Automatic quantification of muscle volumes in magnetic resonance imaging scans of the lower extremities.

Muscle volume measurements are essential for an array of diseases ranging from peripheral arterial disease, muscular dystrophies, neurological conditions to sport injuries and aging. In the clinical setting, muscle volume is not routinely measured due to the lack of standardized ways for its repeatable quantification. In this paper, we present magnetic resonance muscle quantification (MRMQ), a method for the automatic quantification of thigh muscle volume in magnetic resonance imaging (MRI) scans. MRMQ integrates a thigh segmentation and nonuniform image gradient correction step, followed by feature extraction and classification. The classification step leverages prior probabilities, introducing prior knowledge to a maximum a posteriori classifier. MRMQ was validated on 344 slices taken from 60 MRI scans. Experiments for the fully automatic detection of muscle volume in MRI scans demonstrated an averaged accuracy, sensitivity and specificity for leave-one-out cross-validation of 88.3%, 93.6% and 87.2%, respectively.

[1]  Yannis Avrithis,et al.  Affine-invariant curve normalization for object shape representation, classification, and retrieval , 2001, Machine Vision and Applications.

[2]  A. Lamminen,et al.  Antimyosin scintigraphy compared with magnetic resonance imaging in inflammatory myopathies. , 1998, Archives of neurology.

[3]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[4]  A. Ryan,et al.  Determinants of peak V(O2) in peripheral arterial occlusive disease patients. , 2000, The journals of gerontology. Series A, Biological sciences and medical sciences.

[5]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[6]  Y. Fur,et al.  Segmentation of fascias, fat and muscle from magnetic resonance images in humans: the DISPIMAG software , 2006, Magnetic Resonance Materials in Physics, Biology and Medicine.

[7]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[8]  Kiyotaka Fukumoto,et al.  Calibration of cross-sectional images measured by an ultrasound-based muscle evaluation system , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[9]  Beatrice A. Golomb,et al.  Peripheral Arterial Disease: Morbidity and Mortality Implications , 2006, Circulation.

[10]  Gérard Gimenez,et al.  MRI intensity nonuniformity correction using simultaneously spatial and gray-level histogram information , 2007, Comput. Medical Imaging Graph..

[11]  M. Giger,et al.  Computerized interpretation of breast MRI: investigation of enhancement-variance dynamics. , 2004, Medical physics.

[12]  A. Lumsden,et al.  Simultaneous bilateral magnetic resonance imaging of the femoral arteries in peripheral arterial disease patients , 2011, Journal of magnetic resonance imaging : JMRI.

[13]  T. Gwinn,et al.  Estimation of thigh muscle cross-sectional area by dual-energy X-ray absorptiometry in frail elderly patients. , 2007, The American journal of clinical nutrition.

[14]  T. Fukubayashi,et al.  Relationship between quadriceps femoris muscle volume and muscle torque after anterior cruciate ligament repair , 2007, Scandinavian journal of medicine & science in sports.

[15]  G. OLaighin,et al.  A Technique for the Computation of Lower Leg Muscle Volume from MRI Images in the context of Venous Return , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  L. Ferrucci,et al.  Lower Extremity Ischemia, Calf Skeletal Muscle Characteristics, and Functional Impairment in Peripheral Arterial Disease , 2007, Journal of the American Geriatrics Society.

[17]  Charles L Rice,et al.  Muscle fiber number in the biceps brachii muscle of young and old men , 2003, Muscle & nerve.

[18]  Kenneth J Hunt,et al.  Effect of detraining on bone and muscle tissue in subjects with chronic spinal cord injury after a period of electrically-stimulated cycling: a small cohort study. , 2009, Journal of rehabilitation medicine.

[19]  Shinto Eguchi,et al.  Robust estimation in the normal mixture model , 2006 .

[20]  A. Emery,et al.  The muscular dystrophies , 2002, The Lancet.

[21]  P. Esselman,et al.  Decline in isokinetic force with age: muscle cross-sectional area and specific force , 1997, Pflügers Archiv.

[22]  John P Slavotinek,et al.  Assessment of physical examination and magnetic resonance imaging findings of hamstring injury as predictors for recurrent injury. , 2006, The Journal of orthopaedic and sports physical therapy.

[23]  A. Lumsden,et al.  Peripheral Arterial Occlusive Disease: Magnetic Resonance Imaging and the Role of Aggressive Medical Management , 2007, World Journal of Surgery.

[24]  F. Aslam,et al.  Peripheral Arterial Disease: Current Perspectives and New Trends in Management , 2009, Southern medical journal.

[25]  P. McBride,et al.  The significance of lower extremity peripheral arterial disease , 2002, Clinical cardiology.

[26]  A. Hicks,et al.  Muscle characteristics and fatigue properties after spinal cord injury. , 2009, Critical reviews in biomedical engineering.

