Prakash Kn Bhanu1, Channarayapatna Srinivas Arvind2, Ling Yun Yeow2, Wen Xiang Chen3, Wee Shiong Lim4, Cher Heng Tan3. 1. Signal and Image Processing Group, Institute of Bioengineering and Bioimaging, 02-02, Helios,11, Biopolis Way, Singapore, 138667, Singapore. bhanu@ibb.a-star.edu.sg. 2. Signal and Image Processing Group, Institute of Bioengineering and Bioimaging, 02-02, Helios,11, Biopolis Way, Singapore, 138667, Singapore. 3. Department of Diagnostic Radiology, Tan Tock Seng Hospital, 11 Jln Tan Tock Seng, Singapore, 308433, Singapore. 4. Department of Geriatric Medicine, Tan Tock Seng Hospital, 11 Jln Tan Tock Seng, Singapore, 308433, Singapore.
Abstract
BACKGROUND: There is increasing appreciation of the association of obesity beyond co-morbidities, such as cancers, Type 2 diabetes, hypertension, and stroke to also impact upon the muscle to give rise to sarcopenic obesity. Phenotypic knowledge of obesity is crucial for profiling and management of obesity, as different fat-subcutaneous adipose tissue depots (SAT) and visceral adipose tissue depots (VAT) have various degrees of influence on metabolic syndrome and morbidities. Manual segmentation is time consuming and laborious. Study focuses on the development of a deep learning-based, complete data processing pipeline for MRI-based fat analysis, for large cohort studies which include (1) data augmentation and preprocessing (2) model zoo (3) visualization dashboard, and (4) correction tool, for automated quantification of fat compartments SAT and VAT. METHODS: Our sample comprised 190 healthy community-dwelling older adults from the Geri-LABS study with mean age of 67.85 ± 7.90 years, BMI 23.75 ± 3.65 kg/m2, 132 (69.5%) female, and mainly Chinese ethnicity. 3D-modified Dixon T1-weighted gradient-echo MR images were acquired. Residual global aggregation-based 3D U-Net (RGA-U-Net) and standard 3D U-Net were trained to segment SAT, VAT, superficial and deep subcutaneous adipose tissue depots (SSAT and DSAT). Manual segmentation from 26 subjects was used as ground truth during training. Data augmentations, random bias, noise and ghosting were carried out to increase the number of training datasets to 130. Segmentation accuracy was evaluated using Dice and Hausdorff metrics. RESULTS: The accuracy of segmentation was SSAT:0.92, DSAT:0.88 and VAT:0.9. Average Hausdorff distance was less than 5 mm. Automated segmentation significantly correlated R2 > 0.99 (p < 0.001) with ground truth for all 3-fat compartments. Predicted volumes were within ± 1.96SD from Bland-Altman analysis. CONCLUSIONS: DL-based, comprehensive SSAT, DSAT, and VAT analysis tool showed high accuracy and reproducibility and provided a comprehensive fat compartment composition analysis and visualization in less than 10 s.
BACKGROUND: There is increasing appreciation of the association of obesity beyond co-morbidities, such as cancers, Type 2 diabetes, hypertension, and stroke to also impact upon the muscle to give rise to sarcopenic obesity. Phenotypic knowledge of obesity is crucial for profiling and management of obesity, as different fat-subcutaneous adipose tissue depots (SAT) and visceral adipose tissue depots (VAT) have various degrees of influence on metabolic syndrome and morbidities. Manual segmentation is time consuming and laborious. Study focuses on the development of a deep learning-based, complete data processing pipeline for MRI-based fat analysis, for large cohort studies which include (1) data augmentation and preprocessing (2) model zoo (3) visualization dashboard, and (4) correction tool, for automated quantification of fat compartments SAT and VAT. METHODS: Our sample comprised 190 healthy community-dwelling older adults from the Geri-LABS study with mean age of 67.85 ± 7.90 years, BMI 23.75 ± 3.65 kg/m2, 132 (69.5%) female, and mainly Chinese ethnicity. 3D-modified Dixon T1-weighted gradient-echo MR images were acquired. Residual global aggregation-based 3D U-Net (RGA-U-Net) and standard 3D U-Net were trained to segment SAT, VAT, superficial and deep subcutaneous adipose tissue depots (SSAT and DSAT). Manual segmentation from 26 subjects was used as ground truth during training. Data augmentations, random bias, noise and ghosting were carried out to increase the number of training datasets to 130. Segmentation accuracy was evaluated using Dice and Hausdorff metrics. RESULTS: The accuracy of segmentation was SSAT:0.92, DSAT:0.88 and VAT:0.9. Average Hausdorff distance was less than 5 mm. Automated segmentation significantly correlated R2 > 0.99 (p < 0.001) with ground truth for all 3-fat compartments. Predicted volumes were within ± 1.96SD from Bland-Altman analysis. CONCLUSIONS: DL-based, comprehensive SSAT, DSAT, and VAT analysis tool showed high accuracy and reproducibility and provided a comprehensive fat compartment composition analysis and visualization in less than 10 s.
Authors: Chin Meng Khoo; Melvin Khee-Shing Leow; Suresh Anand Sadananthan; Radiance Lim; Kavita Venkataraman; Eric Yin Hao Khoo; S Sendhil Velan; Yu Ting Ong; Ravi Kambadur; Craig McFarlane; Peter D Gluckman; Yung Seng Lee; Yun Seng Lee; Yap Seng Chong; E Shyong Tai Journal: Diabetes Date: 2013-12-18 Impact factor: 9.461
Authors: Dennis T Villareal; Lina Aguirre; A Burke Gurney; Debra L Waters; David R Sinacore; Elizabeth Colombo; Reina Armamento-Villareal; Clifford Qualls Journal: N Engl J Med Date: 2017-05-18 Impact factor: 91.245