Key result
Deep learning MRI segmentation cuts processing time to ~15 seconds while maintaining high accuracy.
Why the study?
Volume and distribution of adipose tissue contribute to insulin resistance and metabolic/cardiovascular disease, but feasible large-scale standardized MRI assessment was needed.
Does deep learning-based image segmentation provide robust and fast quantification of adipose tissue from MRI compared to manual processing in a large population-based cohort?
Cohort (n=11,141)
Yes
Does deep learning-based image segmentation provide robust and fast quantification of adipose tissue from MRI compared to manual processing in a large population-based cohort?
Deep learning-based image segmentation provides highly accurate and significantly faster quantification of trunk adipose tissue from MRI compared to manual processing, enabling large-scale cohort analyses.
Supports efficient large-cohort adipose quantification from MRI; leaves open clinical outcome impact.
This research addresses the assessment of adipose tissue (AT) and spatial distribution of visceral (VAT) and subcutaneous fat (SAT) in the trunk from standardized magnetic resonance imaging at 3 T, thereby demonstrating the feasibility of deep learning (DL)-based image segmentation in a large population-based cohort in Germany (five sites). Volume and distribution of AT play an essential role in the pathogenesis of insulin resistance, a risk factor of developing metabolic/cardiovascular diseases. Cross-validated training of the DL-segmentation model led to a mean Dice similarity coefficient of >0.94, corresponding to a mean absolute volume deviation of about 22 ml. SAT is significantly increased in women compared to men, whereas VAT is increased in males. Spatial distribution shows age- and body mass index-related displacements. DL-based image segmentation provides robust and fast quantification of AT (≈15 s per dataset versus 3 to 4 hours for manual processing) and assessment of its spatial distribution from magnetic resonance images in large cohort studies.
No takes yet. Share an insight, caveat, or question.
Haueise et al. (2023) reported a cohort. Deep learning-based image segmentation vs. Manual processing was evaluated on Mean Dice similarity coefficient and processing time. Deep learning-based image segmentation of magnetic resonance images achieved a mean Dice similarity coefficient >0.94 and reduced processing time to ≈15 seconds per dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: