This repository contains code for extracting the raw optical coherence tomography (OCT) and fundus data from manufacturer's proprietary file formats.
Research in ophthalmology is often hindered by manufacturer's usage of proprietary data formats for storing their data. For example, until recently, the ~200,000 OCT scans in the UK Biobank project was only available in Topcon's .fds file format, which prevented bulk processing and analysis. The only freely available software that allows these scans to be accessed is uocte, which is written in C++ and is no longer maintained. This repository aims to make available python-based tools for reading these proprietary formats.
- .fds (Topcon)
- .fda (Topcon)
- .e2e (Heidelberg)
- .img (Zeiss)
- .dcm
Requires python3.
To install run:
git clone https://github.com/marksgraham/OCT-Converter.git
pip install -e OCT-Converter
Alternate to build and install a python wheel:
git clone https://github.com/marksgraham/OCT-Converter.git
cd OCT-Converter
python setup.py bdist_wheel
pip install dist/*.whl
Example usage scripts are included in examples/.
Are welcome!
30 October 2020
- Extract fundus and laterality data from .e2e
- Now attempts to extract additional volumetric data from .e2e files that was previously missed
22 August 2020
- Experimental support for reading OCT data from .fda files.
14 July 2020
- Can now read fundus data from .fda files.