Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/chfc-cmi/transversal-cmr-seg

Experiments into segmentation of transversal slices of cardiac MR images

https://github.com/chfc-cmi/transversal-cmr-seg

Science Score: 13.0%

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

  • ○
    CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (2.8%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Experiments into segmentation of transversal slices of cardiac MR images

Basic Info
  • Host: GitHub
  • Owner: chfc-cmi
  • License: mit
  • Language: Python
  • Default Branch: master
  • Size: 8.79 KB
Statistics
  • Stars: 0
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 5 years ago · Last pushed about 4 years ago

https://github.com/chfc-cmi/transversal-cmr-seg/blob/master/ 

# Transversal CMR Segmentation
Experiments into segmentation of transversal slices of cardiac MR images

## Initial model
Trained using fastai v1 on 138 images (90 training, 48 validation) from 6 volunteers. Classes to predict were left ventricular cavity and left ventricular myocardium.

The provided model file (see release page) `b0_transversal_5_5.pth` is the base model from
> A Deep Learning Based Cardiac Cine Segmentation Framework for Clinicians - Transfer Learning Application to 7T Markus J Ankenbrand, David Lohr, Wiebke Schltelburg, Theresa Reiter, Tobias Wech, Laura Maria Schreiber medRxiv 2020.06.15.20131656; doi: https://doi.org/10.1101/2020.06.15.20131656

trained for 5 epochs frozen (max_lr=1e-3) and 5 epochs unfrozen (max_lr=1e-4)

Owner

  • Name: Cellular and Molecular Imaging - Comprehensive Heart Failure Center - University Hospital Würzburg
  • Login: chfc-cmi
  • Kind: organization
  • Location: Am Schwarzenberg 15, 97078 Würzburg, Germany

GitHub Events

Total
Last Year