025,
        author = { Yue, Chenxi and Hu, Huawen and Yuan, Qilong and Shi, Enze and Wang, Jiaqi and Zhao, Kui and Wang, Xuhui and Zhang, Shu},
        title = { { Improving Motor Imagery EEG Signal Quality with Dynamic Visual Cues: An Innovative Paradigm and Dataset } },
        booktitle = {proceedings of Medical Image Computing and Computer Assisted Intervention -- MICCAI 2025},
        year = {2025},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 15972},
        month = {September},
        page = {286 -- 295}
}


Reviews

Review #1

  • Please describe the contribution of the paper
    • The work proposes a novel dataset that leverages dynamic visual cueing for MI data acquisition.
    • The experiments demonstrate the superior performance in enhancing attention, task comprehension, and brain state decoding compared with static paradims.
  • 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 is overall clear and easy to follow.
    • The dataset’s dynamic paradigm is novel and effective compared with the static condition tested in the same setting
  • 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.
    • While I understand that this dataset may still be under active development, the current sample size (n=5) is too small for an EEG dataset, especially in the context of public release or publication.
    • The paper claims superiority of the proposed dynamic dataset over existing static datasets. However, this claim is not fully supported by the experimental comparisons: key metrics such as ERD/ERS patterns, time-frequency characteristics, brain activation maps, and decoding accuracy are only evaluated within the dataset itself, without comparisons to other static datasets. This significantly weakens the strength of the claim.
  • 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.

    (3) Weak Reject — could be rejected, dependent on rebuttal

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

    I believe this novel dataset, along with its innovative paradigm, is valuable and has great potential. However, the current sample size is too small to draw strong conclusions. As mentioned in the weaknesses, the lack of comparison with existing datasets further limits the strength of the claims regarding its advantages.

  • 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

    The paper proposed a potential dynamic visual cue method for improving motor imagery EEG signal quality.

  • 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 authors collected a small dataset as a demo and plan to open source it once the paper is accepted. Through qualitative and quantitative analysis, the authors validated the advantages of dynamic visual cues over static visual cues.

  • 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 authors did not present the difference between dynamic visual cues and static visual cues well. A more intuitive figure for illustrating the difference between the two is expected. Also, the questionnaire analysis is too simplistic.

  • 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 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?

    The method of dynamic visual cues proposed by the authors is interesting and innovative. More importantly, the authors claim to provide a demo dataset after acceptance.

  • Reviewer confidence

    Very confident (4)

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

    Accept

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

    The authors provided a reasonable explanation for the questions I raised and promised to make subsequent revisions.



Review #3

  • Please describe the contribution of the paper

    The main contribution of the paper is the proposal of a novel dynamic visual cueing paradigm for motor imagery (MI) brain-computer interface (BCI) data acquisition. This paradigm uses dynamic images of real human movements as visual cues to enhance engagement and task comprehension, thereby improving the quality of EEG signals in MI tasks. Compared to traditional static visual cueing paradigms, the dynamic paradigm shows significant advantages in task comprehension, concentration, and brain state decoding accuracy.

  • 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.

    Comprehensive Validation:The authors validate the effectiveness of the dynamic paradigm through multiple methods, including questionnaires, qualitative analysis (e.g., ERD/ERS phenomena, brain region activation maps), and quantitative analysis (e.g., EEG signal decoding accuracy).

    Practical Potential:The dynamic paradigm’s advantage in improving EEG signal quality makes it highly promising for practical BCI applications. For example, in assisting patients with motor impairments in rehabilitation training or controlling external devices, the dynamic paradigm may provide more accurate brain state decoding, thereby enhancing system performance and user experience.

  • 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.

    Experimental Design Limitations:The experiment recruited only five subjects, which is a very small sample size. This may lead to insufficient statistical power of the results and limit the generalizability to a broader population. Additionally, the experiment did not consider individual differences among subjects (such as reaction speed and concentration levels) that could affect the results.

    Insufficient Explanation of Results:Although the experimental results show that the dynamic paradigm outperforms the static paradigm in EEG signal decoding accuracy, the authors did not fully explain the physiological mechanisms behind this difference. For example, is it because the dynamic paradigm better activates motor-related brain areas, or because subjects are more focused under the dynamic paradigm?

  • 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

    In reviewing this paper, I have noted several areas that require further clarification and improvement.

    Firstly, regarding the experimental design, the authors claim that the dynamic paradigm outperforms the static paradigm, but the experiment only involved five subjects, which is a very small sample size and insufficient to demonstrate statistical significance. Additionally, the experiment did not adequately account for individual differences among subjects (such as concentration levels and task familiarity), which may affect the reliability of the results.

    Secondly, in terms of method description, the paper lacks clarity in detailing the specific implementation of the dynamic and static paradigms. For example, the design and implementation process of the dynamic cues in the dynamic paradigm are not clearly explained, making it difficult for other researchers to replicate the experiment. Moreover, when discussing the advantages of the dynamic paradigm, the authors did not fully consider other potential confounding factors, such as differences in cue content.

    Lastly, in the results analysis, the paper did not conduct an in-depth exploration of the physiological mechanisms underlying the differences between the dynamic and static paradigms. For example, is it because the dynamic paradigm better activates motor-related brain areas, or because subjects are more focused under the dynamic paradigm? The authors need to further investigate these issues in future work and provide more detailed experimental design, method description, and results analysis.

  • 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?

