# ytashan/brain-tumor-segmentation architecture

> Architecture diagram of the GitHub repository ytashan/brain-tumor-segmentation, 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/ytashan/brain-tumor-segmentation
- Repository: https://github.com/ytashan/brain-tumor-segmentation

## Overview

This notebook implements a BraTS 2020 MRI segmentation pipeline, from dataset discovery and preparation through model training and patient-level reporting. The primary user workflow supplies a patient’s MRI path, obtains a tumor segmentation, then derives size and heuristic risk results and produces a 3D report. Separate documented branches cover model evaluation and batch prediction for the unlabeled validation set. The repository contains no sampled source excerpts, so relationships below rely on the README’s documented stages and capabilities; implementation details and internal call ownership cannot be verified.

Main entry points: [`brain-tumor-segmentation-era-v4.ipynb`](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb) (Tumor Segmentation)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data Preparation"]
  node_discovery["Dataset Discovery"]
  node_eda["MRI Exploration"]
  node_preprocess["MRI Preprocessing"]
  node_cache[("Preprocessed Cache")]
  node_patches["Patch Dataset"]
end

subgraph group_model["Segmentation Model"]
  node_model["Residual Attention U-Net"]
  node_training["Model Training"]
  node_inference["Sliding-Window Inference"]
end

subgraph group_analysis["Analysis and Reports"]
  node_segmentation["Tumor Segmentation"]
  node_evaluation["Test Evaluation"]
  node_quantification["Tumor Quantification"]
  node_risk["Research Risk Score"]
  node_visualization["3D Visualization"]
end

subgraph group_outputs["User Outputs"]
  node_report["Patient 3D Report"]
  node_batch["Validation Batch Prediction"]
  node_artifacts["Prediction and Metric Files"]
end

node_user(("Research User"))
node_dataset[("BraTS MRI Data")]

node_user -->|"configures paths"| node_discovery
node_dataset -->|"provides MRI data"| node_discovery
node_discovery -->|"enables exploration"| node_eda
node_discovery -->|"locates data for"| node_preprocess
node_preprocess -->|"writes cache"| node_cache
node_cache -->|"supplies volumes"| node_patches
node_patches -->|"provides samples"| node_training
node_training -->|"optimizes"| node_model
node_model -->|"provides predictions"| node_inference
node_inference -->|"produces labels"| node_segmentation
node_segmentation -->|"evaluated on test set"| node_evaluation
node_segmentation -->|"measured for size"| node_quantification
node_quantification -->|"informs score"| node_risk
node_segmentation -->|"overlaid in"| node_visualization
node_visualization -->|"renders report"| node_report
node_risk -->|"included in"| node_report
node_user -->|"requests patient prediction"| node_inference
node_inference -->|"used for batch prediction"| node_batch
node_batch -->|"writes NIfTIs"| node_artifacts
node_evaluation -->|"produces metrics"| node_artifacts
node_report -->|"exports reports"| node_artifacts

click node_discovery "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_eda "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_preprocess "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_cache "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_patches "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_model "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_training "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_inference "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_segmentation "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_evaluation "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_quantification "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_risk "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_visualization "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_report "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_batch "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb"
click node_artifacts "https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.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_discovery,node_eda,node_preprocess,node_cache,node_patches,node_user toneBlue
class node_model,node_training,node_inference,node_dataset toneAmber
class node_segmentation,node_evaluation,node_quantification,node_risk,node_visualization toneMint
class node_report,node_batch,node_artifacts toneRose
```

## Components

### Data Preparation

- [Dataset Discovery](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [MRI Exploration](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [MRI Preprocessing](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Preprocessed Cache](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Patch Dataset](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`

### Segmentation Model

- [Residual Attention U-Net](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Model Training](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Sliding-Window Inference](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`

### Analysis and Reports

- [Tumor Segmentation](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Test Evaluation](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Tumor Quantification](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Research Risk Score](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [3D Visualization](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`

### User Outputs

- [Patient 3D Report](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Validation Batch Prediction](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`
- [Prediction and Metric Files](https://github.com/ytashan/brain-tumor-segmentation/blob/main/brain-tumor-segmentation-era-v4.ipynb): `brain-tumor-segmentation-era-v4.ipynb`

### Other components

- **Research User**
- **BraTS MRI Data**

## Connections

- Research User → Dataset Discovery: configures paths (evidence: `README.md`)
- BraTS MRI Data → Dataset Discovery: provides MRI data (evidence: `README.md`)
- Dataset Discovery → MRI Exploration: enables exploration (evidence: `README.md`)
- Dataset Discovery → MRI Preprocessing: locates data for (evidence: `README.md`)
- MRI Preprocessing → Preprocessed Cache: writes cache (evidence: `README.md`)
- Preprocessed Cache → Patch Dataset: supplies volumes (evidence: `README.md`)
- Patch Dataset → Model Training: provides samples (evidence: `README.md`)
- Model Training → Residual Attention U-Net: optimizes (evidence: `README.md`)
- Residual Attention U-Net → Sliding-Window Inference: provides predictions (evidence: `README.md`)
- Sliding-Window Inference → Tumor Segmentation: produces labels (evidence: `README.md`)
- Tumor Segmentation → Test Evaluation: evaluated on test set (evidence: `README.md`)
- Tumor Segmentation → Tumor Quantification: measured for size (evidence: `README.md`)
- Tumor Quantification → Research Risk Score: informs score (evidence: `README.md`)
- Tumor Segmentation → 3D Visualization: overlaid in (evidence: `README.md`)
- 3D Visualization → Patient 3D Report: renders report (evidence: `README.md`)
- Research Risk Score → Patient 3D Report: included in (evidence: `README.md`)
- Research User → Sliding-Window Inference: requests patient prediction (evidence: `README.md`)
- Sliding-Window Inference → Validation Batch Prediction: used for batch prediction (evidence: `README.md`)
- Validation Batch Prediction → Prediction and Metric Files: writes NIfTIs (evidence: `README.md`)
- Test Evaluation → Prediction and Metric Files: produces metrics (evidence: `README.md`)
- Patient 3D Report → Prediction and Metric Files: exports reports (evidence: `README.md`)