[27]  T. Fukunaga,et al.  Validity of bioelectrical impedance and ultrasonographic methods for estimating the muscle volume of the upper arm , 2000, European Journal of Applied Physiology.

[28]  Samuele M. Marcora,et al.  Bioelectrical impedance can be used to predict muscle mass and hence improve estimation of glomerular filtration rate in non-diabetic patients with chronic kidney disease. , 2006, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[29]  Takashi Abe,et al.  Prediction and validation of total and regional skeletal muscle mass by ultrasound in Japanese adults , 2005, European Journal of Applied Physiology.

[30]  C Sekiguchi,et al.  Effect of short-duration spaceflight on thigh and leg muscle volume. , 2000, Medicine and science in sports and exercise.

[31]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[32]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

[33]  S B Heymsfield,et al.  Cadaver validation of skeletal muscle measurement by magnetic resonance imaging and computerized tomography. , 1998, Journal of applied physiology.

[34]  A. Capaldi.  Analysis of gene function using DNA microarrays. , 2010, Methods in enzymology.

[35]  Duan Xu,et al.  MRI of the spine: image quality and normal-neoplastic bone marrow contrast at 3 T versus 1.5 T. , 2009, AJR. American journal of roentgenology.

[36]  R. Balaban,et al.  Normalized metabolic stress for 31P-MR spectroscopy studies of human skeletal muscle: MVC vs. muscle volume. , 1997, Journal of applied physiology.

[37]  I. Kakadiaris,et al.  Toward the automatic detection of coronary artery calcification in non-contrast computed tomography data , 2010, The International Journal of Cardiovascular Imaging.

[38]  Geoffrey J McLachlan,et al.  Selection bias in gene extraction on the basis of microarray gene-expression data , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[39]  Vincent Barra,et al.  Segmentation of fat and muscle from MR images of the thigh by a possibilistic clustering algorithm , 2002, Comput. Methods Programs Biomed..

[40]  L. Fried,et al.  Asymptomatic peripheral arterial disease is independently associated with impaired lower extremity functioning: the women's health and aging study. , 2000, Circulation.

[41]  John H Challis,et al.  The validity of ultrasound estimation of muscle volumes. , 2007, Journal of applied biomechanics.

[42]  William A Bauman,et al.  Bone and muscle loss after spinal cord injury: organ interactions , 2010, Annals of the New York Academy of Sciences.

[43]  Daniel L. Feeback,et al.  Muscle volume, MRI relaxation times (T2), and body composition after spaceflight. , 2000, Journal of applied physiology.

[44]  Stein Aerts,et al.  Fine-Tuning Enhancer Models to Predict Transcriptional Targets across Multiple Genomes , 2007, PloS one.

[45]  Yanxi Liu,et al.  Discriminative MR Image Feature Analysis for Automatic Schizophrenia and Alzheimer's Disease Classification , 2004, MICCAI.

[46]  L. Ferrucci,et al.  Pathophysiological Changes in Calf Muscle Predict Mobility Loss at 2-Year Follow-Up in Men and Women With Peripheral Arterial Disease , 2009, Circulation.

[47]  F. Cicuttini,et al.  Physical activity and knee structural change: a longitudinal study using MRI. , 2007, Medicine and science in sports and exercise.

[48]  Andrew C Larson,et al.  Self‐gated cardiac cine MRI , 2004, Magnetic resonance in medicine.

[49]  Susan C. Brown,et al.  Investigating the pathology of Emery-Dreifuss muscular dystrophy. , 2008, Biochemical Society transactions.

[50]  L C Ward,et al.  Predicting composition of leg sections with anthropometry and bioelectrical impedance analysis, using magnetic resonance imaging as reference. , 1999, Clinical science.

[51]  Alexander J. Smola,et al.  Classification in a normalized feature space using support vector machines , 2003, IEEE Trans. Neural Networks.

[52]  Pierre Abraham,et al.  Measurement of Walking Distance and Speed in Patients With Peripheral Arterial Disease: A Novel Method Using a Global Positioning System , 2008, Circulation.

[53]  P. Chérin,et al.  Apport de l'IRM musculaire dans les myopathies inflammatoires , 2004 .

[54]  Robert M. Haralick,et al.  Feature normalization and likelihood-based similarity measures for image retrieval , 2001, Pattern Recognit. Lett..

[55]  T. Abe,et al.  Increases in thigh muscle volume and strength by walk training with leg blood flow reduction in older participants. , 2011, The journals of gerontology. Series A, Biological sciences and medical sciences.

[56]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[57]  K. Uğurbil,et al.  Efficient high‐frequency body coil for high‐field MRI , 2004, Magnetic resonance in medicine.

[58]  K. McCully,et al.  The application of blood flow measurements to the study of aging muscle. , 1995, The journals of gerontology. Series A, Biological sciences and medical sciences.

[59]  Luis Garcia,et al.  Rescue of Dystrophic Muscle Through U7 snRNA-Mediated Exon Skipping , 2004, Science.