Cross-cohort federated learning for pediatric abdominal adipose tissue segmentation and quantification using
Wenwen Zhang1,2, Sevgi Gokce Kafali1,3, Timothy Adamos4
1Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, 90095, United States.
Insights
Federated learning accurately segments pediatric visceral and subcutaneous adipose tissue (VAT, SAT) using MRI, improving metabolic disease risk assessment. This rapid method leverages adult data without sharing, enhancing pediatric imaging analysis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Pediatric Health
Background:
- Pediatric abdominal adipose tissue (visceral and subcutaneous) quantification via MRI aids metabolic disease risk assessment.
- Automated segmentation of pediatric visceral adipose tissue (VAT) is challenging due to its complex structure and limited MRI datasets.
Purpose of the Study:
- Develop a cross-cohort federated learning (FL) framework to enable accurate and rapid automated segmentation of pediatric abdominal VAT and SAT.
- Utilize adult MRI datasets to enhance the performance of pediatric segmentation models.
Main Methods:
- Trained 3D neural network models on pediatric and adult 3D free-breathing (FB) Dixon MRI datasets using a federated learning approach.
- Assessed segmentation performance using Dice scores and compared FL models against standalone and joint training methods.
- Evaluated VAT and SAT volume and proton-density fat fraction (PDFF) quantification using intraclass correlation coefficients (ICCs) and Bland-Altman analysis.
Main Results:
- The FL model achieved high segmentation accuracy (VAT: 91.09%, SAT: 95.55%), outperforming standalone training and matching joint training performance.
- Volume quantification showed strong agreement (VAT: ICC=0.99, SAT: ICC=1.00) between FL and reference methods.
- Inference time for segmentation was under 3 seconds per subject, demonstrating rapid analysis capabilities.
Conclusions:
- The federated learning framework enables accurate and rapid automated segmentation of pediatric abdominal VAT and SAT on 3D FB-MRI.
- This approach effectively leverages larger adult datasets to improve pediatric imaging analysis without compromising data privacy.
- The method holds promise for enhanced risk assessment of metabolic diseases in children through improved adipose tissue quantification.
Background:
Pediatric abdominal visceral and subcutaneous adipose tissue (VAT, SAT) quantified on magnetic resonance imaging (MRI) can assess risk for metabolic diseases. However, the complex structure of VAT in children and the lack of sufficient MRI datasets pose challenges for developing automated segmentation methods.
Purpose:
To achieve accurate and rapid automated segmentation of pediatric abdominal VAT and SAT on motion-robust free-breathing (FB) 3D Dixon MRI by developing a cross-cohort federated learning (FL) framework that leverages adult datasets.
Materials And Methods:
3D FB-MRI datasets were prospectively acquired in children 6-18 years old (single center, 2 scanners; 2016-2023) and used to train 3D neural network models for segmenting abdominal VAT and SAT. The FL model was trained across the pediatric cohort and a separate adult cohort (5 centers, 7 scanners) without requiring direct data sharing. Segmentation performance of the FL model was assessed by Dice scores with respect to references and compared with standalone local training and joint training with full data access. Quantification of VAT and SAT volume and proton-density fat fraction (PDFF) was compared against references using intraclass correlation coefficients (ICCs) and Bland-Altman analysis. Differences between training approaches were analyzed using the Kruskal-Wallis test followed by paired Wilcoxon signed-rank tests.
Results:
The FL model, trained and tested with 134 children (mean age, 13.3 years ± 2.7 [standard deviation]; 71 males) and 920 adults (50.4 years ± 14.0; 677 females), achieved mean Dice scores of 91.09% (VAT) and 95.55% (SAT), outperforming standalone training (VAT: P < .001) and performing comparably to joint training (VAT: P = .21). Volume quantification demonstrated strong agreement (VAT: ICC = 0.99, SAT: ICC = 1.00). PDFF quantification showed small mean differences (VAT: 0.21%, SAT: -1.19%). Inference time was <3 seconds for each subject.
Conclusion:
The proposed FL framework achieved accurate and rapid automated segmentation and quantification of pediatric abdominal VAT and SAT on 3D FB-MRI.
