Key result
Deep learning accurately segments abdominal adipose tissue on MRI, achieving ~97% accuracy for subcutaneous fat.
Why the study?
The study was conducted to validate a deep learning-based vision transformer for automated quantification and segmentation of abdominal adipose tissue from T1-weighted MRI.
Does a deep learning-based vision transformer accurately segment abdominal subcutaneous and visceral fat on MRI compared to manual expert annotation in midlife adults?
Does a deep learning-based vision transformer accurately segment abdominal subcutaneous and visceral fat on MRI compared to manual expert annotation in midlife adults?
Answers are grounded in this paper and cite their sources.
A deep learning-based vision transformer accurately segments abdominal subcutaneous and visceral fat on T1-weighted MRI, providing a reliable tool for large-scale investigations of adiposity.
The purpose of this study is to validate a deep learning-based vision transformer for automated quantification and segmentation of abdominal adipose tissue from T1-weighted MRI. This study included abdominal T1 MRI volumes from 107 participants (mean age, 49.9 years; 35 males, 72 females; BMI range, 18.2-49.6) who were midlife adults enrolled in a prospective study assessing the link between abdominal adiposity and biomarkers of dementia. For each abdominal image, visceral and subcutaneous adipose tissues were annotated by an expert reader as the ground truth. Inter- and intra-reader reliability were assessed to establish ground truth validity. A deep learning-based vision transformer was trained using a fivefold cross-validation scheme, and its performance was evaluated using various segmentation metrics against the manually annotated ground truths. The SwinUNETR48 model achieved average Dice coefficients of 96.56% ± 2.38% (p < .001) for SAT and 88.35% ± 8.82% (p < .001) for VAT in cross-validation. The model generalized well to different adiposity and body sizes within the abdominal cavity. Automated segmentation of abdominal adipose tissue provides a promising option for facilitating large-scale investigation of abdominal fat distribution on MRI.
No takes yet. Share an insight, caveat, or question.
Kassani et al. (2026) studied Abdominal adiposity (n=107). Deep learning-based vision transformer (SwinUNETR48) vs. Manual expert annotation was evaluated on Segmentation accuracy (Dice coefficients) for subcutaneous and visceral adipose tissue (p=<.001). A deep learning-based vision transformer accurately segmented abdominal adipose tissue on MRI, achieving average Dice coefficients of 96.56% for subcutaneous and 88.35% for visceral fat.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: