Skip to content

An open-source, flexible, plug-and-play inline CMR segmentation platform for the rapid deployment of ML models into the clinical workflow.

Notifications You must be signed in to change notification settings

HMS-CardiacMR/CineROI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

An Open-source, Flexible, Plug-and-Play Inline CMR Image Segmentation Platform

Plug-and-play Inline CMR Image Segmentation Platform

This platform facilitates the rapid development and evaluation of any segmentation algorithm in a transparent and reproducible fashion. An open-source, flexible, plug-and-play inline CMR segmentation platform will enable rapid testing and evaluation of new segmentation and analysis algorithms.

Contours Produced Using Automatic Segmentation

Animation summary of Lethe system.

Code

The code in this repository is broken up into two implementations:

  • Segmentation Only: The code for deploying the segmentation model (CarSON) only is located the fire_deployment directory. It contains the model used to segment a SAX cine and the necessary dependencies. It expects to take in fully reconstructed cine images as input.

  • Reconstruction and Segmentation: The code for deploying the resolution enhancement generative adversarial inline neural network (REGAIN) for accelerated cardiac cine combined with the segmentation model (CarSON) is located in the regain_carson directory. It expects to take undersampled k-space data as input.

About

An open-source, flexible, plug-and-play inline CMR segmentation platform for the rapid deployment of ML models into the clinical workflow.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published