Abstract
Objective
To propose a fully automated algorithm, which is implemented to segment subcutaneous adipose tissue (SAT) and internal adipose tissue (IAT) from the total adipose tissue for whole-body fat distribution analysis using proton density fat fraction (PDFF) magnetic resonance images.
Materials and methods
Adipose tissue segmentation was implemented using the U-Net deep neural network model. All datasets were collected using a 3.0 T magnetic resonance imaging (MRI) scanner for whole-body scan of 20 volunteers covering from neck to knee with about 160 images for each volunteer. PDFF images were reconstructed based on chemical-shift-encoded fat–water imaging. After selecting the representative PDFF images (total 906 images), the manual labeling of the SAT area was used for model training (504 images), validation (168 images), and testing (234 images).
Results
The automatic segmentation model was validated through three indices using the validation and test sets. The dice similarity coefficient, precision rate, and recall rate were 0.976 ± 0.048, 0.978 ± 0.048, and 0.978 ± 0.050, respectively, in both validation and test sets.
Conclusion
The proposed algorithm can reliably and automatically segment SAT and IAT from whole-body MRI PDFF images. The proposed method provides a simple and automatic tool for whole-body fat distribution analysis to explore the relationship between fat deposition and metabolic-related chronic diseases.
Similar content being viewed by others
References
Blüher M (2019) Obesity: global epidemiology and pathogenesis. Nat Rev Endocrinol 15(5):288–298
Messiah SE, Vidot DC, Somarriba G, Haney K, Aytur S, Natale RA, Brosco JP, Arheart KL (2015) Obesity and cardiometabolic disease risk factors among US adolescents with disabilities. World J Diabetes 6(1):200–207
Lega IC, Lipscombe LL (2020) Review: diabetes, obesity, and cancer-pathophysiology and clinical implications. Endocr Rev 41(1):33–52
Sebo P, Beer-Borst S, Haller DM, Bovier PA (2008) Reliability of doctors’ anthropometric measurements to detect obesity. Prev Med 47(4):389–393
Bray GA, Frühbeck G, Ryan DH, Wilding JPH (2016) Management of obesity. Lancet 387(10031):1947–1956
Graffy PM, Pickhardt PJ (2016) Quantification of hepatic and visceral fat by CT and MR imaging: relevance to the obesity epidemic, metabolic syndrome and NAFLD. Br J Radiol 89(1062):20151024
Thomas EL, Fitzpatrick J, Malik S, Taylor-Robinson SD, Bell JD (2013) Whole body fat: content and distribution. Prog Nucl Magn Reson Spectrosc 73:56–80
Baum T, Cordes C, Dieckmeyer M, Ruschke S, Franz D, Hauner H, Kirschke JS, Karampinos DC (2016) MR-based assessment of body fat distribution and characteristics. Eur J Radiol 85(8):1512–1518
Ludwig UA, Klausmann F, Baumann S, Honal M, Hovener JB, Konig D, Deibert P, Buchert M (2014) Whole-body MRI-based fat quantification: a comparison to air displacement plethysmography. J Magn Reson Imaging 40(6):1437–1444
Eggers H, Bornert P (2014) Chemical shift encoding-based water-fat separation methods. J Magn Reson Imaging 40(2):251–268
Abraham TM, Pedley A, Massaro JM, Hoffmann U, Fox CS (2015) Association between visceral and subcutaneous adipose depots and incident cardiovascular disease risk factors. Circulation 132(17):1639–1647
Ibrahim MM (2010) Subcutaneous and visceral adipose tissue: structural and functional differences. Obes Rev 11(1):11–18
Hu HH, Chen J, Shen W (2016) Segmentation and quantification of adipose tissue by magnetic resonance imaging. Magn Reson Mater Phy 29(2):259–276
Elbers J, Haumann G, Asscheman H, Seidell J, Gooren LJ (1997) Reproducibility of fat area measurements in young, non-obese subjects by computerized analysis of magnetic resonance images. Int J Obes 21(12):1121–1129
Poll L, Wittsack H, Koch J, Willers R, Scherer A, Kapitza C, Heinemann L (2002) Quantification of total abdominal fat volumes using magnetic resonance imaging. Eur J Med Res 7:347–352
Brennan DD, Whelan PF, Robinson K, Ghita O, O’Brien JM, Sadleir R, Eustace SJ (2005) Rapid automated measurement of body fat distribution from whole-body MRI. Am J Roentgenol 185(2):418–423
Mosbech TH, Pilgaard K, Vaag A, Larsen R (2011) Automatic segmentation of abdominal adipose tissue in MRI. In: Scandinavian conference on image analysis. Springer Berlin Heidelberg, pp 501–511.
