Evaluating Sex-specific Differences in Abdominal Fat Volume and Proton Density Fat Fraction on MRI Scans Using Automated nnU-Net-based Segmentation.
Arun SomasundaramMingming WuAnna ReikSelina RuppJessie HanStella NaebauerDaniela JunkerLisa PatzeltMeike WiechertYu ZhaoDaniel RuckertHans HaunerChristina HolzapfelDimitrios C KarampinosPublished in: Radiology. Artificial intelligence (2024)
"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence . This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Sex-specific abdominal organ volume and proton density fat fraction (PDFF) in people with obesity during a weight loss intervention was assessed using automated multiorgan segmentation of quantitative water-fat MRI. An nnU-Net architecture was employed for automatic segmentation of abdominal organs, including visceral (VAT) and subcutaneous adipose tissue (SAT), liver, psoas and erector spinae muscle, based on quantitative chemical shiftencoded MRI and using ground truth labels generated from participants of the Lifestyle Intervention (LION) study. Each organ's volume and fat content were examined in 127 participants (73 female, 54 male; body mass index, 30-39.9 kg/m 2 ) and in 81 participants (54 female, 32 male) of these after an 8-week formula-based low-calorie diet. Dice scores ranging from 0.91 to 0.97 were achieved for the automatic segmentation. PDFF was found to be lower in VAT compared with SAT in both male and female participants. Before intervention, females exhibited higher PDFF in SAT (90.6% versus 89.7%, P < .001) and lower PDFF in liver (8.6% versus 13.3%, P < .001) and VAT (76.4% versus 81.3%, P < .001) compared with males. This relation persists after intervention. As a response to caloric restriction, male participants lost significantly more VAT volume (1.76 L versus 0.91 L, P < .001) and showed a higher decrease in SAT PDFF (2.7% versus 1.5%, P < .001) than female participants. Automated body composition analysis on quantitative water-fat MRI data provides new insights for understanding sex-specific metabolic response to caloric restriction and weight loss in people with obesity. Published under a CC BY 4.0 license.
Keyphrases
- deep learning
- weight loss
- adipose tissue
- artificial intelligence
- machine learning
- insulin resistance
- convolutional neural network
- body composition
- bariatric surgery
- randomized controlled trial
- contrast enhanced
- magnetic resonance imaging
- roux en y gastric bypass
- big data
- body mass index
- metabolic syndrome
- fatty acid
- weight gain
- gastric bypass
- physical activity
- type diabetes
- high throughput
- high fat diet
- skeletal muscle
- computed tomography
- diffusion weighted imaging
- high resolution
- cardiovascular disease
- clinical trial
- pain management
- obese patients
- ultrasound guided
- mass spectrometry
- resistance training
- systematic review
- psychometric properties
- chronic pain
- preterm infants
- patient safety
- double blind
- adverse drug