Please use this identifier to cite or link to this item:
Title: Interactive system for measurement of cervical and lumbar spine from digital radiographs
Authors: Bai, Zhong Yang
Keywords: DRNTU::Science::Medicine::Optical instruments
Issue Date: 2010
Abstract: The objective of this project is to develop an interactive system capable of measuring cervical and lumbar vertebral body and disc heights, the Cobb angle as well as sagittal plane displacements that can be used for clinical analysis. Although X-ray imaging technology provides a non-invasive and accurate diagnosis of spine injuries and the data acquired from the radiographs can be useful, the images require interpretation by trained personnel. And the process of manual measurements can be time consuming. Therefore, an interactive system is needed to aid radiologists and/or surgeons in handling the large volumes of X-ray images. Since the vertebral is mainly make up of hard tissue therefore it have good contrast with its surrounding tissue in X-ray images, which makes it relatively prominent to identify it – an algorithm which can achieve such automated system has not been documented to date. The present algorithm developed in this project is implemented using MATLAB, and uses mathematical morphology to detect Harris feature points to improve the results‘ precision with minimal supervision, allowing the algorithm to take advantage of the vertebral unique shape and orientation within the image. The results were compared against those that did not use Harris feature to determine the accuracy and reproducibility of the results by performing an intra and inter observers‘ test; where high accuracy and reproducibility have been achieved.
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
1.63 MBAdobe PDFView/Open

Page view(s) 20

checked on Oct 26, 2020

Download(s) 20

checked on Oct 26, 2020

Google ScholarTM


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