Quantitative texture analysis of MRI images for detection of cartilage-related bone marrow edema

• Published in: 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society Vol. 2011; pp. 5112 - 5115
• Main Authors: Tong Kuan Chuah, Chueh Loo Poh, Sheah, K.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.01.2011
• Subjects: Adult; Algorithms; Bone Marrow Diseases - pathology; Bones; Cartilage, Articular - pathology; Edema - pathology; Female; Fluids; Histograms; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image segmentation; Imaging, Three-Dimensional - methods; Knee Joint - pathology; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; Osteoarthritis; Pattern Recognition, Automated - methods; Reproducibility of Results; Rheumatic Diseases - pathology; Sensitivity and Specificity; Three dimensional displays
• ISBN: 9781424441211; 1424441218
• ISSN: 1094-687X; 1557-170X; 1558-4615
• DOI: 10.1109/IEMBS.2011.6091266

This paper presents a study that investigated the potential of texture analysis using Fluid Sensitive Fat Suppressed MRI images for the use in detection of bone marrow edema. A total of 168 slices of knee MRI from 10 subjects were involved. Six histogram-based textures (mean intensity, standard deviation, smoothness, third moment, uniformity and entropy) were calculated in both 2D and 3D, and were compared between healthy group and group affected by bone marrow edema. Two-sample t-tests were performed to assess the difference between healthy group and group affected by edema. The intensity third moment in 2D showed significant difference between the slices of healthy subjects and the slices affected by edema (p<;0.05). Smoothness and standard deviation in 2D showed a modest significance between healthy and affected groups. No significant difference was found in the 3D textures of healthy group and group affected by edema.