https://github.com/borgwardtlab/adni_3dcnnvstda

This is a summary of the model code used in "Back to the basics with inclusion of clinical domain knowledge - A simple, scalable and effective model of Alzheimer's Disease classification". It comprised the relevant 3D CNNs for hippocampus, patch and full inner brain image subsets, the TDA 2D CNN with relevant dense models to combine models trained on persistence images from different homological dimensions. Moreover, the models (GNN and LR) to combine multiple image patches are included, as well as the data splits in terms of ADNI database patient IDs (partitions).
https://github.com/borgwardtlab/adni_3dcnnvstda

Last synced: 10 months ago
JSON representation

This is a summary of the model code used in "Back to the basics with inclusion of clinical domain knowledge - A simple, scalable and effective model of Alzheimer's Disease classification". It comprised the relevant 3D CNNs for hippocampus, patch and full inner brain image subsets, the TDA 2D CNN with relevant dense models to combine models trained on persistence images from different homological dimensions. Moreover, the models (GNN and LR) to combine multiple image patches are included, as well as the data splits in terms of ADNI database patient IDs (partitions).

• Host: GitHub
• URL: https://github.com/borgwardtlab/adni_3dcnnvstda
• Owner: BorgwardtLab
• Created: 2021-07-21T10:26:20.000Z (almost 5 years ago)
• Default Branch: main
• Last Pushed: 2021-08-02T14:06:57.000Z (almost 5 years ago)
• Last Synced: 2025-07-11T11:54:38.401Z (11 months ago)
• Language: Python
• Size: 103 KB
• Stars: 7
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# ADNI_3DCNNvsTDA

This is a summary of the model code used in "Back to the basics with inclusion of clinical domain knowledge - A simple, scalable and effective model of Alzheimer's Disease classification". It comprised the relevant 3D CNNs for hippocampus, patch and full inner brain image subsets, the TDA 2D CNN with relevant dense models to combine models trained on persistence images from different homological dimensions. Moreover, the models (GNN and LR) to combine multiple image patches are included, as well as the data splits in terms of ADNI database patient IDs (partitions).