nach oben

Magnetic Resonance Materials in Physics, Biology and Medicine

Erschienen in:

20.12.2022 | Research Article

Automatic segmentation of human supraclavicular adipose tissue using high-resolution T2-weighted magnetic resonance imaging

verfasst von: Bingxia Wu, Chuanli Cheng, Yulong Qi, Hongyu Zhou, Hao Peng, Qian Wan, Xin Liu, Hairong Zheng, Huimao Zhang, Chao Zou

Erschienen in: Magnetic Resonance Materials in Physics, Biology and Medicine | Ausgabe 4/2023

Einloggen, um Zugang zu erhalten

Abstract

Objective

To achieve efficient segmentation of human supraclavicular adipose tissue (sclavAT) using high-resolution T2-weighted magnetic resonance images.

Methods

High-resolution 1.0 mm isotropic 3D T2-weighted images covering human supraclavicular area were acquired in transverse or coronary plane from 29 volunteers using a 3.0 T MRI scanner. There were typically 144/288 slices for the transverse/coronary scans for each subject, which amounts to a total of 6816 images in 29 volunteers. A U-NET network was trained to segment the supraclavicular adipose tissue (sclavAT). The performance of the automatic segmentation method was evaluated by comparing the output results with the manual labels using the quantitative indices of dice similarity coefficient (DSC), precision rate (PR), and recall rate (RR). The auto-segmented images were used to calculate the sclavAT volumes and registered to the MR fat fraction (FF) images to quantify the fat component of the sclavAT area. The relationship between body mass index (BMI), the volume and FF of sclavAT area was evaluated for all subjects.

Results

The DSC, PR and RR of the automatic sclavAT segmentation method on the testing datasets were 0.920 ± 0.048, 0.915 ± 0.070 and 0.930 ± 0.058. The volume and the mean FF of sclavAT were both found to be strongly correlated to BMI, with the correlation coefficient of 0.703 and 0.625 (p < 0.05), respectively. The averaged computation time of the automatic segmentation method was approximately 0.06 s per slice, compared to more than 5 min for manual labeling.

Conclusion

The present study demonstrates that the proposed automatic segmentation method using U-Net network is able to identify human sclavAT efficiently and accurately.

Nur mit Berechtigung zugänglich

Ravussin E, Galgani JE (2011) The implication of brown adipose tissue for humans. Annu Rev Nutr 31:33–47CrossRefPubMedPubMedCentral

Enerbäck S, Jacobsson A, Simpson EM, Guerra C, Yamashita H, Harper M-E, Kozak LP (1997) Mice lacking mitochondrial uncoupling protein are cold-sensitive but not obese. Nature 387(6628):90–94CrossRefPubMed

Cypess AM, Lehman S, Williams G, Tal I, Rodman D, Goldfine AB, Kuo FC, Palmer EL, Tseng Y-H, Doria A (2009) Identification and importance of brown adipose tissue in adult humans. N Engl J Med 360(15):1509–1517CrossRefPubMedPubMedCentral

Nedergaard J, Bengtsson T, Cannon B (2007) Unexpected evidence for active brown adipose tissue in adult humans. Am J Physiol Endocrinol Metab

Celi FS (2009) Brown adipose tissue—when it pays to be inefficient. N Engl J Med 360(15):1553CrossRefPubMedPubMedCentral

Frühbeck G, Becerril S, Sáinz N, Garrastachu P, García-Velloso MJ (2009) BAT: a new target for human obesity? Trends Pharmacol Sci 30(8):387–396CrossRefPubMed

McNeill BT, Morton NM, Stimson RH (2020) Substrate utilization by brown adipose tissue: what’s hot and what’s not? Front Endocrinol (Lausanne) 11:571659CrossRefPubMed

Harms M, Seale P (2013) Brown and beige fat: development, function and therapeutic potential. Nat Med 19(10):1252–1263CrossRefPubMed

Ong FJ, Ahmed BA, Oreskovich SM, Blondin DP, Haq T, Konyer NB, Noseworthy MD, Haman F, Carpentier AC, Morrison KM (2018) Recent advances in the detection of brown adipose tissue in adult humans: a review. Clin Sci (Lond) 132(10):1039–1054CrossRefPubMed

10.

Sampath SC, Sampath SC, Bredella MA, Cypess AM, Torriani M (2016) Imaging of brown adipose tissue: state of the art. Radiology 280(1):4CrossRefPubMed

11.

van Marken Lichtenbelt WD, Vanhommerig JW, Smulders NM, Drossaerts JM, Kemerink GJ, Bouvy ND, Schrauwen P, Teule GJ (2009) Cold-activated brown adipose tissue in healthy men. N Engl J Med 360(15):1500–1508CrossRefPubMed

12.

Virtanen KA, Lidell ME, Orava J, Heglind M, Westergren R, Niemi T, Taittonen M, Laine J, Savisto N-J, Enerbäck S (2009) Functional brown adipose tissue in healthy adults. N Engl J Med 360(15):1518–1525CrossRefPubMed

13.

