A Novel Extension to Fuzzy Connectivity for Body Composition Analysis: Applications in Thigh, Brain, and Whole Body Tissue Segmentation

Abstract

Magnetic resonance imaging (MRI) is the non-invasive modality of choice for body tissue composition analysis due to its excellent soft tissue contrast and lack of ionizing radiation. However, quantification of body composition requires an accurate segmentation of fat, muscle and other tissues from MR images, which remains a challenging goal due to the intensity overlap between them. In this study, we propose a fully automated, data-driven image segmentation platform that addresses multiple difficulties in segmenting MR images such as varying inhomogeneity, non-standardness, and noise, while producing high-quality definition of different tissues. In contrast to most approaches in the literature, we perform segmentation operation by combining three different MRI contrasts and a novel segmentation tool which takes into account variability in the data. The proposed system, based on a novel affinity definition within the fuzzy connectivity (FC) image segmentation family, prevents the need for user intervention and reparametrization of the segmentation algorithms. In order to make the whole system fully automated, we adapt an affinity propagation clustering algorithm to roughly identify tissue regions and image background. We perform a thorough evaluation of the proposed algorithm's individual steps as well as comparison with several approaches from the literature for the main application of muscle/fat separation. Furthermore, whole-body tissue composition and brain tissue delineation were conducted to show the generalization ability of the proposed system. This new automated platform outperforms other state-of-the-art segmentation approaches both in accuracy and efficiency.

Novel stochastic framework for automatic segmentation of human thigh MRI volumes and its applications in spinal cord injured individuals

“…Similarly, Kovacs et al [45] used the contouring method to segment fascia lata to separate SAT and IMAT in severe muscular dystrophy cases. In a recent study, Irmakci et al [18] proposed an extended version of fuzzy connectivity method to segment the fat and whole muscle areas of thighs as well as brain and whole body tissue using multi-modal MRI images. However, segmenting the challenging task of segmenting different muscles or muscle groups in the absence of substantial intensity differences between muscles is not addressed in this study.…”

“…To overcome these issues, different automatic segmentation methods of MRI images were proposed in the literature. Initial attempts for automatic segmentation of the MR thigh images started with the work of Barra et al [14, 15] where they used intensity differences between tissues to segment the total muscle and fat areas in elderly population and it was further advanced by others to segment subcutaneous adipose tissue (SAT), IMAT and bone areas in obese or elderly populations [16–18]. More recently, various algorithms were proposed to use prior shape information to segment individual thigh muscles in healthy and elderly populations and individuals with chronic diseases [19, 20].…”

Semi-Supervised Deep Learning for Multi-Tissue Segmentation from Multi-Contrast MRI

“…The clustering based techniques worked well for IMAT, but failed to detect the subcutaneous fat. A novel fuzzy connectivity based segmentation method was used for fat and muscle segmentation in thigh images [15]. The method used affinity propagation clustering technique to minimize user intervention in the segmentation process while achieving the-state-of-the-art dice score of 84% and 87% for fat and muscle tissues, respectively.…”

“…The method used affinity propagation clustering technique to minimize user intervention in the segmentation process while achieving the-state-of-the-art dice score of 84% and 87% for fat and muscle tissues, respectively. A comprehensive evaluation of other pre-deep learning era methods can be found here [15].…”

Automatic signal and image-based assessments of spinal cord injury and treatments.

“…contouring method to segment fascia lata to separate SAT and IMAT in severe muscular dystrophy cases. In a recent study, Irmakci et al[101] proposed an extended version of fuzzy connectivity method to segment the fat and whole muscle areas of thighs as well as brain and whole body tissue using multi-modal MRI images. However, segmenting the challenging task of segmenting different muscles or muscle groups in the absence of substantial intensity differences between muscles is not addressed in this study.…”