    I have given a rating of “Accept” based on several factors. Firstly, the paper proposes a novel dynamic visual cueing paradigm for improving motor imagery tasks in brain-computer interfaces, which has some degree of novelty and potential for practical application. However, the experimental design has limitations, such as a very small sample size, which makes it difficult to demonstrate the statistical significance of the dynamic paradigm’s superiority.

  • Reviewer confidence

    Confident but not absolutely certain (3)

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

    Accept

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

    The paper proposes a novel dynamic visual cueing paradigm for motor imagery (MI) EEG signal acquisition, demonstrating significant improvements in task comprehension, attention, and EEG signal decoding accuracy compared to traditional static paradigms. The authors have addressed the major concerns raised in the first review, including the small sample size and the lack of detailed method description. They have expanded the dataset to include more subjects and provided additional details on the experimental methods. The revised manuscript now includes a more comprehensive analysis and clearer illustrations. However, there are still minor areas for improvement: -The authors could provide more detailed physiological explanations for the observed differences between dynamic and static paradigms. -The questionnaire analysis could include more demographic information to better understand the subject population. -The authors could discuss potential applications of the dynamic paradigm in clinical settings or other practical scenarios.




Author Feedback

Dear Editors and Reviewers, We sincerely thank you for taking the time to review our manuscript entitled “Improving Motor Imagery EEG Signal Quality with Dynamic Visual Cues: An Innovative Paradigm and Dataset”. We deeply appreciate your constructive comments, which have helped us substantially improve the quality and clarity of our work. Our responses are as follows: Response to Reviewer #1 We thank Reviewer #1 for their positive feedback on the novelty of our dynamic visual cues, and for the constructive suggestions. Q1: The distinction between dynamic and static visual cues is not clearly presented; a more intuitive illustration is needed. The questionnaire analysis is overly simplistic. R1: We thank the reviewer for this valuable suggestion. We will revise the figure to more clearly and intuitively illustrate the differences between dynamic visual cues and static visual cues. Regarding the questionnaire analysis, we conducted a comprehensive set of questionnaire-based assessments, including a demographic questionnaire, post-run feedback forms, and surveys covering subjects’ physical conditions and emotional states prior to the experiment, as well as their immediate feedback during the task. Due to space limitations in the original submission, we provided only a simplified version of the analysis. We will include more discussion to enrich the questionnaire analysis. Response to Reviewer #2 We are grateful to Reviewer #2 for recognizing the novelty and potential impact of our proposed paradigm. We also appreciate the important concerns raised, which we have addressed as follows. Q1: The sample size (n=5) is insufficient for an EEG dataset, inadequate for public release or publication. A1: Thank you for highlighting this important concern. While the current dataset includes data from five subjects, each subject contributed to both the dynamic and static paradigms, with rich experimental content and multiple task types. As a result, the amount of data per participant is substantially larger—approximately twice that of conventional EEG datasets with similar sample sizes. More importantly, we have already expanded our sample size to 10 subjects, and we are currently processing data from additional subjects under both paradigms, with plans to release the expanded dataset in future updates. Q2: Experimental comparisons are insufficient to support superiority of the proposed dynamic dataset over existing static datasets. Key metrics are only evaluated within the dataset itself without direct comparisons to other static datasets. A2: Thank you very much for your insightful question. In this work, the key to comparing dynamic paradigms with static paradigms lies in conducting experiments on the same subjects. Using external datasets would not provide meaningful reference points, as this would introduce confounding variables from different subject populations, recording conditions, and equipment setups, potentially leading to biased conclusions. Therefore, it is necessary to collect data from the same subjects across multiple paradigms. Furthermore, our static paradigm design references current mainstream paradigm design approaches. In future work, we plan to expand our data collection to include additional both dynamic and static paradigms. Response to Reviewer #3 We sincerely thank Reviewer #3 for the encouraging feedback and generous score. Your recognition of the paradigm’s practical potential and validation is highly appreciated. We are currently processing data from additional subjects and plan to release these in future updates to expand the dataset and enhance its generalizability. Dear Editors and Reviewers, we believe that the manuscript has been significantly improved as a result of these revisions and now more clearly presents our contributions. We hope the reviewers and editors find our responses satisfactory. Thank you once again for your valuable feedback and consideration.




Meta-Review

Meta-review #1

  • Your recommendation

    Invite for Rebuttal

  • 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

  • After you have reviewed the rebuttal and updated reviews, please provide your recommendation based on all reviews and the authors’ rebuttal.

    Accept

  • Please justify your recommendation. You may optionally write justifications for ‘accepts’, but are expected to write a justification for ‘rejects’

    N/A



Meta-review #2

  • After you have reviewed the rebuttal and updated reviews, please provide your recommendation based on all reviews and the authors’ rebuttal.

    Accept

  • Please justify your recommendation. You may optionally write justifications for ‘accepts’, but are expected to write a justification for ‘rejects’

    N/A



Meta-review #3

  • After you have reviewed the rebuttal and updated reviews, please provide your recommendation based on all reviews and the authors’ rebuttal.

    Accept

  • Please justify your recommendation. You may optionally write justifications for ‘accepts’, but are expected to write a justification for ‘rejects’

    This paper presents a novel dynamic visual cueing paradigm to improve motor imagery EEG signal quality, supported by both qualitative and quantitative validation. While concerns about the small sample size and lack of broader dataset comparisons were raised, the authors’ rebuttal addressed these issues with clarification and evidence of ongoing dataset expansion. The proposed paradigm is promising, methodologically sound, and has potential for meaningful impact in BCI research, thus I would lean towards accepting.



back to top