Authors

Rotem Leibovitz, Jhonathan Osin, Lior Wolf, Guy Gurevitch, Talma Hendler

Abstract

We obtain a personal signature of a person’s learning progress in a self-neuromodulation task, guided by functional MRI (fMRI). The signature is based on predicting the activity of the Amygdala in a second neurofeedback session, given a similar fMRI-derived brain state in the first session. The prediction is made by a deep neural network, which is trained on the entire training cohort of patients. This signal, which is indicative of a person’s progress in performing the task of Amygdala modulation, is aggregated across multiple prototypical brain states and then classified by a linear classifier to various personal and clinical indications. The predictive power of the obtained signature is stronger than previous approaches for obtaining a personal signature from fMRI neurofeedback and provides an indication that a person’s learning pattern may be used as a diagnostic tool.

Link to paper

DOI: https://link.springer.com/chapter/10.1007/978-3-031-16431-6_27

SharedIt: https://rdcu.be/cVD49

Link to the code repository

https://github.com/MICCAI22/fmri_nf

Link to the dataset(s)

N/A

Reviews

Review #1

Please describe the contribution of the paper

This paper claims that neurofeedback data can also predict individual behavioral and clinical traits, in addition to instead existing generic resting-state 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.

This writing is easy to understand and the organization is good.
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. Neurofeedback is a major innovation of this paper, however, neurofeedback data is not easy to obtain, the authors need to further clarify how these neurofeedback data (e.g. fMRI data, Clinical data) for the experiments were obtained.
2. The design of the method section needs to be further clarified, e.g., why K-means clustering operations are performed.
3. It’s not clear that why the authors use the error of prediction as the signature, what is the motivation?
Please rate the clarity and organization of this paper

Good
Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance

The source code has been made public and has a good reproduction base.
Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
1. The motivation for the methods section needs to be further clarified.
2. NF data needs to be further compared and discussed with the performance of resting-state data that are commonly used.
Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making

5
Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

The organization of the paper is good, but the motivation is poor and the method is not clear description.
Number of papers in your stack

4
What is the ranking of this paper in your review stack?

1
Reviewer confidence

Very confident
[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

This interesting piece of work describes a self-modulation task guided by fMRI. Classifications are based on the fMRI signal and set to various personal and clinical indications. The individual learning pattern based in the amygdala can be used as a diagnostic tool perhaps.
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.
- This has novelty and the research is creative
- The application to mental disorders is no too far away, since the amygdala is a clear structure for fear/anxiety related symptoms.
- Neurofeedback is a strong candidate for self learning
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.
- Selection of the datasets is unclear, while it is part of a bigger dataset.
- The fMRI processing method has not been described. Was there any quality control (movement or artifacts in the data)?
- How was the fMRI acquisition performed?
Please rate the clarity and organization of this paper

Very Good
Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance

The described method seems reproducible. Code has been put up on Github.
Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html

Great piece of work! The focus on the amygdala is clear and well defined. This opens opportunities for further research into fear/anxiety disorders. The method is neuromodulatory and uses fMRI. Though details on the acquisition and data quality control are missing.
Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making

7
Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

There is potential for clinical applications.
Number of papers in your stack

4
What is the ranking of this paper in your review stack?

1
Reviewer confidence

Somewhat Confident
[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 authors developed a method for extraction of information from rs-fMRI data, which better predict personal traits
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.

The way of predicting data in Amygdala from non-Amygdala regions and using the prediction error as one of the traits predictor is novel and interesting
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.

Not sure how to properly interpret the MSE results. They seem to be arbitrarily scaled.
Please rate the clarity and organization of this paper

Satisfactory
Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance

no concern
Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html
- Not sure how to properly interpret the MSE results. They seem to be arbitrarily scaled.
- What’s the importance of the results regarding to traits prediction. Are they clinically useful?
- The description of the method does not seem to be very clear, maybe because the pipeline is fairly complicated and the space for this paper is somehow limited
Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making

5
Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

Overall seems to be a reasonable approach but with some major concerns
Number of papers in your stack

4
What is the ranking of this paper in your review stack?

3
Reviewer confidence

Confident but not absolutely certain
[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 #4

Please describe the contribution of the paper

The paper provides an increment in performance in obtaining personal signatures, and links brain states to the difference between actual and expected learning success.
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.

The presented method provides a sizable improvement in performance over previous work.
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.

The clinical traits may change over time, the proposed method may not work well on longitudinal data.
Please rate the clarity and organization of this paper

Good
Please comment on the reproducibility of the paper. Note, that authors have filled out a reproducibility checklist upon submission. Please be aware that authors are not required to meet all criteria on the checklist - for instance, providing code and data is a plus, but not a requirement for acceptance

Reproducibility is okay.
Please provide detailed and constructive comments for the authors. Please also refer to our Reviewer’s guide on what makes a good review: https://conferences.miccai.org/2022/en/REVIEWER-GUIDELINES.html

Experiments on longitudinal data are suggested to show the robustness of the proposed method.
Rate the paper on a scale of 1-8, 8 being the strongest (8-5: accept; 4-1: reject). Spreading the score helps create a distribution for decision-making

5
Please justify your recommendation. What were the major factors that led you to your overall score for this paper?

The proposed method gains improvements over previous work. The experiments and results are solid.
Number of papers in your stack

4
What is the ranking of this paper in your review stack?

2
Reviewer confidence

Not Confident
[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

Primary Meta-Review

Please provide your assessment of this work, taking into account all reviews. Summarize the key strengths and weaknesses of the paper and justify your recommendation. In case you deviate from the reviewers’ recommendations, explain in detail the reasons why. In case of an invitation for rebuttal, clarify which points are important to address in the rebuttal.

I respect all the reviewers’ suggestions, though I have concerns about the effectiveness of the proposed methods on longitudinal data.
What is the ranking of this paper in your stack? Use a number between 1 (best paper in your stack) and n (worst paper in your stack of n papers). If this paper is among the bottom 30% of your stack, feel free to use NR (not ranked).

1

Author Feedback

We thank the reviewer and the area chair for the supportive feedback. All requests for elucidation will be fully and carefully addressed. We will also try to check whether suitable longitudinal data is available and try to address this concern.

back to top

fMRI Neurofeedback Learning Patterns are Predictive of Personal and Clinical Traits