Wu M, Junker D, Branca RT, Karampinos DC (2020) Magnetic resonance imaging techniques for brown adipose tissue detection. Front Endocrinol (Lausanne) 11:421CrossRefPubMed

14.

Wang H, Wang Z, Wang J, Li K, Geng G, Kang F, Cao X (2022) ICA-Unet: an improved U-net network for brown adipose tissue segmentation. J Innov Opt Health Sci 15(03):2250018CrossRef

15.

Leitner BP, Huang S, Brychta RJ, Duckworth CJ, Baskin AS, McGehee S, Tal I, Dieckmann W, Gupta G, Kolodny GM (2017) Mapping of human brown adipose tissue in lean and obese young men. Proc Natl Acad Sci USA 114(32):8649–8654CrossRefPubMedPubMedCentral

16.

Khanna A, Branca RT (2012) Detecting brown adipose tissue activity with BOLD MRI in mice. Magn Reson Med 68(4):1285–1290CrossRefPubMedPubMedCentral

17.

Carter BW, Schucany WG (2008) Brown adipose tissue in a newborn. In: Baylor University Medical Center Proceedings, 2008. Taylor & Francis, pp 328–330

18.

Bhanu Prakash K, Srour H, Velan SS, Chuang K-H (2016) A method for the automatic segmentation of brown adipose tissue. MAGMA 29(2):287–299CrossRefPubMed

19.

Hu HH, Perkins TG, Chia JM, Gilsanz V (2013) Characterization of human brown adipose tissue by chemical-shift water-fat MRI. Am J Roentgenol 200(1):177CrossRef

20.

Shimizu I, Walsh K (2015) The whitening of brown fat and its implications for weight management in obesity. Curr Obes Rep 4(2):224–229CrossRefPubMed

21.

Gao P, Jiang Y, Wu H, Sun F, Li Y, He H, Wang B, Lu Z, Hu Y, Wei X (2020) Inhibition of mitochondrial calcium overload by SIRT3 prevents obesity-or age-related whitening of brown adipose tissue. Diabetes 69(2):165–180CrossRefPubMed

22.

Romu T, Vavruch C, Dahlqvist-Leinhard O, Tallberg J, Dahlström N, Persson A, Heglind M, Lidell ME, Enerbäck S, Borga M (2016) A randomized trial of cold-exposure on energy expenditure and supraclavicular brown adipose tissue volume in humans. Metabolism 65(6):926–934CrossRefPubMed

23.

Holstila M, Pesola M, Saari T, Koskensalo K, Raiko J, Borra RJ, Nuutila P, Parkkola R, Virtanen KA (2017) MR signal-fat-fraction analysis and T2* weighted imaging measure BAT reliably on humans without cold exposure. Metabolism 70:23–30CrossRefPubMed

24.

Oreskovich SM, Ong FJ, Ahmed BA, Konyer NB, Blondin DP, Gunn E, Singh NP, Noseworthy MD, Haman F, Carpentier AC (2019) MRI reveals human brown adipose tissue is rapidly activated in response to cold. J Endocr Soc 3(12):2374–2384CrossRefPubMedPubMedCentral

25.

Hui SC, Ko JK, Zhang T, Shi L, Yeung DK, Wang D, Chan Q, Chu WC (2017) Quantification of brown and white adipose tissue based on Gaussian mixture model using water–fat and MRI in adolescents. J Magn Reson Imaging 46(3):758–768CrossRefPubMed

26.

Lundström E, Strand R, Forslund A, Bergsten P, Weghuber D, Ahlström H, Kullberg J (2017) Automated segmentation of human cervical-supraclavicular adipose tissue in magnetic resonance images. Sci Rep 7(1):1–12CrossRef

27.

Chen Y-CI, Cypess AM, Chen Y-C, Palmer M, Kolodny G, Kahn CR, Kwong KK (2013) Measurement of human brown adipose tissue volume and activity using anatomic MR imaging and functional MR imaging. J Nucl Med 54(9):1584–1587CrossRefPubMed

28.

Franssens BT, Eikendal AL, Leiner T, van der Graaf Y, Visseren FL, Hoogduin J (2016) Reliability and agreement of adipose tissue fat fraction measurements with water–fat MRI in patients with manifest cardiovascular disease. NMR Biomed 29(1):48–56CrossRefPubMed

29.

Tan M, Le Q (2019) Efficientnet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning, 2019. PMLR, pp 6105–6114

30.

Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:14126980

31.

Aurelio YS, de Almeida GM, de Castro CL, Braga AP (2019) Learning from imbalanced data sets with weighted cross-entropy function. Neural Process Lett 50(2):1937–1949CrossRef

32.

Hamilton G, Yokoo T, Bydder M, Cruite I, Schroeder ME, Sirlin CB, Middleton MS (2011) In vivo characterization of the liver fat 1H MR spectrum. NMR Biomed 24(7):784–790CrossRefPubMed

33.

