# huilin0220/stenunet architecture

> Architecture diagram of the GitHub repository huilin0220/stenunet, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-19). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/huilin0220/stenunet
- Repository: https://github.com/huilin0220/stenunet

## Overview

StenUNet is a coronary-angiography stenosis segmentation system built on nnU-Net v2. Its documented workflow prepares multiple image modalities, plans and trains a model, then preprocesses test images, predicts segmentations, and postprocesses the results. The repository also contains nnU-Net capabilities for dataset planning, model architectures, evaluation, ensembling, and model sharing. Arrows are limited to relationships shown in the README or source index; several nnU-Net connections remain unverified because their implementation excerpts are incomplete.

Main entry points: [`inference.py`](https://github.com/huilin0220/stenunet/blob/master/inference.py) (Inference entry), [`training.py`](https://github.com/huilin0220/stenunet/blob/master/training.py) (Model training), [`nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py`](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py) (nnU-Net trainer), [`nnunetv2/inference/predict_from_raw_data.py`](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/inference/predict_from_raw_data.py) (Segmentation predictor)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Data preparation"]
  node_rawdata["Raw angiograms"]
  node_customprep["Image preprocessing<br/>[preprocess.py]"]
  node_filters["Image filters<br/>[DDFB.py]"]
end

subgraph group_model["Planning and training"]
  node_trainplan["Training planning"]
  node_training["Model training<br/>[training.py]"]
  node_trainer["nnU-Net trainer<br/>[nnUNetTrainer.py]"]
  node_weights["Model weights"]
end

subgraph group_predict["Prediction workflow"]
  node_inferentry["Inference entry<br/>[inference.py]"]
  node_nnpredict["Segmentation predictor"]
  node_sliding["Sliding-window inference"]
  node_nnpreprocess["Dataset preprocessing"]
  node_postprocess["Small-segment removal"]
  node_results["Prediction results"]
end

subgraph group_nnutils["nnU-Net capabilities"]
  node_planning["Experiment planning"]
  node_datasetprep["Dataset preparation"]
  node_arch["Network architectures<br/>[unet.py]"]
  node_plans["Plan configuration<br/>[plans_handler.py]"]
  node_readers["Image I/O"]
  node_resample["Resampling"]
  node_labels["Label handling<br/>[label_handling.py]"]
  node_eval["Prediction evaluation"]
  node_ensemble["Model ensembling<br/>[ensemble.py]"]
  node_sharing["Model sharing<br/>[entry_points.py]"]
end

node_user(("Dataset user"))

node_user -->|"provides data"| node_rawdata
node_rawdata -->|"preprocessed by"| node_customprep
node_customprep -->|"uses filters"| node_filters
node_user -->|"plans training"| node_trainplan
node_trainplan -.->|"configures"| node_training
node_training -.->|"runs trainer"| node_trainer
node_training -->|"produces weights"| node_weights
node_user -->|"starts inference"| node_inferentry
node_inferentry -->|"preprocesses images"| node_customprep
node_inferentry -->|"requests predictions"| node_nnpredict
node_nnpredict -->|"preprocesses cases"| node_nnpreprocess
node_nnpredict -->|"runs inference"| node_sliding
node_inferentry -->|"loads checkpoint"| node_weights
node_inferentry -->|"postprocesses output"| node_postprocess
node_postprocess -->|"writes results"| node_results
node_datasetprep -->|"plans dataset"| node_planning
node_planning -->|"creates plans"| node_plans
node_planning -->|"selects reader"| node_readers
node_plans -->|"creates label manager"| node_labels
node_plans -->|"configures preprocessing"| node_nnpreprocess
node_nnpreprocess -->|"resamples data"| node_resample
node_trainer -.->|"builds network"| node_arch
node_trainer -->|"evaluates validation"| node_eval
node_user -.->|"evaluates predictions"| node_eval
node_user -.->|"ensembles models"| node_ensemble
node_user -.->|"shares models"| node_sharing

click node_customprep "https://github.com/huilin0220/stenunet/blob/master/pre_process/preprocess.py"
click node_filters "https://github.com/huilin0220/stenunet/blob/master/utils/DDFB.py"
click node_trainplan "https://github.com/huilin0220/stenunet/blob/master/training_planning.py"
click node_training "https://github.com/huilin0220/stenunet/blob/master/training.py"
click node_trainer "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py"
click node_inferentry "https://github.com/huilin0220/stenunet/blob/master/inference.py"
click node_nnpredict "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/inference/predict_from_raw_data.py"
click node_sliding "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/inference/sliding_window_prediction.py"
click node_nnpreprocess "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/preprocessing/preprocessors/default_preprocessor.py"
click node_postprocess "https://github.com/huilin0220/stenunet/blob/master/post_process/remove_small_segments.py"
click node_planning "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/experiment_planning/experiment_planners/default_experiment_planner.py"
click node_datasetprep "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/experiment_planning/plan_and_preprocess_entrypoints.py"
click node_arch "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/dynamic_network_architectures/architectures/unet.py"
click node_plans "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/utilities/plans_handling/plans_handler.py"
click node_readers "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/imageio/reader_writer_registry.py"
click node_resample "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/preprocessing/resampling/default_resampling.py"
click node_labels "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/utilities/label_handling/label_handling.py"
click node_eval "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/evaluation/evaluate_predictions.py"
click node_ensemble "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/ensembling/ensemble.py"
click node_sharing "https://github.com/huilin0220/stenunet/blob/master/nnunetv2/model_sharing/entry_points.py"

