Automated assessment of thigh composition using machine learning for Dixon magnetic resonance images

Yang, Yu; Chong, Mei Sian; Tay, Laura; Yew, Suzanne; Yeo, Audrey; Tan, Cher Heng

doi:10.1007/s10334-016-0547-2

Cited by 36 publications

(33 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This difference between two readers is consistent with results from previous studies that reported an interobserver variability between manual segmentations of two different readers of 18.4/ 14.7% for the IMF, before/after quality control, respectively [45]. Yet, the DSC observed for IMF using data from the same reader compares quite favorable to the literature, while the DSC achieved with data from the 2nd reader is still comparable with the best achieved results of 0.80 in a study of Yang et al using DIXON MRIs [22]. Further, since the observed effect was systematic and therefore similar for all patients, measuring (side) differences or longitudinal change in the IMF may not be strongly affected.…”

Section: Discussionsupporting

confidence: 63%

“…There exist several semi-automated [16][17][18][19][20][21] and fully automated [22][23][24][25] tools for thigh tissue volume and CSA segmentation to overcome the challenges in capturing the complex morphology and texture of thigh muscle and adipose tissue that are complicated by considerable intersubject variability ( Fig. 1) and potentially also artefacts as intensity distortions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain

Kemnitz

Baumgartner

Eckstein

et al. 2019

Magn Reson Mater Phy

View full text Add to dashboard Cite

Objective Segmentation of thigh muscle and adipose tissue is important for the understanding of musculoskeletal diseases such as osteoarthritis. Therefore, the purpose of this work is (a) to evaluate whether a fully automated approach provides accurate segmentation of muscles and adipose tissue cross-sectional areas (CSA) compared with manual segmentation and (b) to evaluate the validity of this method based on a previous clinical study. Materials and methods The segmentation method is based on U-Net architecture trained on 250 manually segmented thighs from the Osteoarthritis Initiative (OAI). The clinical evaluation is performed on a hold-out test set bilateral thighs of 48 subjects with unilateral knee pain. Results The segmentation time of the method is < 1 s and demonstrated high agreement with the manual method (dice similarity coeffcient: 0.96 ± 0.01). In the clinical study, the automated method shows that similar to manual segmentation (− 5.7 ± 7.9%, p < 0.001, effect size: 0.69), painful knees display significantly lower quadriceps CSAs than contralateral painless knees (− 5.6 ± 7.6%, p < 0.001, effect size: 0.73). Discussion Automated segmentation of thigh muscle and adipose tissues has high agreement with manual segmentations and can replicate the effect size seen in a clinical study on osteoarthritic pain.

show abstract

Section: Discussionsupporting

confidence: 63%

Section: Introductionmentioning

confidence: 99%

Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain

Kemnitz

Baumgartner

Eckstein

et al. 2019

Magn Reson Mater Phy

View full text Add to dashboard Cite

show abstract

“…9,10 It is interesting that in elderly subjects, muscle mass declines at a slower rate than strength, emphasizing a strong role of muscle fat infiltration and potentially of the amount of perimuscular fat. A number of diagnostic techniques mostly based on magnetic resonance imaging (MRI) have been introduced [11][12][13][14] for the assessment of fat. In the present study, multi-point T 2 *-corrected Dixon MRI and multi-echo T 2 -corrected magnetic resonance spectroscopy (MRS) were used to measure proton density fat fraction (PDFF) and proton density water fraction (PDWF) while minimizing MR-specific effects.…”

Section: Introductionmentioning

confidence: 99%

Repeatability of Dixon magnetic resonance imaging and magnetic resonance spectroscopy for quantitative muscle fat assessments in the thigh

