“Radiologists often examine x-rays of cervical, thoracic and lumbar vertebrae for determining the presence of osteoarthritis and osteoporosis. There are several features used to assess whether a vertebra is normal such as the height contrast in the anterior and posterior sides. Vertebral distortion along the anterior boundary can also be used as an indicator of vertebra normality. The vertebral boundary increasingly deviates from the general rectangular shape as the vertebra becomes less normal in appearance. For abnormal vertebrae, bony growths (“osteophytes”) may appear at the vertebral comers. This research introduces image processing techniques for computing size-invariant features from lumbar spine vertebrae for detecting anterior osteophytes. Four size invariant features based on the vertebral convex hull are investigated for highlighting anterior osteophytes to differentiate normal from abnormal vertebrae. A multi-layer perceptron-based approach is used for feature evaluation of 714 lumbar spine vertebrae. Experimental results yield an average correct recognition of 90.5% of abnormal vertebrae and 86.6% correct normal vertebrae classification."--Abstract, page iii.
Stanley, R. Joe
Moss, Randy Hays, 1953-
Stoecker, William V.
Electrical and Computer Engineering
M.S. in Computer Engineering
University of Missouri--Rolla
vii, 27 pages
© 2003 Maruthi Cherukuri, All rights reserved.
Thesis - Restricted Access
Computer vision in medicine
Osteoarthritis -- Diagnosis -- Research
Print OCLC #
Link to Catalog Record
Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.http://merlin.lib.umsystem.edu/record=b5069802~S5
Cherukuri, Maruthi, "Anterior osteophyte detection in lumbar vertebrae using size-invariant features" (2003). Masters Theses. 2366.
Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.