Aydin Eresen1, Noor E Hafsa2, Lejla Alic2,3, Sharla M Birch4, John F Griffin4, Joe N Kornegay4, Jim X Ji1,2. 1. Department of Electrical and Computer Engineering, Texas A&M University, College Station, Texas. 2. Department of Electrical and Computer Engineering, Texas A&M University, Doha, Qatar. 3. Magnetic Detection & Imaging Group, Faculty of Science & Technology, University of Twente, Enschede, The Netherlands. 4. College of Veterinary Medicine and Biomedical Sciences, Texas A&M University, College Station, Texas.
Abstract
INTRODUCTION: Golden retriever muscular dystrophy (GRMD) is a spontaneous X-linked canine model of Duchenne muscular dystrophy that resembles the human condition. Muscle percentage index (MPI) is proposed as an imaging biomarker of disease severity in GRMD. METHODS: To assess MPI, we used MRI data acquired from nine GRMD samples using a 4.7 T small-bore scanner. A machine learning approach was used with eight raw quantitative mapping of MRI data images (T1m, T2m, two Dixon maps, and four diffusion tensor imaging maps), three types of texture descriptors (local binary pattern, gray-level co-occurrence matrix, gray-level run-length matrix), and a gradient descriptor (histogram of oriented gradients). RESULTS: The confusion matrix, averaged over all samples, showed 93.5% of muscle pixels classified correctly. The classification, optimized in a leave-one-out cross-validation, provided an average accuracy of 80% with a discrepancy in overestimation for young (8%) and old (20%) dogs. DISCUSSION: MPI could be useful for quantifying GRMD severity, but careful interpretation is needed for severe cases.
INTRODUCTION:Golden retriever muscular dystrophy (GRMD) is a spontaneous X-linked canine model of Duchenne muscular dystrophy that resembles the human condition. Muscle percentage index (MPI) is proposed as an imaging biomarker of disease severity in GRMD. METHODS: To assess MPI, we used MRI data acquired from nine GRMD samples using a 4.7 T small-bore scanner. A machine learning approach was used with eight raw quantitative mapping of MRI data images (T1m, T2m, two Dixon maps, and four diffusion tensor imaging maps), three types of texture descriptors (local binary pattern, gray-level co-occurrence matrix, gray-level run-length matrix), and a gradient descriptor (histogram of oriented gradients). RESULTS: The confusion matrix, averaged over all samples, showed 93.5% of muscle pixels classified correctly. The classification, optimized in a leave-one-out cross-validation, provided an average accuracy of 80% with a discrepancy in overestimation for young (8%) and old (20%) dogs. DISCUSSION: MPI could be useful for quantifying GRMD severity, but careful interpretation is needed for severe cases.