This project was realized within the framework of the end of studies project aiming at obtaining the diploma of engineer in applied data processing. In this context, the main idea of this project is to develop a medical image processing library using a service-oriented architecture.
- Clone the repo
$ git clone https://github.com/HamzaGbada/dicomPreProcess.git
- Docker Build Image
$ docker build -t dicomPreProcess .
Once done, run the Docker image and map the port to whatever you wish on your host to test the web dashbord. In this example, we simply map port 5000 of the host to port 5000 of the Docker:
$ docker run -d -p 5000:5000 --name dicomImage dicomPreProcess -dVerify the deployment by navigating to your server address in your preferred browser (or you can use Postman to test API).
127.0.0.1:5000To test the implemented algorithms separately:
$ docker exec -it dicomImage /bin/bash$ python run.py -h
usage: run.py [-h] [-a ALGORITHM] [-m METHOD] -f FILE
Description of your Dicom PreProcess
optional arguments:
-h, --help show this help message and exit
-a ALGORITHM, --algorithm ALGORITHM
Choose the algorithm to use. It can be "grail" or "fedbs"
-m METHOD, --method METHOD
Choose the method to use. It can be "dog", "log" or "bbp". This command is validated if and only if the "fedbs" algorithm is chosen
-f FILE, --file FILE Choose the DICOM file path to be processed by default the file is located "data/"
For exemple if you want to test FEDBS algorithm for micro-calcification detection on the file 20587054.dcm:
$ python run.py -a fedbs -m dog -f 20587054.dcm
Distributed under the MIT License. See LICENSE for more information.
Your Name - Hamza Gbada
Project Link: HamzaGbada/dicomPreProcess