Deep learning-based segmentation
Deep learning-based segmentation has been studied in 1 paper since 2024: 1 observational study in people. The newest paper, May 22, 2024: “Development and validation of a reliable method for automated measurements of psoas muscle volume in CT scans using deep learning-based segmentation: a cross-sectional study”.
1 paper studies it2 findingsUpdated
- Humans1
What did studies of Deep learning-based segmentation find?
1Studies of Deep learning-based segmentation measured 1 outcome; the most studied are measurement time (1 study).
Measurement time
downin silico1
1 study
Measurement time
downin silico1
Deep learning-based segmentation decreases measurement time in silico (48 times shorter).
“Our automated segmentation system had an average measurement time of 2 min 20 s ± 20 s, which was 48 times shorter than that of the manual measurement method”
In silicon = 520
BMJ open
What is Deep learning-based segmentation linked with?
1Studies link Deep learning-based segmentation with 1 measure, most often Dice similarity coefficient (1 study).
Dice similarity coefficient
upin silico1
1 study
Dice similarity coefficient
upin silico1
Deep learning-based segmentation is associated with Dice similarity coefficient in silico (0.927 ± 0.019).
“The Dice similarity coefficient was used to compare the manual segmentation with automated segmentation; an average Dice score of 0.927 ± 0.019 was obtained, with no critical outliers.”
In silicon = 520
BMJ open