MétaCan
← all works

BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis

2021· article· en· 708 citations· W3199008037 on OpenAlex· 10.1016/j.media.2021.102233

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

Classifier prediction

metacan-v1-d91a1de5be90

Predictions imitate two machine teachers. Scores are not calibrated prevalence probabilities.

Classifier candidate
ObservationalBench or experimentalNot applicable
Classifier consensus
Bench or experimentalNot applicable
Teacher imitation scores

Codex

Not applicable0.264
Other design0.081
Bench or experimental0.079
Observational0.028
Bibliometrics0.026
Simulation or modelling0.012
Meta-analysis0.004
Metaresearch0.000
Case report0.000
Theoretical or conceptual0.000
Meta-epidemiology (broad)0.000
Open science0.000
Science and technology studies0.000
Research integrity0.000
Qualitative0.000
Scholarly communication0.000
Meta-epidemiology (narrow)0.000
Non-randomized trial0.000
Systematic review0.000
Randomized trial0.000

Gemma

Not applicable0.393
Bench or experimental0.110
Simulation or modelling0.009
Bibliometrics0.008
Metaresearch0.006
Observational0.005
Meta-analysis0.002
Theoretical or conceptual0.002
Research integrity0.001
Non-randomized trial0.001
Science and technology studies0.000
Case report0.000
Meta-epidemiology (broad)0.000
Scholarly communication0.000
Qualitative0.000
Systematic review0.000
Meta-epidemiology (narrow)0.000
Open science0.000
Randomized trial0.000

Machine scores (provisional)

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Opus teacher head0.020
GPT teacher head0.296
Teacher spread
0.276 how far apart the two teachers sit on this one work
Validation status
score_only:v0-immature-baseline verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Abstract

Understanding which brain regions are related to a specific neurological disorder or cognitive stimuli has been an important area of neuroimaging research. We propose BrainGNN, a graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI) and discover neurological biomarkers. Considering the special property of brain graphs, we design novel ROI-aware graph convolutional (Ra-GConv) layers that leverage the topological and functional information of fMRI. Motivated b…

Retrieved from PubMed through NCBI EFetch. Structured section labels are preserved.