Grimm

Meyer

Nickel

et al. 2018

J cachexia sarcopenia muscle

View full text Add to dashboard Cite

BackgroundChanges in muscle fat composition as for example observed in sarcopenia or muscular dystrophy affect physical performance and muscular function, like strength and power. The purpose of the present study is to measure the repeatability of Dixon magnetic resonance imaging (MRI) for assessing muscle volume and fat in the thigh. Furthermore, repeatability of magnetic resonance spectroscopy (MRS) for assessing muscle fat is determined.MethodsA prototype 6‐point Dixon MRI method was used to measure muscle volume and muscle proton density fat fraction (PDFF) in the left thigh. PDFF was measured in musculus semitendinosus of the left thigh with a T2‐corrected multi‐echo MRS method. For the determination of short‐term repeatability (consecutive examinations), the root mean square coefficients of variation of Dixon MRI and MRS data of 23 young and healthy (29 ± 5 years) and 24 elderly men with sarcopenia (78 ± 5 years) were calculated. For the estimation of the long‐term repeatability (13 weeks between examinations), the root mean square coefficients of variation of MRI data of seven young and healthy (31 ± 7 years) and 23 elderly sarcopenic men (76 ± 5 years) were calculated. Long‐term repeatability of MRS was not determined.ResultsShort‐term errors of Dixon MRI volume measurement were between 1.2% and 1.5%, between 2.1% and 1.6% for Dixon MRI PDFF measurement, and between 9.0% and 15.3% for MRS. Because of the high short‐term repeatability errors of MRS, long‐term errors were not determined. Long‐term errors of MRI volume measurement were between 1.9% and 4.0% and of Dixon MRI PDFF measurement between 2.1% and 4.2%.ConclusionsThe high degree of repeatability of volume and PDFF Dixon MRI supports its use to predict future mobility impairment and measures the success of therapeutic interventions, for example, in sarcopenia in aging populations and muscular dystrophy. Because of possible inhomogeneity of fat infiltration in muscle tissue, the application of MRS for PDFF measurements in muscle is more problematic because this may result in high repeatability errors. In addition, the tissue composition within the MRS voxel may not be representative for the whole muscle.

show abstract

“…Andrews et al employed a probabilistic shape representation for the segmentation of the thigh muscle heads and reported a mean DSC of 0.81 ± 0.07 [ 28 ]. Using a voxel classifier-based technology combined with morphological operations for the segmentation of thigh muscles and adipose tissue, Yang et al [ 26 ] reported DSCs of 0.96 ± 0.03 for the SCF, 0.80 ± 0.03 for the IMF and 0.97 ± 0.01 for the combined thigh muscles (quadriceps, hamstrings, adductors and sartorius) when the algorithm was applied to four contrast Dixon MR images and somewhat lower DSCs when the algorithm was applied to fat and water suppressed (SCF 0.94 ± 0.04, IMF 0.68 ± 0.10 and combined thigh muscle 0.96 ± 0.03) or unsuppressed (SCF 0.80 ± 0.10, IMF 0.37 ± 0.13 and combined thigh muscle 0.73 ± 0.21) MR images only. Karlsson et al used a multi-atlas segmentation approach to automatically segment the lean muscle tissue from whole body intensity corrected water-fat separated MRIs and reported a true positive volume fraction of 0.93 ± 0.01 to 0.93 ± 0.03 for the automated thigh segmentation [ 29 ].…”

Section: Discussionmentioning

confidence: 99%

Validation of an active shape model-based semi-automated segmentation algorithm for the analysis of thigh muscle and adipose tissue cross-sectional areas

Kemnitz

Eckstein

Culvenor

et al. 2017

Magn Reson Mater Phy

View full text Add to dashboard Cite

ObjectiveTo validate a semi-automated method for thigh muscle and adipose tissue cross-sectional area (CSA) segmentation from MRI.Materials and methodsAn active shape model (ASM) was trained using 113 MRI CSAs from the Osteoarthritis Initiative (OAI) and combined with an active contour model and thresholding-based post-processing steps. This method was applied to 20 other MRIs from the OAI and to baseline and follow-up MRIs from a 12-week lower-limb strengthening or endurance training intervention (n = 35 females). The agreement of semi-automated vs. previous manual segmentation was assessed using the Dice similarity coefficient and Bland-Altman analyses. Longitudinal changes observed in the training intervention were compared between semi-automated and manual segmentations.ResultsHigh agreement was observed between manual and semi-automated segmentations for subcutaneous fat, quadriceps and hamstring CSAs. With strength training, both the semi-automated and manual segmentation method detected a significant reduction in adipose tissue CSA and a significant gain in quadriceps, hamstring and adductor CSAs. With endurance training, a significant reduction in adipose tissue CSAs was observed with both methods.ConclusionThe semi-automated approach showed high agreement with manual segmentation of thigh muscle and adipose tissue CSAs and showed longitudinal training effects similar to that observed using manual segmentation.Electronic supplementary materialThe online version of this article (doi:10.1007/s10334-017-0622-3) contains supplementary material, which is available to authorized users.

show abstract

Automated assessment of thigh composition using machine learning for Dixon magnetic resonance images

Abstract: Our proposed method based on machine learning produces accurate tissue quantification and showed an effective use of large information provided by the four contrast images from Dixon MRI.

Cited by 36 publications

References 27 publications

Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain

Clinical evaluation of fully automated thigh muscle and adipose tissue segmentation using a U-Net deep learning architecture in context of osteoarthritic knee pain

Repeatability of Dixon magnetic resonance imaging and magnetic resonance spectroscopy for quantitative muscle fat assessments in the thigh

Validation of an active shape model-based semi-automated segmentation algorithm for the analysis of thigh muscle and adipose tissue cross-sectional areas

Contact Info

Product

Resources

About