This repository contains an extended version of the source code corresponding to the paper "Learning deformable registration of medical images with anatomical constraints" (Neural Networks, 2020). You can check out our paper here: https://arxiv.org/abs/2001.07183.
This project uses Python 3.8.10 and PyTorch 1.10.1.
python3 -m venv env
, 2) source env/bin/activate
pip install -r requirements.txt
pip install -e .
./01_run_aenet.sh
./02_run_acregnet.sh
In both scenarios, by editing the variable named DATASET
you can choose the input dataset: JSRT, Montgomery or Shenzhen.
A command line tool for chest x-ray image registration is also provided. Here's an example of how to use it:
acregnet --mov JPCLN001.png --fix JPCLN002.png --model results/JSRT/ACRegNet/train/model.pt --dst output
Anatomical segmentation masks produced with a Multi-atlas segmentation model and AC-RegNet: https://github.com/lucasmansilla/NIH_chest_xray14_segmentations.