Abstract #0989

An Automatic Machine learning Approach for multi-parametric MR based Brown adipose tissue characterization and Segmentation in mice and rats

Bhanu Prakash KN¹, Hussein Srour ^1,2, Sanjay Kumar Verma¹, Jadegoud Yaligar¹, Venkatesh Gopalan¹, Swee Shean Lee¹, Kai Hsiang Chuang ^1,2, and Sendhil Velan S^1,3

¹Laboratory of Metabolic Imaging, Singapore Bioimaging Consortium, Singapore, Singapore, ²Queensland Brain Institute, Brisbane, Australia, ³MRS & Metabolic Imaging Group, Singapore Institute for Clinical Sciences, Singapore, Singapore

We have utilized multiparametric MR images (fat-fraction (FF), T₂ and T₂*) of adipose tissues and evaluated different segmentation algorithms like multidimensional thresholding, region growing, clustering, and machine learning approach for its suitability and efficacy to separate WAT from BAT depots. A machine learning algorithm i.e. Neural Network based segmentation provided increased specificity compared to other algorithms. This methodology can be easily extended for multi-parametric human images and longitudinal studies.

This abstract and the presentation materials are available to members only; a login is required.

Join Here