Automated unsupervised multi‐parametric classification of adipose tissue depots in skeletal muscle. Issue 4 (23rd October 2012)

• Record Type: Journal Article
• Authors: Valentinitsch, Alexander; C. Karampinos, Dimitrios; Alizai, Hamza; Subburaj, Karupppasamy; Kumar, Deepak; M. Link, Thomas; Majumdar, Sharmila
• Is Part Of: Journal of magnetic resonance imaging. Volume 37:Issue 4(2013)
• Page Start: 917
• Page End: 927
• Publication Date: 2012-10-23
• Subjects: Magnetic resonance imaging -- Periodicals; 616
• DOI: 10.1002/jmri.23884
• Languages: English
• ISSNs: 1053-1807

Abstract

<abstract abstract-type="main" xml:lang="en"> <title>Abstract</title> <sec id="abs1-1" sec-type="section"> <title>Purpose:</title> <p>To introduce and validate an automated unsupervised multi‐parametric method for segmentation of the subcutaneous fat and muscle regions to determine subcutaneous adipose tissue (SAT) and intermuscular adipose tissue (IMAT) areas based on data from a quantitative chemical shift‐based water‐fat separation approach.</p> </sec> <sec id="abs1-2" sec-type="section"> <title>Materials and Methods:</title> <p>Unsupervised standard k‐means clustering was used to define sets of similar features (k = 2) within the whole multi‐modal image after the water‐fat separation. The automated image processing chain was composed of three primary stages: tissue, muscle, and bone region segmentation. The algorithm was applied on calf and thigh datasets to compute SAT and IMAT areas and was compared with a manual segmentation.</p> </sec> <sec id="abs1-3" sec-type="section"> <title>Results:</title> <p>The IMAT area using the automatic segmentation had excellent agreement with the IMAT area using the manual segmentation for all the cases in the thigh (R<sup>2</sup>: 0.96) and for cases with up to moderate IMAT area in the calf (R<sup>2</sup>: 0.92). The group with the highest grade of muscle fat infiltration in the calf had the highest error in the inner SAT contour calculation.</p> </sec> <sec id="abs1-4" sec-type="section"> <title>Conclusion:</title> <p>The proposed multi‐parametric segmentation approach combined with quantitative water‐fat imaging provides an accurate and reliable method for an automated calculation of the SAT and IMAT areas reducing considerably the total postprocessing time. J. Magn. Reson. Imaging 2013;37:917–927. © 2012 Wiley Periodicals, Inc.</p> </sec> </abstract>