AutoMorph - GitLite

KO | EN

gitlite — search

#react #ai #llm #golang #go #rust #deep-learning #linux #docker #java #windows #cli #pytorch #security

AutoMorph

(★ 166)

vessel segmentation, artery and vein, optic disc, vascular feature analysis

File Explorer

Download Latest Version (.zip)

- launch.json
- 1.png
- 100.png
- 11.png
- __init__.py
- EyeQ_process_main.py
- fundus_prep.py
- - results_ensemble.csv
- dataset.py
- merge_quality_assessment.py
- model.py
- test_outside.py
- test_outside.sh
- - dataset.py
  - model.py
  - utils.py
- FD_cal.py
- test_outside.py
- test_outside.sh
- - fig2.png
  - get_model.py
  - res_unet_adrian.py
- - evaluation.py
  - get_loaders.py
  - get_loaders_backup.py
  - model_saving_loading.py
  - paired_transforms_tv04.py
  - reproducibility.py
- generate_av_results.py
- test_outside.sh
- dataset.py
- FD_cal.py
- model.py
- test_outside.sh
- test_outside_integrated.py
- utils.py
- - settings.json
- - create_datasets_disc_centred.py
  - create_datasets_macular_centred.py
  - roi_tortuosity.py
  - setup.py
- .codecov.yml
- .travis.yml
- LICENSE.md
- - settings.json
- - create_datasets.py
  - create_datasets_disc_centred_B.py
  - create_datasets_disc_centred_C.py
  - create_datasets_macular_centred_B.py
  - create_datasets_macular_centred_C.py
  - roi_tortuosity.py
  - setup.py
- .codecov.yml
- .travis.yml
- LICENSE.md
.gitignore
automorph_data.py
csv_merge.py
DOCKER.md
generate_resolution.py
LICENSE
LOCAL.md
README.md
requirement.txt
resolution_information.csv
run.sh

# Installation Guide

1. Get the code

git clone https://github.com/rmaphoh/AutoMorph

Downloads the entire project code from GitHub to your computer.

cd AutoMorph

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

⚠️ This is a large repository, so this method may point to an internal sub-package rather than the actual core product. Check the full README as well.

pip install .

Installs the package published on PyPI directly — no need to clone the source.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

Runs the Python script (or module).

✅ If it runs without errors and prints output in the terminal, it worked.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# AutoMorph 2022 👀
--Code for [AutoMorph: Automated Retinal Vascular Morphology Quantification via a Deep Learning Pipeline](https://tvst.arvojournals.org/article.aspx?articleid=2783477).

Please contact 	**ykzhoua@gmail.com** or **yukun.zhou.19@ucl.ac.uk** if you have questions.

Project website: https://rmaphoh.github.io/projects/automorph.html

Talks on NIHR Moorfields BRC: https://moorfieldsbrc.nihr.ac.uk/case-study/research-report/

## News 👀
2025-05-16 update: Docker and its instruction have been updated.

2024-06-27 update: pytorch 2.3 & python 3.11 supported; Mac M2 GPU supported; CPU supported (thanks to [staskh](https://github.com/staskh))

2023-08-24 update: Added feature measurement for disc-centred images; removed unused files.
&nbsp;

## Pixel resolution

The units for vessel average width, disc/cup height and width, and calibre metrics are defined as microns. For it, we need to organise a [resolution_information.csv](https://github.com/rmaphoh/AutoMorph/blob/main/resolution_information.csv) which includes the pixel resolution information, which can be queried in FDA or Dicom files. Alternatively, approximate value can be used, e.g., 0.008 for Topcon 3D-OCT.

**If you don't use these features or care their units**, you can put all images in the folder ./images and run

```bash
python generate_resolution.py
```
&nbsp;

## Running AutoMorph
### Running with Colab

Use the Google Colab and a free Tesla T4 gpu [Colab link click](https://colab.research.google.com/drive/13Qh9umwRM1OMRiNLyILbpq3k9h55FjNZ?usp=sharing).

👀 A specific version for [APTOSxJSAIO 2025 hands-on tutorial](https://colab.research.google.com/drive/1ppzxBElLa_yJl-V3IWKyQQDG_2m6OWVL#scrollTo=vnEudwJimFgt)

### Running on local/virtual machine

Install and use on your own machines [LOCAL.md](LOCAL.md).

### Running with Docker

Zero experience in Docker? No worries [DOCKER.md](DOCKER.md).

&nbsp;

## Common questions

### Memory/ram error

We use Tesla T4 (16Gb) and 32vCPUs (120Gb). When you meet memory/ram issue in running, try to decrease batch size:

* ./M1_Retinal_Image_quality_EyePACS/test_outside.sh -b=64 to smaller, e.g., 32 or 16.
* ./M2_Artery_vein/test_outside.sh --batch-size=8 to smaller
* ./M2_lwnet_disc_cup/test_outside.sh --batchsize=8 to smaller

### Invalid results

In csv files, invalid values (e.g., optic disc segmentation failure) are indicated with NAN values.

### Components

1. Vessel segmentation [BF-Net](https://github.com/rmaphoh/Learning-AVSegmentation.git)

2. Image pre-processing [EyeQ](https://github.com/HzFu/EyeQ.git)

3. Optic disc segmentation [lwnet](https://github.com/agaldran/lwnet.git)

4. Feature measurement [retipy](https://github.com/alevalv/retipy.git)

&nbsp;

## Citation

```
@article{zhou2022automorph,
  title={AutoMorph: Automated Retinal Vascular Morphology Quantification Via a Deep Learning Pipeline},
  author={Zhou, Yukun and Wagner, Siegfried K and Chia, Mark A and Zhao, An and Xu, Moucheng and Struyven, Robbert and Alexander, Daniel C and Keane, Pearse A and others},
  journal={Translational vision science \& technology},
  volume={11},
  number={7},
  pages={12--12},
  year={2022},
  publisher={The Association for Research in Vision and Ophthalmology}
}
```