It appears you don't have support to open PDFs in this web browser. To view this file, Open with your PDF reader
Abstract
The standard method for identifying active Brown Adipose Tissue (BAT) is [18F]-Fluorodeoxyglucose ([18F]-FDG) PET/CT imaging, which is costly and exposes patients to radiation, making it impractical for population studies. These issues can be addressed with computational methods that predict [18F]-FDG uptake by BAT from CT; earlier population studies pave the way for developing such methods by showing some correlation between the Hounsfield Unit (HU) of BAT in CT and the corresponding [18F]-FDG uptake in PET. In this study, we propose training convolutional neural networks (CNNs) to predict [18F]-FDG uptake by BAT from unenhanced CT scans in the restricted regions that are likely to contain BAT. Using the Attention U-Net architecture, we perform experiments on datasets from four different cohorts, the largest study to date. We segment BAT regions using predicted [18F]-FDG uptake values, achieving 23% to 40% better accuracy than conventional CT thresholding. Additionally, BAT volumes computed from the segmentations distinguish the subjects with and without active BAT with an AUC of 0.8, compared to 0.6 for CT thresholding. These findings suggest CNNs can facilitate large-scale imaging studies more efficiently and cost-effectively using only CT.
The standard method for identifying active brown adipose tissue is costly and exposes patients to radiation. Here, the authors show that convolutional neural networks can predict [18F]-FDG uptake by BAT from unenhanced CT scans and improve the segmentation accuracy compared to conventional CT thresholding.
You have requested "on-the-fly" machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Show full disclaimer
Neither ProQuest nor its licensors make any representations or warranties with respect to the translations. The translations are automatically generated "AS IS" and "AS AVAILABLE" and are not retained in our systems. PROQUEST AND ITS LICENSORS SPECIFICALLY DISCLAIM ANY AND ALL EXPRESS OR IMPLIED WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES FOR AVAILABILITY, ACCURACY, TIMELINESS, COMPLETENESS, NON-INFRINGMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Your use of the translations is subject to all use restrictions contained in your Electronic Products License Agreement and by using the translation functionality you agree to forgo any and all claims against ProQuest or its licensors for your use of the translation functionality and any output derived there from. Hide full disclaimer
Details









1 ETH Zurich, Computer Vision Lab., Zurich, Switzerland (GRID:grid.5801.c) (ISNI:0000 0001 2156 2780)
2 ETH Zurich, Computer Vision Lab., Zurich, Switzerland (GRID:grid.5801.c) (ISNI:0000 0001 2156 2780); Memorial Sloan Kettering Cancer Center, Department of Radiology, New York, NY, USA (GRID:grid.51462.34) (ISNI:0000 0001 2171 9952); University Hospital Zurich, Institute for Diagnostic and Interventional Radiology, Zurich, Switzerland (GRID:grid.412004.3) (ISNI:0000 0004 0478 9977); NYU Grossman School of Medicine, Department of Radiology, New York, NY, USA (GRID:grid.137628.9) (ISNI:0000 0004 1936 8753)
3 University Hospital Zurich, Institute for Diagnostic and Interventional Radiology, Zurich, Switzerland (GRID:grid.412004.3) (ISNI:0000 0004 0478 9977)
4 University of Almería, Department of Nursing, Physiotherapy and Medicine and SPORT Research Group (CTS-1024), CERNEP Research Center, Almería, Spain (GRID:grid.28020.38) (ISNI:0000 0001 0196 9356); Instituto de Salud Carlos III, CIBER de Fisiopatología de la Obesidad y Nutrición (CIBEROBN), Granada, Spain (GRID:grid.413448.e) (ISNI:0000 0000 9314 1427); Leiden University Medical Center, Department of Medicine, Division of Endocrinology and Einthoven Laboratory for Experimental Vascular Medicine, Leiden, The Netherlands (GRID:grid.10419.3d) (ISNI:0000 0000 8945 2978)
5 Sport and Health University Research Institute (iMUDS), University of Granada, Department of Physical Education and Sports, Faculty of Sports Science, Granada, Spain (GRID:grid.4489.1) (ISNI:0000 0001 2167 8994); Ibs.Granada, Instituto de Investigación Biosanitaria, Granada, Spain (GRID:grid.507088.2); Instituto de Salud Carlos III, Centro de Investigación Biomédica en Red Fisiopatología de la Obesidad y Nutrición (CIBERobn), Madrid, Spain (GRID:grid.413448.e) (ISNI:0000 0000 9314 1427)
6 Memorial Sloan Kettering Cancer Center, Department of Radiology, New York, NY, USA (GRID:grid.51462.34) (ISNI:0000 0001 2171 9952)
7 University Zurich Hospital, Department of Nuclear Medicine, Zurich, Switzerland (GRID:grid.412004.3) (ISNI:0000 0004 0478 9977); University of Zurich, Zurich, Switzerland (GRID:grid.7400.3) (ISNI:0000 0004 1937 0650)
8 University Hospital of Basel, Department of Radiology and Nuclear Medicine, Basel, Switzerland (GRID:grid.410567.1) (ISNI:0000 0001 1882 505X)
9 ETH Zürich, Swiss Multi-Omics Center, Zürich, Switzerland (GRID:grid.5801.c) (ISNI:0000 0001 2156 2780)
10 Ecole Polytechnique Fédérale de Lausanne (EPFL), Laboratory of Systems Biology and Genetics, Institute of Bioengineering, School of Life Sciences, Lausanne, Switzerland (GRID:grid.5333.6) (ISNI:0000 0001 2183 9049); Swiss Institute of Bioinformatics, Lausanne, Switzerland (GRID:grid.419765.8) (ISNI:0000 0001 2223 3006)
11 University Hospital Basel and University of Basel, Department of Endocrinology, Diabetes and Metabolism, Basel, Switzerland (GRID:grid.6612.3) (ISNI:0000 0004 1937 0642)
12 ETH Zurich, Department of Health Sciences and Technology, Zurich, Switzerland (GRID:grid.5801.c) (ISNI:0000 0001 2156 2780)
13 ETH Zurich, Computer Vision Lab., Zurich, Switzerland (GRID:grid.5801.c) (ISNI:0000 0001 2156 2780); The LOOP Zürich - Medical Research Center, Zürich, Switzerland (GRID:grid.5801.c)