Please use this identifier to cite or link to this item:
Title: Medical image processing and analysis of MRI images for sarcopenia detection
Authors: Mohan, Divya
Keywords: DRNTU::Engineering::Bioengineering
Issue Date: 2015
Abstract: Sarcopenia is the degenerative loss of skeletal muscle mass (0.5–1.0% loss per year after the age of 50), quality, and strength associated with aging. It is characterized initially by muscle atrophy (a decrease in the size of the muscle), along with a reduction in muscle tissue quality, evident from such factors as replacement of muscle fibres with fat. It is thus becoming increasingly important to quantify the fat infiltrates within the muscle in order to determine how healthy the individual is. Since Sarcopenia is still just being understood, this analysis of the fat infiltrates in the muscle could add significantly to our knowledge on this condition. Currently, the only method extensively used for separating fat infiltrates from muscle is manual segmentation. This is incredibly time consuming and inefficient and leaves a lot of room for bias and error. Thus, the need for semi-automatic and automatic segmentation becomes very evident. The aim of this project is to completely automate the segmentation of fat infiltrates from muscle using Matlab programming. The approach taken to achieve this aim was to implement a Snake active contour program through Matlab. Once implemented, any source of inaccuracy was identified and rectified as much as possible. Further, the program was made user-friendly so as to minimize human error, as well as to make the program more accessible to new users. On addition of all the changes, the program now became almost entirely automated, and accessible to any user.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCBE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
2.23 MBAdobe PDFView/Open

Page view(s)

Updated on Apr 15, 2021


Updated on Apr 15, 2021

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.