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):2390–2401CrossRefPubMed

34.

Collignon A, Maes F, Delaere D, Vandermeulen D, Suetens P, Marchal G (1995) Automated multi-modality image registration based on information theory. In: Information processing in medical imaging, 1995. Citeseer, pp 263–274

35.

Ogawa M, Koskensalo K, Laurila S, Holstila M, Lahesmaa M, Virtanen KA, Iida H, Akima H, Nuutila P (2022) Brown adipose tissue fat-fraction is associated with skeletal muscle adiposity. Eur J Appl Physiol 122(1):81–90CrossRefPubMed

36.

Fan Z, Zuehlsdorff S, Liu X, Li D (2012) Prospective self-gating for swallowing motion: a feasibility study in carotid artery wall MRI using three-dimensional variable-flip-angle turbo spin-echo. Magn Reson Med 67(2):490–498CrossRefPubMed

37.

Jones TA, Wayte SC, Reddy NL, Adesanya O, Dimitriadis GK, Barber TM, Hutchinson CE (2018) Identification of an optimal threshold for detecting human brown adipose tissue using receiver operating characteristic analysis of IDEAL MRI fat fraction maps. Magn Reson Imaging 51:61–68CrossRefPubMed

38.

Gashi G, Madoerin P, Maushart CI, Michel R, Senn JR, Bieri O, Betz MJ (2019) MRI characteristics of supraclavicular brown adipose tissue in relation to cold-induced thermogenesis in healthy human adults. J Magn Reson Imaging 50(4):1160–1168CrossRefPubMed

39.

Abreu-Vieira G, Sardjoe Mishre AS, Burakiewicz J, Janssen LG, Nahon KJ, Van der Eijk JA, Riem TT, Boon MR, Dzyubachyk O, Webb AG (2020) Human brown adipose tissue estimated with magnetic resonance imaging undergoes changes in composition after cold exposure: an in vivo MRI study in healthy volunteers. Front Endocrinol (Lausanne) 10:898CrossRefPubMed

40.

Deng J, Neff LM, Rubert NC, Zhang B, Shore RM, Samet JD, Nelson PC, Landsberg L (2018) MRI characterization of brown adipose tissue under thermal challenges in normal weight, overweight, and obese young men. J Magn Reson Imaging 47(4):936–947CrossRefPubMed

41.

Franz D, Weidlich D, Freitag F, Holzapfel C, Drabsch T, Baum T, Eggers H, Witte A, Rummeny EJ, Hauner H (2018) Association of proton density fat fraction in adipose tissue with imaging-based and anthropometric obesity markers in adults. Int J Obes (Lond) 42(2):175–182CrossRefPubMed

42.

Ohtomo T, Ino K, Miyashita R, Chigira M, Nakamura M, Someya K, Inaba N, Fujita M, Takagi M, Yamada J (2017) Chronic high-fat feeding impairs adaptive induction of mitochondrial fatty acid combustion-associated proteins in brown adipose tissue of mice. Biochem Biophys Rep 10:32–38PubMedPubMedCentral

43.

Sanchez-Delgado G, Martinez-Tellez B, Acosta FM, Virtue S, Vidal-Puig A, Gil A, Llamas-Elvira JM, Ruiz JR (2021) Brown adipose tissue volume and fat content are positively associated with whole-body adiposity in young men—not in women. Diabetes 70(7):1473–1485CrossRefPubMed

44.

Gifford A, Towse TF, Walker RC, Avison MJ, Welch EB (2015) Human brown adipose tissue depots automatically segmented by positron emission tomography/computed tomography and registered magnetic resonance images. J Vis Exp 96:e52415

45.

Branca RT, McCallister A, Yuan H, Aghajanian A, Faber JE, Weimer N, Buchanan R, Floyd CS, Antonacci M, Zhang L (2018) Accurate quantification of brown adipose tissue mass by xenon-enhanced computed tomography. Proc Natl Acad Sci USA 115(1):174–179CrossRefPubMed

Titel: Automatic segmentation of human supraclavicular adipose tissue using high-resolution T2-weighted magnetic resonance imaging
verfasst von: Bingxia Wu
Chuanli Cheng
Yulong Qi
Hongyu Zhou
Hao Peng
Qian Wan
Xin Liu
Hairong Zheng
Huimao Zhang
Chao Zou
Publikationsdatum: 20.12.2022
Verlag: Springer International Publishing
Erschienen in: Magnetic Resonance Materials in Physics, Biology and Medicine / Ausgabe 4/2023
Print ISSN: 0968-5243
Elektronische ISSN: 1352-8661
DOI: https://doi.org/10.1007/s10334-022-01056-w

Update Radiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Die Highlights vom Kongress des American College of Cardiology 2024

Springer Medizin

Automatic segmentation of human supraclavicular adipose tissue using high-resolution T2-weighted magnetic resonance imaging