# 141002/brain-tumor-mri-tda-ml architecture

> Architecture diagram of the GitHub repository 141002/brain-tumor-mri-tda-ml, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-04). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/141002/brain-tumor-mri-tda-ml
- Repository: https://github.com/141002/brain-tumor-mri-tda-ml

## Overview

This is a notebook-led brain MRI classification experiment using persistent homology. The documented workflow loads MRI images, prepares them for cubical-complex filtration, derives H0/H1 persistence-image features, then splits the data, evaluates three classifiers, and compares results. The repository tree contains only the notebook and requirements file; the README describes additional source modules, but they are not present in the supplied tree. The graph therefore maps documented responsibilities to the notebook and cites README relationships; notebook internals were not sampled.

Main entry points: [`brain_tumor_mri.ipynb`](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb) (Stratified split)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_prep["Image Preparation"]
  node_prepare["Image preparation"]
  node_filtration["Filtration grid"]
end

subgraph group_tda["Topological Features"]
  node_complex["Cubical complex"]
  node_persistence["Persistence computation"]
  node_h0["H0 diagrams"]
  node_h1["H1 diagrams"]
  node_images["Persistence images"]
  node_features["800D features"]
end

subgraph group_classification["Classification"]
  node_split["Stratified split"]
  node_logistic["Logistic regression"]
  node_svm["RBF SVM"]
  node_forest["Random forest"]
  node_evaluation["Model evaluation"]
end

node_user(("Notebook user"))
node_drive["MRI dataset"]
node_notebook["Experiment notebook"]

node_user -->|"runs"| node_notebook
node_drive -->|"supplies images"| node_notebook
node_notebook -->|"prepares images"| node_prepare
node_prepare -->|"normalizes and inverts"| node_filtration
node_filtration -->|"builds grid"| node_complex
node_complex -->|"computes intervals"| node_persistence
node_persistence -->|"produces H0"| node_h0
node_persistence -->|"produces H1"| node_h1
node_h0 -->|"vectorizes"| node_images
node_h1 -->|"vectorizes"| node_images
node_images -->|"concatenates"| node_features
node_features -->|"feeds"| node_split
node_split -->|"trains and tests"| node_logistic
node_split -->|"trains and tests"| node_svm
node_split -->|"trains and tests"| node_forest
node_logistic -->|"reports metrics"| node_evaluation
node_svm -->|"reports metrics"| node_evaluation
node_forest -->|"reports metrics"| node_evaluation

click node_notebook "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_prepare "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_filtration "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_complex "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_persistence "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_h0 "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_h1 "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_images "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_features "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_split "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_logistic "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_svm "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_forest "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"
click node_evaluation "https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_prepare,node_filtration,node_user toneBlue
class node_complex,node_persistence,node_h0,node_h1,node_images,node_features toneAmber
class node_split,node_logistic,node_svm,node_forest,node_evaluation toneMint
class node_drive toneIndigo
class node_notebook toneTeal
```

## Components

### Image Preparation

- [Image preparation](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [Filtration grid](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`

### Topological Features

- [Cubical complex](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [Persistence computation](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [H0 diagrams](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [H1 diagrams](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [Persistence images](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [800D features](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`

### Classification

- [Stratified split](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [Logistic regression](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [RBF SVM](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [Random forest](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`
- [Model evaluation](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`

### Other components

- **Notebook user**
- **MRI dataset**
- [Experiment notebook](https://github.com/141002/brain-tumor-mri-tda-ml/blob/main/brain_tumor_mri.ipynb): `brain_tumor_mri.ipynb`

## Connections

- Notebook user → Experiment notebook: runs (evidence: `README.md`)
- MRI dataset → Experiment notebook: supplies images (evidence: `README.md`)
- Experiment notebook → Image preparation: prepares images (evidence: `README.md`)
- Image preparation → Filtration grid: normalizes and inverts (evidence: `README.md`)
- Filtration grid → Cubical complex: builds grid (evidence: `README.md`)
- Cubical complex → Persistence computation: computes intervals (evidence: `README.md`)
- Persistence computation → H0 diagrams: produces H0 (evidence: `README.md`)
- Persistence computation → H1 diagrams: produces H1 (evidence: `README.md`)
- H0 diagrams → Persistence images: vectorizes (evidence: `README.md`)
- H1 diagrams → Persistence images: vectorizes (evidence: `README.md`)
- Persistence images → 800D features: concatenates (evidence: `README.md`)
- 800D features → Stratified split: feeds (evidence: `README.md`)
- Stratified split → Logistic regression: trains and tests (evidence: `README.md`)
- Stratified split → RBF SVM: trains and tests (evidence: `README.md`)
- Stratified split → Random forest: trains and tests (evidence: `README.md`)
- Logistic regression → Model evaluation: reports metrics (evidence: `README.md`)
- RBF SVM → Model evaluation: reports metrics (evidence: `README.md`)
- Random forest → Model evaluation: reports metrics (evidence: `README.md`)
