Key result
The proposed 3D convolutional neural network (DCNet) achieved highly accurate whole-body adipose tissue segmentation with a Dice overlap of 0.94, significantly outperforming a standard 3D UNet.
Why the study?
Fast, reliable automatic segmentation of adipose tissue into subcutaneous and visceral compartments from whole-body MRI is needed to examine metabolic conditions and identify individuals at increased risk.
Does a 3D convolutional neural network (DCNet) improve the automated segmentation of adipose tissue compartments in whole-body MRI compared to 3D UNet?
Does a 3D convolutional neural network (DCNet) improve the automated segmentation of adipose tissue compartments in whole-body MRI compared to 3D UNet?
Answers are grounded in this paper and cite their sources.
A 3D convolutional neural network (DCNet) enables fast and highly accurate automated segmentation of subcutaneous and visceral adipose tissue from whole-body MRI across diverse epidemiological cohorts.
Purpose: To enable fast and reliable assessment of subcutaneous and visceral adipose tissue compartments derived from whole-body MRI. Methods: Quantification and localization of different adipose tissue compartments from whole-body MR images is of high interest to examine metabolic conditions. For correct identification and phenotyping of individuals at increased risk for metabolic diseases, a reliable automatic segmentation of adipose tissue into subcutaneous and visceral adipose tissue is required. In this work we propose a 3D convolutional neural network (DCNet) to provide a robust and objective segmentation. In this retrospective study, we collected 1000 cases (66± 13 years; 523 women) from the Tuebingen Family Study and from the German Center for Diabetes research (TUEF/DZD), as well as 300 cases (53± 11 years; 152 women) from the German National Cohort (NAKO) database for model training, validation, and testing with a transfer learning between the cohorts. These datasets had variable imaging sequences, imaging contrasts, receiver coil arrangements, scanners and imaging field strengths. The proposed DCNet was compared against a comparable 3D UNet segmentation in terms of sensitivity, specificity, precision, accuracy, and Dice overlap. Results: Fast (5-7seconds) and reliable adipose tissue segmentation can be obtained with high Dice overlap (0.94), sensitivity (96.6%), specificity (95.1%), precision (92.1%) and accuracy (98.4%) from 3D whole-body MR datasets (field of view coverage 450x450x2000mm³). Segmentation masks and adipose tissue profiles are automatically reported back to the referring physician. Conclusion: Automatic adipose tissue segmentation is feasible in 3D whole-body MR data sets and is generalizable to different epidemiological cohort studies with the proposed DCNet.
No takes yet. Share an insight, caveat, or question.
Küstner et al. (2020) studied Adipose tissue distribution (n=1,300). 3D convolutional neural network (DCNet) vs. 3D UNet segmentation was evaluated on Dice overlap for adipose tissue segmentation (p=<0.001). The proposed 3D convolutional neural network (DCNet) achieved highly accurate whole-body adipose tissue segmentation with a Dice overlap of 0.94, significantly outperforming a standard 3D UNet.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: