Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/9kyos9/fmri_gnn

Repository for Dissertation [Multi-Atlas Based Graph Neural Network for Alzheimer's Disease Prediction Using rs-fMRI Data]

https://github.com/9kyos9/fmri_gnn

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Repository for Dissertation [Multi-Atlas Based Graph Neural Network for Alzheimer's Disease Prediction Using rs-fMRI Data]

Basic Info
  • Host: GitHub
  • Owner: 9kyos9
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 278 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 10 months ago · Last pushed 10 months ago
Metadata Files
Readme

README.md

Multi-Atlas Based Graph Neural Network for Alzheimer's Disease Prediction Using rs-fMRI Data

This is a repository for Dissertation Project at KCL

Dataset Availability

The dataset used for this study was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). Due to the Data Use Agreement with the Alzheimer's Disease Neuroimaging Initiative (ADNI), the raw data used in this project cannot be shared publicly. To access the data, please visit the ADNI website and apply for access directly.

Project Structure

The file structure of this project is as follows.

```bash ├── README.md ├── script │ ├── connadpreprocessingtemplate.m │ ├── connadpreprocessingtemplate.m │ └── unzip.m ├── notebooks │ ├── fMRIGCNwknngraphensemblehyperparametertuningnestedCV.ipynb │ └── fMRIGCNwknngraphensemblenohyperparametertuning.ipynb └── src ├── ROIAALExtraction.py └── ROISchaeferExtraction.py

```

  • script/: Contains MATLAB scripts for preprocessing the raw fMRI data using the CONN Toolbox.

  • src/: Contains Python modules for feature extraction. These scripts are used to extract regional time series and generate functional connectivity (FC) matrices based on various brain atlases (e.g., AAL, Schaefer).

  • notebooks/: Contains Jupyter notebooks for the main analysis pipeline, which includes graph construction, GNN model training, and evaluation.

    • fMRIGCN_w_knngraph_ensemble_hyperparametertuning_nestedCV.ipynb: Implements the full GNN ensemble model with a robust hyperparameter tuning process using Nested Cross-Validation.
    • fMRIGCN_w_knngraph_ensemble_no_hyperparametertuning.ipynb: Implements the same pipeline but without hyperparameter tuning. These two notebooks are provided to directly compare and demonstrate the impact of hyperparameter tuning on model performance.
    • Note on Model Implementation: As the single-atlas models are the building blocks for the final ensemble model, they are implemented within both notebooks. Upon execution, the notebooks will output the evaluation results for the individual single-atlas models and the final ensemble model, allowing for a comprehensive performance comparison.

Owner

  • Name: Eunkyo
  • Login: 9kyos9
  • Kind: user
  • Location: Seoul
  • Company: Dongguk University

GitHub Events

Total
  • Push event: 5
Last Year
  • Push event: 5