Shen J, Baum T, Cordes C, Ott B, Skurk T, Kooijman H, Rummeny EJ, Hauner H, Menze BH, Karampinos DC (2016) Automatic segmentation of abdominal organs and adipose tissue compartments in water-fat MRI: application to weight-loss in obesity. Eur J Radiol 85(9):1613–1621
Lundstrom E, Strand R, Forslund A, Bergsten P, Weghuber D, Ahlstrom H, Kullberg J (2017) Automated segmentation of human cervical-supraclavicular adipose tissue in magnetic resonance images. Sci Rep 7(1):1–12
Yang YX, Chong MS, Tay L, Yew S, Yeo A, Tan CH (2016) Automated assessment of thigh composition using machine learning for Dixon magnetic resonance images. Magn Reson Mater Phy 29(5):723–731
Shen N, Li X, Zheng S, Zhang L, Fu Y, Liu X, Li M, Li J, Guo S, Zhang H (2019) Automated and accurate quantification of subcutaneous and visceral adipose tissue from magnetic resonance imaging based on machine learning. Magn Reson Imaging 64:28–36
Langner T, Hedstrom A, Morwald K, Weghuber D, Forslund A, Bergsten P, Ahlstrom H, Kullberg J (2019) Fully convolutional networks for automated segmentation of abdominal adipose tissue depots in multicenter water-fat MRI. Magn Reson Med 81(4):2736–2745
Wurslin C, Machann J, Rempp H, Claussen C, Yang B, Schick F (2010) Topography mapping of whole body adipose tissue using a fully automated and standardized procedure. J Magn Reson Imaging 31(2):430–439
Kuhn JP, Hernando D, Mensel B, Kruger PC, Ittermann T, Mayerle J, Hosten N, Reeder SB (2014) Quantitative chemical shift-encoded MRI is an accurate method to quantify hepatic steatosis. J Magn Reson Imaging 39(6):1494–1501
Kullberg J, Johansson L, Ahlstrom H, Courivaud F, Koken P, Eggers H, Bornert P (2009) Automated assessment of whole-body adipose tissue depots from continuously moving bed MRI: a feasibility study. J Magn Reson Imaging 30(1):185–193
Küstner T, Hepp T, Fischer M, Schwartz M, Fritsche A, Häring H-U, Nikolaou K, Bamberg F, Yang B, Schick F (2020) Fully automated and standardized segmentation of adipose tissue compartments via deep learning in 3D whole-body MRI of epidemiologic cohort studies. Radiol Artif Intell 2(5):e200010
Wald D, Teucher B, Dinkel J, Kaaks R, Delorme S, Boeing H, Seidensaal K, Meinzer HP, Heimann T (2012) Automatic quantification of subcutaneous and visceral adipose tissue from whole-body magnetic resonance images suitable for large cohort studies. J Magn Reson Imaging 36(6):1421–1434
Peng H, Zou C, Cheng C, Tie C, Qiao Y, Wan Q, Lv J, He Q, Liang D, Liu X, Liu W, Zheng H (2019) Fat-water separation based on Transition REgion Extraction (TREE). Magn Reson Med 82(1):436–448
Cheng C, Zou C, Liang C, Liu X, Zheng H (2017) Fat-water separation using a region-growing algorithm with self-feeding phasor estimation. Magn Reson Med 77(6):2390–2401
Zou C, Cheng C, Qiao Y, Wan Q, Tie C, Pan M, Liang D, Zheng H, Liu X (2019) Hierarchical iterative linear-fitting algorithm (HILA) for phase correction in fat quantification by bipolar multi-echo sequence. Quant Imaging Med Surg 9(2):247–262
MacCannell ADV, Sinclair KJ, McKenzie CA, Staples JF (2019) Environmental temperature effects on adipose tissue growth in a hibernator. J Exp Biol 222(3):jeb194548
Wu M, Junker D, Branca RT, Karampinos DC (2020) Magnetic resonance imaging techniques for brown adipose tissue detection. Front Endocrinol 11:421
Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):1–48
Bloice MD, Roth PM, Holzinger A (2019) Biomedical image augmentation using Augmentor. Bioinformatics 35(21):4522–4524
Ronneberger O, Fischer P (2015) Brox T U-Net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention—MICCAI 2015. Springer International Publishing, Cham, pp 234–241.
Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, pp 675–678
Wu Y, Liu L, Bae J, Chow K-H, Iyengar A, Pu C, Wei W, Yu L, Zhang Q (2019) Demystifying learning rate policies for high accuracy training of deep neural networks. In: 2019 IEEE international conference on big data (big data). IEEE, pp 1971–1980.
Funding
This research was supported by the National natural Science Foundation of China [Grant Number 61901462 and 81801724], the China Postdoctoral Science Foundation [Grant Number 2019M650220], the Guangdong Grant ‘Key Technologies for Treatment of Brain Disorders’ [Grant Number 2018B030332001], Scientific Instrument Innovation Team of the Chinese Academy of Sciences [Grant Number GJJSTD20180002], International Partnership Program of Chinese Academy of Sciences Grant [Grant Number 154144KYSB20180063], Shenzhen Double Chain Grant [Grant Number [2018]256], and the Strategic Priority Research Program of Chinese Academy of Sciences [Grant Number XDB25000000].
Author information
Authors and Affiliations
Contributions
ZW and CC have made substantial contributions to the conception and design of the study, to the acquisition, analysis, and interpretation of data, and have drafted the manuscript. CZ and SQ have made substantial contributions to the conception and design of the work, to the acquisition, analysis, and interpretation of data, and have substantially revised the manuscript. HP, YQ, QW, and HZ have made substantial contributions to the acquisition, analysis, and interpretation of data. DL, XL, and HrZ have made substantial contributions to the conception and design of the work and substantively have revised the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
All authors declare that they have no conflict of interest.
Ethical approval
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional review board of Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (IRB approval number: SIAT-IRB-200315-H0454).
Informed consent
Informed consent was obtained from all individual participants included in the study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Wang, Z., Cheng, C., Peng, H. et al. Automatic segmentation of whole-body adipose tissue from magnetic resonance fat fraction images based on machine learning. Magn Reson Mater Phy 35, 193–203 (2022). https://doi.org/10.1007/s10334-021-00958-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10334-021-00958-5