Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks

Sven Koitka, Lennard Kroll, Eugen Malamutmann and 2 more

European Radiology · 2020 · CC BY

Abstract

Objectives. Body tissue composition is a long-known biomarker with high diagnostic and prognostic value not only in cardiovascular, oncological, and orthopedic diseases but also in rehabilitation medicine or drug dosage. In this study, the aim was to develop a fully automated, reproducible, and quantitative 3D volumetry of body tissue composition from standard CT examinations of the abdomen in order to be able to offer such valuable biomarkers as part of routine clinical imaging.

Methods. Therefore, an in-house dataset of 40 CTs for training and 10 CTs for testing were fully annotated on every fifth axial slice with five different semantic body regions: abdominal cavity, bones, muscle, subcutaneous tissue, and thoracic cavity. Multi-resolution U-Net 3D neural networks were employed for segmenting these body regions, followed by subclassifying adipose tissue and muscle using known Hounsfield unit limits.

Results. The Sørensen Dice scores averaged over all semantic regions was 0.9553 and the intra-class correlation coefficients for subclassified tissues were above 0.99.

Conclusions. Our results show that fully automated body composition analysis on routine CT imaging can provide stable biomarkers across the whole abdomen and not just on L3 slices, which is historically the reference location for analyzing body composition in the clinical routine.

Key Points. • Our study enables fully automated body composition analysis on routine abdomen CT scans. • The best segmentation models for semantic body region segmentation achieved an averaged Sørensen Dice score of 0.9553. • Subclassified tissue volumes achieved intra-class correlation coefficients over 0.99.

Electronic supplementary material. The online version of this article (10.1007/s00330-020-07147-3) contains supplementary material, which is available to authorized users.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 36

