https://github.com/anwai98/chest-ct-reg

Image Registration on Chest CT Volumes
https://github.com/anwai98/chest-ct-reg

chest copd ct deep-learning elastix transformix voxelmorph

Last synced: over 1 year ago
JSON representation

Image Registration on Chest CT Volumes

• Host: GitHub
• URL: https://github.com/anwai98/chest-ct-reg
• Owner: anwai98
• Created: 2022-03-20T12:47:25.000Z (over 4 years ago)
• Default Branch: main
• Last Pushed: 2022-03-21T21:28:35.000Z (over 4 years ago)
• Last Synced: 2024-10-20T14:28:41.242Z (almost 2 years ago)
• Topics: chest, copd, ct, deep-learning, elastix, transformix, voxelmorph
• Language: Jupyter Notebook
• Homepage:
• Size: 355 KB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Chest-CT-Reg

Image Registration on Chest CT Volumes

Dataset used - COPDgene (Castillo, Richard et al. “A reference dataset for deformable image registration spatial accuracy evaluation using the COPDgene study archive.” Physics in medicine and biology vol. 58,9 (2013): 2861-77. doi:10.1088/0031-9155/58/9/2861)

How to play with the codes?

1. Follow the steps for the Classical Registration Pipeline Step-Wise. There are a few details to take care of in the dataset.

2. Use the DICOM Files to train the Voxelmoprh Deep Learning Pipeline, and obtain the result and calculate the TRE in both the aforementioned pipelines.

> Note : Comments are provided for explanation (almost). For more information, contact me!

## Qualitative Results

![image](https://user-images.githubusercontent.com/52396323/159360615-e80faa6e-04b6-42d0-ad40-8a85d1e790bb.png)

## Challenge Results (MAIA - 3rd Semester)

Our method was the fastest and had the best results (Ranked 1st) in the Subject MIRA - Medical Image Registration and Applications.