Automatic segmentation of the interscapular brown adipose tissue in rats based on deep learning using the dynamic magnetic resonance fat fraction images

被引:1
作者
Cheng, Chuanli [1 ,2 ]
Wu, Bingxia [3 ]
Zhang, Lei [4 ]
Wan, Qian [1 ]
Peng, Hao [1 ]
Liu, Xin [1 ]
Zheng, Hairong [1 ]
Zhang, Huimao [4 ]
Zou, Chao [1 ,2 ]
机构
[1] Shenzhen Univ Town, Shenzhen Inst Adv Technol, Chinese Acad Sci, Paul C Lauterbur Res Ctr Biomed Imaging, 1068 Xueyuan Ave, Shenzhen 518055, Peoples R China
[2] Imaging Res Inst Innovat Med Equipment, Shenzhen, Peoples R China
[3] Wuhan Univ Technol, Sch Informat Engn, Wuhan, Peoples R China
[4] Jilin Univ, Bethune Hosp 1, Radiol Dept, Changchun, Peoples R China
关键词
Brown adipose tissue; Automatic labelling; Magnetic resonance imaging; Fat fraction; Deep learning; IDENTIFICATION; ALGORITHM; OBESITY; WHITE;
D O I
10.1007/s10334-023-01133-8
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 The study aims to propose an accurate labelling method of interscapular BAT (iBAT) in rats using dynamic MR fat fraction (FF) images with noradrenaline (NE) stimulation and then develop an automatic iBAT segmentation method using a U-Net model. Materials and methods Thirty-four rats fed different diets or housed at different temperatures underwent successive MR scans before and after NE injection. The iBAT were labelled automatically by identifying the regions with obvious FF change in response to the NE stimulation. Further, these FF images along with the recognized iBAT mask images were used to develop a deep learning network to accomplish the robust segmentation of iBAT in various rat models, even without NE stimulation. The trained model was then validated in rats fed with high-fat diet (HFD) in comparison with normal diet (ND). Result A total of 6510 FF images were collected using a clinical 3.0 T MR scanner. The dice similarity coefficient (DSC) between the automatic and manual labelled results was 0.895 +/- 0.022. For the network training, the DSC, precision rate, and recall rate were found to be 0.897 +/- 0.061, 0.901 +/- 0.068 and 0.899 +/- 0.086, respectively. The volumes and FF values of iBAT in HFD rats were higher than ND rats, while the FF decrease was larger in ND rats after NE injection. Conclusion An automatic iBAT segmentation method for rats was successfully developed using the dynamic labelled FF images of activated BAT and deep learning network.
引用
收藏
页码:215 / 226
页数:12
相关论文
共 50 条
[41]   Automatic liver segmentation and assessment of liver fibrosis using deep learning with MR T1-weighted images in rats [J].
Zhang, Wenjing ;
Zhao, Nan ;
Gao, Yuanxiang ;
Huang, Baoxiang ;
Wang, Lili ;
Zhou, Xiaoming ;
Li, Zhiming .
MAGNETIC RESONANCE IMAGING, 2024, 107 :1-7
[42]   Residual learning: A new paradigm to improve deep learning-based segmentation of the left ventricle in magnetic resonance imaging cardiac images [J].
Zarvani, Maral ;
Saberi, Sara ;
Azmi, Reza ;
Shojaedini, Seyed Vahab .
JOURNAL OF MEDICAL SIGNALS & SENSORS, 2021, 11 (03) :159-168
[43]   Automatic tissue image segmentation based on image processing and deep learning [J].
Kong, Zhenglun ;
Luo, Junyi ;
Xu, Shengpu ;
Li, Ting .
NEURAL IMAGING AND SENSING 2018, 2018, 10481
[44]   FM-Net: A Fully Automatic Deep Learning Pipeline for Epicardial Adipose Tissue Segmentation [J].
Feng, Fan ;
Carlhall, Carl-Johan ;
Tan, Yongyao ;
Agrawal, Shaleka ;
Lundberg, Peter ;
Bai, Jieyun ;
Yang, John Zhiyong ;
Trew, Mark ;
Zhao, Jichao .
STATISTICAL ATLASES AND COMPUTATIONAL MODELS OF THE HEART. REGULAR AND CMRXRECON CHALLENGE PAPERS, STACOM 2023, 2024, 14507 :88-97
[45]   Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning [J].
Xin Li ;
Yi Lin ;
Zhuoyao Xie ;
Zixiao Lu ;
Liwen Song ;
Qiang Ye ;
Menghong Wang ;
Xiao Fang ;
Yi He ;
Hao Chen ;
Yinghua Zhao .
Insights into Imaging, 15
[46]   Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning [J].
Li, Xin ;
Lin, Yi ;
Xie, Zhuoyao ;
Lu, Zixiao ;
Song, Liwen ;
Ye, Qiang ;
Wang, Menghong ;
Fang, Xiao ;
He, Yi ;
Chen, Hao ;
Zhao, Yinghua .
INSIGHTS INTO IMAGING, 2024, 15 (01)
[47]   Interpretation of Magnetic Resonance Images of Temporomandibular Joint Disorders by Using Deep Learning [J].
Ozsari, Sifa ;
Yapicioglu, Fatima Rabia ;
Yilmaz, Dilek ;
Kamburoglu, Kivanc ;
Guzel, Mehmet Serdar ;
Bostanci, Gazi Erkan ;
Acici, Koray ;
Asuroglu, Tunc .
IEEE ACCESS, 2023, 11 :49102-49113
[48]   In Vivo Assessment of Cold Stimulation Effects on the Fat Fraction of Brown Adipose Tissue Using DIXON MRI [J].
Stahl, Vanessa ;
Maier, Florian ;
Freitag, Martin T. ;
Floca, Ralf O. ;
Berger, Moritz C. ;
Umathum, Reiner ;
Diaz, Mauricio Berriel ;
Herzig, Stephan ;
Weber, Marc-Andre ;
Dimitrakopoulou-Strauss, Antonia ;
Rink, Kristian ;
Bachert, Peter ;
Ladd, Mark E. ;
Nagel, Armin M. .
JOURNAL OF MAGNETIC RESONANCE IMAGING, 2017, 45 (02) :369-380
[49]   Implementation of deep learning algorithms for automatic MRI segmentation and Fat Fraction quantification in individual muscles. [J].
Martin, Sandra ;
Trabelsi, Amira ;
Andre, Remi ;
Wojak, Julien ;
Fortanier, Etienne ;
Attarian, Shahram ;
Guye, Maxime ;
Dubois, Marc ;
Abdeddaim, Redha ;
Bendahan, David .
MEDICAL IMAGING 2023, 2023, 12464
[50]   Improving automatic segmentation of liver tumor images using a deep learning model [J].
Song, Zhendong ;
Wu, Huiming ;
Chen, Wei ;
Slowik, Adam .
HELIYON, 2024, 10 (07)