The full text of this item is not available at this time because the student has placed this item under an embargo for a period of time. The Libraries are not authorized to provide a copy of this work during the embargo period, even for Texas A&M users with NetID.
Automatic Canine Muscle Histology Image Segmentation Based on RGB Histogram
MetadataShow full item record
Duchenne muscular dystrophy is a fatal, congenital disease affecting males. Histopathological methods have served to aid in its diagnosis; however, the ratio of skeletal muscle tissue constituents—a theoretical marker of the disease—has yet to be rigorously quantified. An automatic histology image segmentation algorithm was developed in this work to quantify the collagen to muscle fiber ratio occurring in 11 muscle samples from golden retriever muscular dystrophic animals. Preliminary artifact removal and segmentation of myosatellite cells was included. Additionally, the effect of altering the processing resolution was studied on the outcome of the collagen to muscle ratio. In comparison with estimations from a repurposed industry software, Aperio ImageScope, the custom algorithm was faster and less susceptible to artifact. However, processing resolution increased execution time and had significant effects on the collagen to muscle ratio for both algorithms. An optimal processing resolution was suggested.
McConnell, Stephen Craig (2017). Automatic Canine Muscle Histology Image Segmentation Based on RGB Histogram. Master's thesis, Texas A & M University. Available electronically from