Automated Assessment of Epicardial Adipose Tissue Using Deep Learning
Author Information
Author(s): Theis Maike, Garajová Laura, Salam Babak, Nowak Sebastian, Block Wolfgang, Attenberger Ulrike I., Kütting Daniel, Luetkens Julian A., Sprinkart Alois M.
Primary Institution: University Hospital Bonn, Bonn, Germany
Hypothesis
Can deep learning methods provide a robust automatic assessment of epicardial adipose tissue in CT scans?
Conclusion
The study presents a method for automatic assessment of epicardial adipose tissue in CT scans, which could enhance clinical evaluations.
Supporting Evidence
- Deep learning methods for automatic assessment of epicardial adipose tissue (EAT) have great potential.
- A 2-step approach with slice extraction and tissue segmentation enables robust automated evaluation of EAT.
- End-to-end automation enables large-scale research on the value of EAT for outcome analysis.
Takeaway
This study shows that computers can help doctors quickly measure fat around the heart using special pictures from CT scans.
Methodology
The study used deep learning models for slice extraction and tissue segmentation on CT scans from patients undergoing TAVR.
Potential Biases
Potential bias due to the dataset being from one center and the exclusion of non-contrast scans.
Limitations
The study was conducted at a single center and only included contrast-enhanced CT scans.
Participant Demographics
Mean age 80.6 years, 47.2% female.
Statistical Information
P-Value
p<0.001
Confidence Interval
[1.6, 2.0]
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website