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_rawdata,node_customprep,node_filters,node_user toneBlue
class node_trainplan,node_training,node_trainer,node_weights toneAmber
class node_inferentry,node_nnpredict,node_sliding,node_nnpreprocess,node_postprocess,node_results toneMint
class node_planning,node_datasetprep,node_arch,node_plans,node_readers,node_resample,node_labels,node_eval,node_ensemble,node_sharing toneRose
```

## Components

### Data preparation

- **Raw angiograms**
- [Image preprocessing](https://github.com/huilin0220/stenunet/blob/master/pre_process/preprocess.py): `pre_process/preprocess.py`
- [Image filters](https://github.com/huilin0220/stenunet/blob/master/utils/DDFB.py): `utils/DDFB.py`

### Planning and training

- [Training planning](https://github.com/huilin0220/stenunet/blob/master/training_planning.py): `training_planning.py`
- [Model training](https://github.com/huilin0220/stenunet/blob/master/training.py): `training.py`
- [nnU-Net trainer](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py): `nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py`
- **Model weights**

### Prediction workflow

- [Inference entry](https://github.com/huilin0220/stenunet/blob/master/inference.py): `inference.py`
- [Segmentation predictor](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/inference/predict_from_raw_data.py): `nnunetv2/inference/predict_from_raw_data.py`
- [Sliding-window inference](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/inference/sliding_window_prediction.py): `nnunetv2/inference/sliding_window_prediction.py`
- [Dataset preprocessing](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/preprocessing/preprocessors/default_preprocessor.py): `nnunetv2/preprocessing/preprocessors/default_preprocessor.py`
- [Small-segment removal](https://github.com/huilin0220/stenunet/blob/master/post_process/remove_small_segments.py): `post_process/remove_small_segments.py`
- **Prediction results**

### nnU-Net capabilities

- [Experiment planning](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/experiment_planning/experiment_planners/default_experiment_planner.py): `nnunetv2/experiment_planning/experiment_planners/default_experiment_planner.py`
- [Dataset preparation](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/experiment_planning/plan_and_preprocess_entrypoints.py): `nnunetv2/experiment_planning/plan_and_preprocess_entrypoints.py`
- [Network architectures](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/dynamic_network_architectures/architectures/unet.py): `nnunetv2/dynamic_network_architectures/architectures/unet.py`
- [Plan configuration](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/utilities/plans_handling/plans_handler.py): `nnunetv2/utilities/plans_handling/plans_handler.py`
- [Image I/O](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/imageio/reader_writer_registry.py): `nnunetv2/imageio/reader_writer_registry.py`
- [Resampling](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/preprocessing/resampling/default_resampling.py): `nnunetv2/preprocessing/resampling/default_resampling.py`
- [Label handling](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/utilities/label_handling/label_handling.py): `nnunetv2/utilities/label_handling/label_handling.py`
- [Prediction evaluation](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/evaluation/evaluate_predictions.py): `nnunetv2/evaluation/evaluate_predictions.py`
- [Model ensembling](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/ensembling/ensemble.py): `nnunetv2/ensembling/ensemble.py`
- [Model sharing](https://github.com/huilin0220/stenunet/blob/master/nnunetv2/model_sharing/entry_points.py): `nnunetv2/model_sharing/entry_points.py`

### Other components

- **Dataset user**

## Connections

- Dataset user → Raw angiograms: provides data
- Raw angiograms → Image preprocessing: preprocessed by
- Image preprocessing → Image filters: uses filters (evidence: `pre_process/preprocess.py`)
- Dataset user → Training planning: plans training
- Training planning → Model training: configures
- Model training → nnU-Net trainer: runs trainer
- Model training → Model weights: produces weights
- Dataset user → Inference entry: starts inference
- Inference entry → Image preprocessing: preprocesses images (evidence: `inference.py`)
- Inference entry → Segmentation predictor: requests predictions (evidence: `inference.py`)
- Segmentation predictor → Dataset preprocessing: preprocesses cases (evidence: `nnunetv2/inference/predict_from_raw_data.py`)
- Segmentation predictor → Sliding-window inference: runs inference (evidence: `nnunetv2/inference/predict_from_raw_data.py`)
- Inference entry → Model weights: loads checkpoint
- Inference entry → Small-segment removal: postprocesses output (evidence: `inference.py`)
- Small-segment removal → Prediction results: writes results
- Dataset preparation → Experiment planning: plans dataset (evidence: `nnunetv2/experiment_planning/plan_and_preprocess_entrypoints.py`)
- Experiment planning → Plan configuration: creates plans (evidence: `nnunetv2/experiment_planning/experiment_planners/default_experiment_planner.py`)
- Experiment planning → Image I/O: selects reader (evidence: `nnunetv2/experiment_planning/experiment_planners/default_experiment_planner.py`)
- Plan configuration → Label handling: creates label manager (evidence: `nnunetv2/utilities/plans_handling/plans_handler.py`)
- Plan configuration → Dataset preprocessing: configures preprocessing (evidence: `nnunetv2/utilities/plans_handling/plans_handler.py`)
- Dataset preprocessing → Resampling: resamples data (evidence: `nnunetv2/preprocessing/preprocessors/default_preprocessor.py`)
- nnU-Net trainer → Network architectures: builds network
- nnU-Net trainer → Prediction evaluation: evaluates validation (evidence: `nnunetv2/training/nnUNetTrainer/nnUNetTrainer.py`)
- Dataset user → Prediction evaluation: evaluates predictions
- Dataset user → Model ensembling: ensembles models
- Dataset user → Model sharing: shares models
