# manasisbyali234/brain_tumor architecture

> Architecture diagram of the GitHub repository manasisbyali234/brain_tumor, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/manasisbyali234/brain_tumor
- Repository: https://github.com/manasisbyali234/brain_tumor

## Overview

This repository is a CT–MRI brain-tumor detection application with training, evaluation, inference, and visual explanation workflows. Users can submit scan pairs through the Streamlit or Tkinter interface, or run command-line prediction: images are prepared, aligned, fused, classified, and presented with explanation outputs. The graph also preserves the documented data-training and evaluation branches. Some UI and supporting source excerpts are partial; edges reflect explicit README statements, shown calls, or SOURCE INDEX references rather than assumed wiring.

Main entry points: [`predict.py`](https://github.com/manasisbyali234/brain_tumor/blob/main/predict.py) (Pair prediction), [`app.py`](https://github.com/manasisbyali234/brain_tumor/blob/main/app.py) (Web interface), [`gui_app.py`](https://github.com/manasisbyali234/brain_tumor/blob/main/gui_app.py) (Desktop interface), [`utils/dataset.py`](https://github.com/manasisbyali234/brain_tumor/blob/main/utils/dataset.py) (Dataset builder)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interfaces["User interfaces"]
  node_streamlit["Web interface<br/>[app.py]"]
  node_desktop["Desktop interface<br/>[gui_app.py]"]
end

subgraph group_imaging["Image processing"]
  node_scan_data[("Scan dataset")]
  node_dataset["Dataset builder<br/>[dataset.py]"]
  node_preprocess["Preprocessing<br/>[preprocessing.py]"]
  node_registration["Image registration<br/>[registration.py]"]
  node_fusion["Image fusion<br/>[fusion.py]"]
end

subgraph group_learning["Model and learning"]
  node_trainer["Dataset training<br/>[train.py]"]
  node_image_trainer["Image-based training<br/>[train_on_images.py]"]
  node_cnn["CNN models<br/>[cnn_model.py]"]
  node_evaluation["Model evaluation<br/>[evaluate.py]"]
end

subgraph group_results["Interpretation and results"]
  node_prediction["Pair prediction<br/>[predict.py]"]
  node_explain["Explainability<br/>[explainability.py]"]
  node_tumor_marking["Tumor marking<br/>[mark_tumors.py]"]
  node_outputs[("Saved results")]
end

node_user(("Clinician / user"))

node_user -->|"uses"| node_streamlit
node_user -->|"uses"| node_desktop
node_streamlit -->|"runs"| node_preprocess
node_streamlit -->|"runs"| node_registration
node_streamlit -->|"runs"| node_fusion
node_streamlit -->|"runs"| node_explain
node_streamlit -->|"uses"| node_cnn
node_desktop -->|"calls"| node_preprocess
node_desktop -->|"calls"| node_registration
node_desktop -->|"calls"| node_fusion
node_desktop -->|"calls"| node_explain
node_scan_data -->|"supplies scans"| node_dataset
node_dataset -->|"calls"| node_preprocess
node_dataset -->|"calls"| node_registration
node_dataset -->|"calls"| node_fusion
node_trainer -->|"loads data"| node_dataset
node_trainer -->|"builds model"| node_cnn
node_image_trainer -->|"trains"| node_cnn
node_prediction -->|"calls"| node_preprocess
node_prediction -->|"calls"| node_registration
node_prediction -->|"calls"| node_fusion
node_prediction -->|"predicts with"| node_cnn
node_prediction -->|"requests explanations"| node_explain
node_prediction -->|"saves figure"| node_outputs
node_evaluation -->|"saves metrics"| node_outputs
node_tumor_marking -->|"calls"| node_preprocess
node_tumor_marking -->|"loads weights"| node_cnn
node_explain -.->|"optional SHAP plot"| node_outputs

click node_streamlit "https://github.com/manasisbyali234/brain_tumor/blob/main/app.py"
click node_desktop "https://github.com/manasisbyali234/brain_tumor/blob/main/gui_app.py"
click node_scan_data "https://github.com/manasisbyali234/brain_tumor/tree/main/data"
click node_dataset "https://github.com/manasisbyali234/brain_tumor/blob/main/utils/dataset.py"
click node_preprocess "https://github.com/manasisbyali234/brain_tumor/blob/main/utils/preprocessing.py"
click node_registration "https://github.com/manasisbyali234/brain_tumor/blob/main/utils/registration.py"
click node_fusion "https://github.com/manasisbyali234/brain_tumor/blob/main/utils/fusion.py"
click node_trainer "https://github.com/manasisbyali234/brain_tumor/blob/main/train.py"
click node_image_trainer "https://github.com/manasisbyali234/brain_tumor/blob/main/train_on_images.py"
click node_cnn "https://github.com/manasisbyali234/brain_tumor/blob/main/models/cnn_model.py"
click node_evaluation "https://github.com/manasisbyali234/brain_tumor/blob/main/evaluate.py"
click node_prediction "https://github.com/manasisbyali234/brain_tumor/blob/main/predict.py"
click node_explain "https://github.com/manasisbyali234/brain_tumor/blob/main/utils/explainability.py"
click node_tumor_marking "https://github.com/manasisbyali234/brain_tumor/blob/main/mark_tumors.py"
click node_outputs "https://github.com/manasisbyali234/brain_tumor/tree/main/outputs"

