Paper Info
Title
Computerized method for detection of vertebral fractures on lateral chest radiographs based on morphometric data
Abstract
Vertebral fractures are the most common osteoporosis-related fractures. It is important to detect vertebral fractures because they are associated with an increased risk of subsequent fractures, and because pharmacologic therapy can reduce the risk of such subsequent fractures. Although vertebral fractures are often not recognized clinically, they can be visualized on lateral chest radiographs taken for other purposes. However, only 15-60% of vertebral fractures found on lateral chest radiographs are mentioned in radiology reports. Our purpose in this study was to develop a computerized method for detection of vertebral fractures on lateral chest radiographs in order to assist radiologists' image interpretation. Our computerized method is based on the automated identification of upper and lower vertebral edges on lateral chest radiographs. In order to facilitate the development of the scheme, radiologists studied 25 normals and 20 cases with severe fractures, providing morphometric data for each identifiable vertebra, which consisted of six points for each vertebra. Anatomic information was obtained from the morphometric data on normal cases in terms of vertebral heights, distances of vertebral disk spaces, and the vertebral centerline. Computerized detection of vertebral fractures was based on a reduction in the heights of fractured vertebrae compared to those of adjacent vertebrae and normal reference data. Vertebral heights from morphometric data on normal cases were used as reference. On 138 lateral chest radiographs (including the 20 with fractures), the sensitivity and the specificity of our method for detection of fracture cases were 95% (19/20) and 43.5% (50/118), respectively, with 0.90 (124/138) false-positives per image. In conclusion, the computerized method would be useful for detection of potentially overlooked vertebral fractures on lateral chest radiographs.
Year
DOI
Venue
2007
10.1117/12.706533
Proceedings of SPIE
Keywords
Field
DocType
quantitative image analysis,Modalities : digital radiography,Diagnostic Task : detection
Lateral chest,Radiography,Vertebra,Radiology,Pharmacologic therapy,Medicine
Conference
Volume
ISSN
Citations 
6514
0277-786X
0
PageRank 
References 
Authors
0.34
0
8
Name
Order
Citations
PageRank
satoshi kasai100.68
Feng Li233849.66
Junji Shiraishi3198.08
Qiang Li44512.17
christopher m straus500.34
Tamara J. Vokes621.55
Heber MacMahon720231.61
Kunio Doi8358.75