Segmentation of fat and muscle from MR images of the thigh by a possibilistic clustering algorithm

Physical training is proved to induce changes in physical capacity and body composition. We propose in this article a fast, unsupervised and fully three-dimensional automatic method to extract muscle and fat volumes from magnetic resonance images of thighs in order to assess these changes. The technique relies on the use of a fuzzy clustering algorithm and post-processings to accurately process the body composition of thighs. Results are compared on 11 healthy voluntary elderly people with those provided on the same data by a validated method already published, and its reliability is assessed on repeated measures on three subjects. The two methods statistically agree when computing muscle and fat volumes, and clinical implications of this fully automatic method are important for medicine, physical conditioning, weight-loss programs and predictions of optimal body weight.

[1]  W. Totty,et al.  Measurement of fat distribution by magnetic resonance imaging. , 1989, Investigative radiology.

[2]  V. Frouin,et al.  Body composition determined with MR in patients with Duchenne muscular dystrophy, spinal muscular atrophy, and normal subjects. , 1997, Magnetic resonance imaging.

[3]  James M. Keller,et al.  The possibilistic C-means algorithm: insights and recommendations , 1996, IEEE Trans. Fuzzy Syst..

[4]  J Coudert,et al.  Effects of 14 weeks of progressive endurance training on energy expenditure in elderly people , 1998, British Journal of Nutrition.

[5]  Jean-Yves Boire,et al.  Automatic assessment of muscle/fat temporal variations on MR images of the thigh , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  Jean-Yves Boire,et al.  Automatic muscle/fat quantification on MR images , 1995, Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.

[7]  A Colin,et al.  A novel tool for rapid prototyping and development of simple 3D medical image processing applications on PCs. , 1997, Computer methods and programs in biomedicine.

[8]  D. Altman,et al.  STATISTICAL METHODS FOR ASSESSING AGREEMENT BETWEEN TWO METHODS OF CLINICAL MEASUREMENT , 1986, The Lancet.

[9]  E De Kerviler,et al.  MR quantification of muscle fatty replacement in McArdle's disease. , 1996, Magnetic resonance imaging.

[10]  Vito Di Gesù,et al.  An application of integrated clustering to MRI segmentation , 1994, Pattern Recognit. Lett..

[11]  M D Jensen,et al.  Measuring leg muscle and fat mass in humans: comparison of CT and dual-energy X-ray absorptiometry. , 2000, Journal of applied physiology.

[12]  James M. Keller,et al.  A possibilistic approach to clustering , 1993, IEEE Trans. Fuzzy Syst..

[13]  R. Ross,et al.  Adipose tissue distribution measured by magnetic resonance imaging in obese women. , 1993, The American journal of clinical nutrition.

[14]  Steven B. Heymsfield,et al.  Body composition and aging: a study by in vivo neutron activation analysis. , 1993, The Journal of nutrition.

[15]  R M Peshock,et al.  Estimation of adipose tissue mass by magnetic resonance imaging: validation against dissection in human cadavers. , 1994, Journal of lipid research.

[16]  Vincent Barra,et al.  Benefit of endurance training in elderly people over a short period is reversible , 2000, European Journal of Applied Physiology.

[17]  J. P. Miller,et al.  Effects of strength training on total and regional body composition in older men. , 1994, Journal of applied physiology.

[18]  G Zuccoli,et al.  [An assessment of abdominal fatty tissue distribution in obese children. A comparison between echography and computed tomography]. , 1999, La Radiologia medica.

[19]  David H. Laidlaw,et al.  Partial-volume Bayesian classification of material mixtures in MR volume data using voxel histograms , 1997, IEEE Transactions on Medical Imaging.

[20]  M F Fuller,et al.  Imaging techniques for the assessment of body composition. , 1994, The Journal of nutrition.