1.
Sam S (2018) Differential effect of subcutaneous abdominal and visceral adipose tissue on cardiometabolic risk. Horm Mol Biol Clin Invest 33. 10.1515/hmbci-2018-0014
Not in our library10.1515/hmbci-2018-0014
2.
Peterson SJ, Braunschweig CA. Prevalence of sarcopenia and associated & outcomes in the clinical setting. Nutr Clin Pract. 2016;31:40-48.
Not in our library10.1177/0884533615622537
3.
Mraz M, Haluzik M. The role of adipose tissue immune cells in obesity and low- grade inflammation. J Endocrinol. 2014;222:R113-R127.
Not in our library10.1530/joe-14-0283
4.
Kent E, O’Dwyer V, Fattah C, Farah N, O'Connor C, Turner MJ. Correlation between birth weight and maternal body composition. Obstet Gynecol. 2013;121:46-50.
Not in our library10.1097/aog.0b013e31827a0052
5.
Hilton TN, Tuttle LJ, Bohnert KL, Mueller MJ, Sinacore DR. Excessive adipose tissue infiltration in skeletal muscle in individuals with obesity, diabetes mellitus, and peripheral neuropathy: association with performance and function. Phys Ther. 2008;88:1336-1344.
Not in our library10.2522/ptj.20080079
6.
Mazzali G, Di Francesco V, Zoico E, et al. Interrelations between fat distribution, muscle lipid content, adipocytokines, and insulin resistance: effect of moderate weight loss in older women. Am J Clin Nutr. 2006;84:1193-1199.
Not in our library10.1093/ajcn/84.5.1193
7.
Zopfs D, Theurich S, Große Hokamp N, et al. Single-slice CT measurements allow for accurate assessment of sarcopenia and body composition. Eur Radiol. 2020;30:1701-1708.
Not in our library10.1007/s00330-019-06526-9
8.
Weston AD, Korfiatis P, Kline TL, et al. Automated abdominal segmentation of CT scans for body composition analysis using deep learning. Radiology. 2019;290:669-679.
Not in our library10.1148/radiol.2018181432
9.
Seabolt LA, Welch EB, Silver HJ. Imaging methods for analyzing body composition in human obesity and cardiometabolic disease. Ann N Y Acad Sci. 2015;1353:41-59.
Not in our library10.1111/nyas.12842
10.
Yushkevich PA, Piven J, Hazlett HC, et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage. 2006;31:1116-1128.
Not in our library10.1016/j.neuroimage.2006.01.015
11.
Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O, Ourselin S, Joskowicz L, Sabuncu MR, Unal G, Wells W. 3D U-net: learning dense volumetric segmentation from sparse annotation. Medical image computing and computer-assisted intervention – MICCAI 2016. 2016;424-432.
Not in our library
12.
Ibtehaz N, Rahman MS. MultiResUNet: rethinking the U-Net architecture for multimodal biomedical image segmentation. Neural Netw. 2020;121:74-87.
Not in our library10.1016/j.neunet.2019.08.025
13.
Ulyanov D, Vedaldi A, Lempitsky V (2017) Improved texture networks: maximizing quality and diversity in feed-forward stylization and texture synthesis. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 10.1109/CVPR.2017.437
Not in our library
14.
Ioffe S, Szegedy C, Bach F, Blei D. Batch normalization: accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd international conference on machine learning. 2015;448-456.
Not in our library
15.
Odena A, Dumoulin V, Olah C (2016) Deconvolution and checkerboard artifacts. Distill. 10.23915/distill.00003
Not in our library
16.
Abadi M, Barham P, Chen J, et al (2016) TensorFlow: a system for large-scale machine learning. 12th USENIX symposium on operating systems design and implementation (OSDI 16). USENIX Association, Savannah, GA, pp 265–283
Not in our library
17.
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd international conference on learning representations (ICLR). San Diego, CA, USA
Not in our library
18.
Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: seventh international conference on learning representations (ICLR). Ernest N. Morial Convention Center, New Orleans, USA
Not in our library
19.
Isensee F, Petersen J, Klein A, Handels H, Deserno TM, Maier A, Maier-Hein KH, Palm C, Tolxdorff T, et al. nnU-Net: self-adapting framework for U-net-based medical image segmentation. Bildverarbeitung für die Medizin 2019. 2019;22-22.
Not in our library
20.
Sudre CH, Li W, Vercauteren T, Ourselin S, Jorge Cardoso M, Cardoso MJ, Arbel T, Carneiro G, Syeda-Mahmood T, JMRS T, Moradi M, Bradley A, Greenspan H, Papa JP, Madabhushi A, Nascimento JC, Cardoso JS, Belagiannis V, Lu Z. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep learning in medical image analysis and multimodal learning for clinical decision support. 2017;240-248.
Not in our library10.1007/978-3-319-67558-9_28
21.
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press https://www.deeplearningbook.org
Not in our library
22.
Aubrey J, Esfandiari N, Baracos VE, et al. Measurement of skeletal muscle radiation attenuation and basis of its biological variation. Acta Physiol (Oxf). 2014;210:489-497.
Not in our library10.1111/apha.12224
23.
Kim YJ, Lee SH, Kim TY, Park JY, Choi SH, Kim KG. Body fat assessment method using CT images with separation mask algorithm. J Digit Imaging. 2013;26:155-162.
Not in our library10.1007/s10278-012-9488-0
24.
Kullberg J, Hedström A, Brandberg J, et al. Automated analysis of liver fat, muscle and adipose tissue distribution from CT suitable for large-scale studies. Sci Rep. 2017;7:10425.
Not in our library10.1038/s41598-017-08925-8
25.
Mensink SD, Spliethoff JW, Belder R, Klaase JM, Bezooijen R, Slump CH (2011) Development of automated quantification of visceral and subcutaneous adipose tissue volumes from abdominal CT scans. In: M.D RMS, Ginneken B van (eds) Medical imaging 2011: computer-aided diagnosis. SPIE, pp 799–810. 10.1117/12.878017
Not in our library
26.
Agarwal C, Dallal AH, Arbabshirani MR, Patel A, Moore G (2017) Unsupervised quantification of abdominal fat from CT images using Greedy Snakes. In: Styner MA, Angelini ED (eds) Medical Imaging 2017: Image processing. SPIE, pp 785–792. 10.1117/12.2254139
Not in our library
27.
Ohshima S, Yamamoto S, Yamaji T, et al. Development of an automated 3D segmentation program for volume quantification of body fat distribution using CT. Nihon Hoshasen Gijutsu Gakkai Zasshi. 2008;64:1177-1181.
Not in our library10.6009/jjrt.64.1177
28.
Parikh AM, Coletta AM, Yu ZH, et al. Development and validation of a rapid and robust method to determine visceral adipose tissue volume using computed tomography images. PLoS One. 2017;12:1-11.
Not in our library10.1371/journal.pone.0183515
29.
Pednekar A, Bandekar AN, Kakadiaris IA, Naghavi M (2005) Automatic segmentation of abdominal fat from CT data. In: 2005 seventh IEEE workshops on applications of computer vision (WACV/MOTION’05), pp 308–315. 10.1109/ACVMOT.2005.31
Not in our library
30.
Popuri K, Cobzas D, Esfandiari N, Baracos V, Jägersand M. Body composition assessment in axial CT images using FEM-based automatic segmentation of skeletal muscle. IEEE Trans Med Imaging. 2016;35:512-520.
Not in our library10.1109/tmi.2015.2479252
31.
Joshi AA, Hu HH, Leahy RM, Goran MI, Nayak KS. Automatic intra-subject registration-based segmentation of abdominal fat from water–fat MRI. J Magn Reson Imaging. 2013;37:423-430.
Not in our library10.1002/jmri.23813
32.
Positano V, Gastaldelli A, Sironi AM, Santarelli MF, Lombardi M, Landini L. An accurate and robust method for unsupervised assessment of abdominal fat by MRI. J Magn Reson Imaging. 2004;20:684-689.
Not in our library10.1002/jmri.20167
33.
Zhou A, Murillo H, Peng Q. Novel segmentation method for abdominal fat quantification by MRI. J Magn Reson Imaging. 2011;34:852-860.
Not in our library10.1002/jmri.22673
34.
Bridge CP, Rosenthal M, Wright B, Stoyanov D, Taylor Z, Sarikaya D, McLeod J, González Ballester MA, NCF C, Martel A, Maier-Hein L, Malpani A, Zenati MA, De Ribaupierre S, Xiongbiao L, Collins T, Reichl T, Drechsler K, Erdt M, Linguraru MG, Oyarzun Laura C, Shekhar R, Wesarg S, Celebi ME, Dana K, Halpern A, et al. Fully-automated analysis of body composition from CT in cancer patients using convolutional neural networks. OR 2.0 Context-aware operating theaters, computer assisted robotic endoscopy, clinical image-based procedures, and skin image analysis. 2018;204-213.
Not in our library
35.
Gibson E, Giganti F, Hu Y, et al. Automatic multi-organ segmentation on abdominal CT with dense V-networks. IEEE Trans Med Imaging. 2018;37:1822-1834.
Not in our library10.1109/tmi.2018.2806309
36.
Gibson E, Giganti F, Hu Y et al (2018) Multi-organ abdominal CT reference standard segmentations. Zenodo. 10.5281/zenodo.1169361
Not in our library

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.