Data

Tools

Indexes

Applications

Experiments

Open Source Science

ct-to-synthetic-mri-generation

This repository collates the models for CT to MRI synthesis. MRIs have benefits over CTs: they have better soft tissue contrast and registration of brain scans is often done to an MRI atlas.

https://github.com/jakemcnaughton/ct-to-synthetic-mri-generation

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: mdpi.com
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

This repository collates the models for CT to MRI synthesis. MRIs have benefits over CTs: they have better soft tissue contrast and registration of brain scans is often done to an MRI atlas.

Basic Info
  • Host: GitHub
  • Owner: jakemcnaughton
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 1.18 MB
Statistics
  • Stars: 17
  • Watchers: 1
  • Forks: 3
  • Open Issues: 0
  • Releases: 0
Created over 3 years ago · Last pushed about 1 year ago
Metadata Files
Readme Citation

README.md

Synthetic Brain MRI Generation from CT Scans Using Deep Learning

This repository collates the models developed in our paper in which we use CNNs to translate CTs to MRIs for stroke patients. MRIs have specific benefits over CTs: they have better contrast and detail of soft tissue and lesions and registration of brain scans is often registered to an MRI atlas, making an MRI the preferable model to have available. See our recent review to compare different types of medical image generation.

How to Use this Repo

There are 8 different architectures in the Models folder. To run a model, first select if you want to run it 3D, 3D patch-based, or 2D. Then select the respective file for running: main3D.py, main_patch.py, main2D.py

Import ONLY the model you want to use.

Preprocessing

We aligned the CT and MRI of each patient together and then aligned everything to the MNI152 atlas before performing brain extraction. alt text

Training

Set Test = False

Select GPUs (export CUDAVISIBLEDEVICES= x, y, z, ...)

Set NAME to the name of your model

Run "python main3D.py"

Testing

Set Test = True

Run "python main3D.py"

Evaluation

"eval.py" calculate SSIM, MAE, MSE, and PSNR over the non-zero pixels of the results.

"toimage.py" lets you save Image slices of your nifti files.

Citing

If you use this code please cite the following papers. bibtex @Article{bioengineering10091078, AUTHOR = {McNaughton, Jake and Fernandez, Justin and Holdsworth, Samantha and Chong, Benjamin and Shim, Vickie and Wang, Alan}, TITLE = {Machine Learning for Medical Image Translation: A Systematic Review}, JOURNAL = {Bioengineering}, VOLUME = {10}, YEAR = {2023}, NUMBER = {9}, ARTICLE-NUMBER = {1078}, URL = {https://www.mdpi.com/2306-5354/10/9/1078}, ISSN = {2306-5354}, DOI = {10.3390/bioengineering10091078} }

bibtex @Article{biomedinformatics3030050, AUTHOR = {McNaughton, Jake and Holdsworth, Samantha and Chong, Benjamin and Fernandez, Justin and Shim, Vickie and Wang, Alan}, TITLE = {Synthetic MRI Generation from CT Scans for Stroke Patients}, JOURNAL = {BioMedInformatics}, VOLUME = {3}, YEAR = {2023}, NUMBER = {3}, PAGES = {791--816}, URL = {https://www.mdpi.com/2673-7426/3/3/50}, ISSN = {2673-7426}, DOI = {10.3390/biomedinformatics3030050} }

Owner

  • Login: jakemcnaughton
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: CT to Synthetic MRI Generation
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Jake
    family-names: McNaughton
    email: jmcn735@aucklanduni.ac.nz
    affiliation: University of Auckland
    orcid: 'https://orcid.org/0000-0002-7423-8113'
repository-code: >-
  https://github.com/jakemcnaughton/CT-to-Synthetic-MRI-Generation/
date-released: '2023-06-03'

GitHub Events

Total
  • Watch event: 9
  • Delete event: 1
  • Push event: 4
  • Pull request event: 2
  • Create event: 1
Last Year
  • Watch event: 9
  • Delete event: 1
  • Push event: 4
  • Pull request event: 2
  • Create event: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 0
  • Total pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: 7 minutes
  • Total issue authors: 0
  • Total pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 1
  • Average time to close issues: N/A
  • Average time to close pull requests: 7 minutes
  • Issue authors: 0
  • Pull request authors: 1
  • Average comments per issue: 0
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
  • jakemcnaughton (1)
Top Labels
Issue Labels
Pull Request Labels