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

被引:2
作者
Wu, Bingxia [1 ,2 ]
Cheng, Chuanli [2 ,3 ]
Qi, Yulong [4 ]
Zhou, Hongyu [2 ]
Peng, Hao [2 ]
Wan, Qian [2 ]
Liu, Xin [2 ]
Zheng, Hairong [2 ]
Zhang, Huimao [5 ]
Zou, Chao [2 ,3 ]
机构
[1] Wuhan Univ Technol, Sch Informat Engn, Wuhan, Peoples R China
[2] Chinese Acad Sci, Shenzhen Inst Adv Technol, Paul C Lauterbur Res Ctr Biomed Imaging, 1068 Xueyuan Ave, Shenzhen 518055, Peoples R China
[3] Imaging Res Inst Innovat Med Equipment, Shenzhen, Peoples R China
[4] Peking Univ, Radiol Dept, Shenzhen Hosp, Shenzhen, Peoples R China
[5] Jilin Univ, Radiol Dept, Bethune Hosp 1, Changchun, Peoples R China
基金
中国国家自然科学基金;
关键词
Supraclavicular adipose tissue; Magnetic resonance imaging; Brown adipose tissue; Deep learning; Fat fraction; FAT-FRACTION; WATER-FAT; BROWN; MRI; IDENTIFICATION; VOLUME; BAT;
D O I
10.1007/s10334-022-01056-w
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
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.
引用
收藏
页码:641 / 649
页数:9
相关论文
共 45 条
[11]   Mice lacking mitochondrial uncoupling protein are cold-sensitive but not obese [J].
Enerback, S ;
Jacobsson, A ;
Simpson, EM ;
Guerra, C ;
Yamashita, H ;
Harper, ME ;
Kozak, LP .
NATURE, 1997, 387 (6628) :90-94
[12]   Prospective self-gating for swallowing motion: A feasibility study in carotid artery wall MRI using three-dimensional variable-flip-angle turbo spin-echo [J].
Fan, Zhaoyang ;
Zuehlsdorff, Sven ;
Liu, Xin ;
Li, Debiao .
MAGNETIC RESONANCE IN MEDICINE, 2012, 67 (02) :490-498
[13]   Reliability and agreement of adipose tissue fat fraction measurements with water-fat MRI in patients with manifest cardiovascular disease [J].
Franssens, Bas T. ;
Eikendal, Anouk L. ;
Leiner, Tim ;
van der Graaf, Yolanda ;
Visseren, Frank L. J. ;
Hoogduin, J. M. .
NMR IN BIOMEDICINE, 2016, 29 (01) :48-56
[14]   Association of proton density fat fraction in adipose tissue with imaging-based and anthropometric obesity markers in adults [J].
Franz, D. ;
Weidlich, D. ;
Freitag, F. ;
Holzapfel, C. ;
Drabsch, T. ;
Baum, T. ;
Eggers, H. ;
Witte, A. ;
Rummeny, E. J. ;
Hauner, H. ;
Karampinos, D. C. .
INTERNATIONAL JOURNAL OF OBESITY, 2018, 42 (02) :175-182
[15]   BAT: a new target for human obesity? [J].
Fruehbeck, Gema ;
Becerril, Sara ;
Sainz, Neira ;
Garrastachu, Puy ;
Jose Garcia-Velloso, Maria .
TRENDS IN PHARMACOLOGICAL SCIENCES, 2009, 30 (08) :387-396
[16]   Inhibition of Mitochondrial Calcium Overload by SIRT3 Prevents Obesity- or Age-Related Whitening of Brown Adipose Tissue [J].
Gao, Peng ;
Jiang, Yanli ;
Wu, Hao ;
Sun, Fang ;
Li, Yaohong ;
He, Hongbo ;
Wang, Bin ;
Lu, Zongshi ;
Hu, Yingru ;
Wei, Xiao ;
Cui, Yuanting ;
He, Chengkang ;
Wang, Lijuan ;
Zheng, Hongting ;
Yang, Gangyi ;
Liu, Daoyan ;
Yan, Zhencheng ;
Zhu, Zhiming .
DIABETES, 2020, 69 (02) :165-180
[17]   MRI characteristics of supraclavicular brown adipose tissue in relation to cold-induced thermogenesis in healthy human adults [J].
Gashi, Gani ;
Madoerin, Philipp ;
Maushart, Claudia, I ;
Michel, Regina ;
Senn, Jael-Rut ;
Bieri, Oliver ;
Betz, Matthias J. .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2019, 50 (04) :1160-1168
[18]   Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images [J].
Gifford, Aliya ;
Towse, Theodore F. ;
Walker, Ronald C. ;
Avison, Malcolm J. ;
Welch, E. Brian .
JOVE-JOURNAL OF VISUALIZED EXPERIMENTS, 2015, (96)
[19]   In vivo characterization of the liver fat 1H MR spectrum [J].
Hamilton, Gavin ;
Yokoo, Takeshi ;
Bydder, Mark ;
Cruite, Irene ;
Schroeder, Michael E. ;
Sirlin, Claude B. ;
Middleton, Michael S. .
NMR IN BIOMEDICINE, 2011, 24 (07) :784-790
[20]   Brown and beige fat: development, function and therapeutic potential [J].
Harms, Matthew ;
Seale, Patrick .
NATURE MEDICINE, 2013, 19 (10) :1252-1263