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

Ismail Irmakci, Sarfaraz Hussein, Aydogan Savran, Rita R. Kalyani, David Reiter, Chee W. Chia, Kenneth Fishbein, Richard G. Spencer, Luigi Ferrucci, Ulas Bagci

Research output: Contribution to journalArticle

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.

Original languageEnglish (US)
JournalIEEE Transactions on Biomedical Engineering
DOIs
StateAccepted/In press - Aug 29 2018

Fingerprint

Brain
Tissue
Chemical analysis
Oils and fats
Image segmentation
Magnetic resonance imaging
Muscle
Ionizing radiation
Clustering algorithms

Keywords

  • Affinity Propagation
  • Brain tissue segmentation
  • Fat Quantification
  • Fat Segmentation
  • MRI
  • Muscle Quantification
  • Muscle Segmentation
  • Whole-body tissue classification

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

A Novel Extension to Fuzzy Connectivity for Body Composition Analysis : Applications in Thigh, Brain, and Whole Body Tissue Segmentation. / Irmakci, Ismail; Hussein, Sarfaraz; Savran, Aydogan; Kalyani, Rita R.; Reiter, David; Chia, Chee W.; Fishbein, Kenneth; Spencer, Richard G.; Ferrucci, Luigi; Bagci, Ulas.

In: IEEE Transactions on Biomedical Engineering, 29.08.2018.

Research output: Contribution to journalArticle

Irmakci, Ismail ; Hussein, Sarfaraz ; Savran, Aydogan ; Kalyani, Rita R. ; Reiter, David ; Chia, Chee W. ; Fishbein, Kenneth ; Spencer, Richard G. ; Ferrucci, Luigi ; Bagci, Ulas. / A Novel Extension to Fuzzy Connectivity for Body Composition Analysis : Applications in Thigh, Brain, and Whole Body Tissue Segmentation. In: IEEE Transactions on Biomedical Engineering. 2018.
@article{9a7965052ebe465cb43c004165c2d48a,
title = "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.",
keywords = "Affinity Propagation, Brain tissue segmentation, Fat Quantification, Fat Segmentation, MRI, Muscle Quantification, Muscle Segmentation, Whole-body tissue classification",
author = "Ismail Irmakci and Sarfaraz Hussein and Aydogan Savran and Kalyani, {Rita R.} and David Reiter and Chia, {Chee W.} and Kenneth Fishbein and Spencer, {Richard G.} and Luigi Ferrucci and Ulas Bagci",
year = "2018",
month = "8",
day = "29",
doi = "10.1109/TBME.2018.2866764",
language = "English (US)",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - A Novel Extension to Fuzzy Connectivity for Body Composition Analysis

T2 - Applications in Thigh, Brain, and Whole Body Tissue Segmentation

AU - Irmakci, Ismail

AU - Hussein, Sarfaraz

AU - Savran, Aydogan

AU - Kalyani, Rita R.

AU - Reiter, David

AU - Chia, Chee W.

AU - Fishbein, Kenneth

AU - Spencer, Richard G.

AU - Ferrucci, Luigi

AU - Bagci, Ulas

PY - 2018/8/29

Y1 - 2018/8/29

N2 - 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.

AB - 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.

KW - Affinity Propagation

KW - Brain tissue segmentation

KW - Fat Quantification

KW - Fat Segmentation

KW - MRI

KW - Muscle Quantification

KW - Muscle Segmentation

KW - Whole-body tissue classification

UR - http://www.scopus.com/inward/record.url?scp=85052634270&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85052634270&partnerID=8YFLogxK

U2 - 10.1109/TBME.2018.2866764

DO - 10.1109/TBME.2018.2866764

M3 - Article

C2 - 30176577

AN - SCOPUS:85052634270

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

ER -