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_streamlit,node_desktop,node_user toneBlue
class node_scan_data,node_dataset,node_preprocess,node_registration,node_fusion toneAmber
class node_trainer,node_image_trainer,node_cnn,node_evaluation toneMint
class node_prediction,node_explain,node_tumor_marking,node_outputs toneRose
```

## Components

### User interfaces

- [Web interface](https://github.com/manasisbyali234/brain_tumor/blob/main/app.py): `app.py`
- [Desktop interface](https://github.com/manasisbyali234/brain_tumor/blob/main/gui_app.py): `gui_app.py`

### Image processing

- [Scan dataset](https://github.com/manasisbyali234/brain_tumor/tree/main/data): `data`
- [Dataset builder](https://github.com/manasisbyali234/brain_tumor/blob/main/utils/dataset.py): `utils/dataset.py`
- [Preprocessing](https://github.com/manasisbyali234/brain_tumor/blob/main/utils/preprocessing.py): `utils/preprocessing.py`
- [Image registration](https://github.com/manasisbyali234/brain_tumor/blob/main/utils/registration.py): `utils/registration.py`
- [Image fusion](https://github.com/manasisbyali234/brain_tumor/blob/main/utils/fusion.py): `utils/fusion.py`

### Model and learning

- [Dataset training](https://github.com/manasisbyali234/brain_tumor/blob/main/train.py): `train.py`
- [Image-based training](https://github.com/manasisbyali234/brain_tumor/blob/main/train_on_images.py): `train_on_images.py`
- [CNN models](https://github.com/manasisbyali234/brain_tumor/blob/main/models/cnn_model.py): `models/cnn_model.py`
- [Model evaluation](https://github.com/manasisbyali234/brain_tumor/blob/main/evaluate.py): `evaluate.py`

### Interpretation and results

- [Pair prediction](https://github.com/manasisbyali234/brain_tumor/blob/main/predict.py): `predict.py`
- [Explainability](https://github.com/manasisbyali234/brain_tumor/blob/main/utils/explainability.py): `utils/explainability.py`
- [Tumor marking](https://github.com/manasisbyali234/brain_tumor/blob/main/mark_tumors.py): `mark_tumors.py`
- [Saved results](https://github.com/manasisbyali234/brain_tumor/tree/main/outputs): `outputs`

### Other components

- **Clinician / user**

## Connections

- Clinician / user → Web interface: uses (evidence: `README.md`)
- Clinician / user → Desktop interface: uses (evidence: `README.md`)
- Web interface → Preprocessing: runs (evidence: `app.py`)
- Web interface → Image registration: runs (evidence: `app.py`)
- Web interface → Image fusion: runs (evidence: `app.py`)
- Web interface → Explainability: runs (evidence: `app.py`)
- Web interface → CNN models: uses (evidence: `app.py`)
- Desktop interface → Preprocessing: calls (evidence: `gui_app.py`)
- Desktop interface → Image registration: calls (evidence: `gui_app.py`)
- Desktop interface → Image fusion: calls (evidence: `gui_app.py`)
- Desktop interface → Explainability: calls (evidence: `gui_app.py`)
- Scan dataset → Dataset builder: supplies scans (evidence: `README.md`)
- Dataset builder → Preprocessing: calls (evidence: `utils/dataset.py`)
- Dataset builder → Image registration: calls (evidence: `utils/dataset.py`)
- Dataset builder → Image fusion: calls (evidence: `utils/dataset.py`)
- Dataset training → Dataset builder: loads data (evidence: `train.py`)
- Dataset training → CNN models: builds model (evidence: `train.py`)
- Image-based training → CNN models: trains (evidence: `train_on_images.py`)
- Pair prediction → Preprocessing: calls (evidence: `predict.py`)
- Pair prediction → Image registration: calls (evidence: `predict.py`)
- Pair prediction → Image fusion: calls (evidence: `predict.py`)
- Pair prediction → CNN models: predicts with (evidence: `README.md`)
- Pair prediction → Explainability: requests explanations (evidence: `README.md`)
- Pair prediction → Saved results: saves figure (evidence: `README.md`)
- Model evaluation → Saved results: saves metrics (evidence: `README.md`)
- Tumor marking → Preprocessing: calls (evidence: `mark_tumors.py`)
- Tumor marking → CNN models: loads weights (evidence: `mark_tumors.py`)
- Explainability → Saved results: optional SHAP plot (evidence: `README.md`)
