An automatic segmentation for improved visualization of atrial ablation lesions using magnetic resonance imaging
2011

Automatic Segmentation of Atrial Ablation Lesions Using MRI

Sample size: 5 publication Evidence: moderate

Author Information

Author(s): Karim Rashed, Arujuna Aruna, Gill Jaspal, ONeill Mark, Gill Jaswinder, Razavi Reza, Rueckert Daniel, Schaeffter Tobias, Rhode Kawal

Primary Institution: King's College London

Hypothesis

Can a fully-automated approach improve the segmentation and visualization of atrial ablation lesions in MRI?

Conclusion

The study shows that a fully-automatic method for segmenting and visualizing post-ablation lesions is effective and reduces observer variability.

Supporting Evidence

  • The algorithm segmented scars in less than 30 seconds with no user interaction.
  • The total surface area of scar was computed and represented as a percentage of the atrial surface area.
  • There was good agreement between the results from the novel approach and the expert’s semi-automatic segmentation.

Takeaway

This study created a computer program that quickly finds and shows scars in the heart after surgery, making it easier for doctors to see them without needing to do it by hand.

Methodology

Five patients with paroxysmal AF underwent MRI scans post-ablation, and the endocardial cavity was segmented using a fully-automated algorithm.

Participant Demographics

5 patients with paroxysmal atrial fibrillation, average age 55 years, 2 male.

Statistical Information

P-Value

0.36

Statistical Significance

p=0.36

Digital Object Identifier (DOI)

10.1186/1532-429X-13-S1-P251

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication