KMID : 0603720130190030196
|
|
Journal of Korean Society of Medical Informatics 2013 Volume.19 No. 3 p.196 ~ p.204
|
|
Quantitative Measurement Method for Possible Rib Fractures in Chest Radiographs
|
|
Kim Jae-Il
Kim Sung-Jun Kim Young-Jae Kim Kwang-Gi Park Jin-Ah
|
|
Abstract
|
|
|
Objectives: Th is paper proposes a measurement method to quantify the abnormal characteristics of the broken parts of ribs using local texture and shape features in chest radiographs. Methods: Our measurement method comprises two steps: a mea-surement area assignment and sampling step using a spline curve and sampling lines orthogonal to the spline curve, and a fracture-ness measurement step with three measures, asymmetry and gray-level co-occurrence matrix based measures (contrast and homogeneity). Th ey were designed to quantify the regional shape and texture features of ribs along the centerline. Th e discriminating ability of our method was evaluated through region of interest (ROI) analysis and rib fracture classifi cation test using support vector machine. Results: Th e statistically signifi cant diff erence was found between the measured values from fracture and normal ROIs; asymmetry (p < 0.0001), contrast (p < 0.001), and homogeneity (p = 0.022). Th e rib fracture classifi er, trained with the measured values in ROI analysis, detected every rib fracture from chest radiographs used for ROI analysis, but it also classifi ed some unbroken parts of ribs as abnormal parts (8 to 17 line sets; length of each line set, 2.998 ¡¾ 2.652 mm; length of centerlines, 131.067 ¡¾ 29.460 mm). Conclusions: Our measurement method, which includes a fl exible measurement technique for the curved shape of ribs and the proposed shape and texture measures, could discriminate the suspicious regions of ribs for possible rib fractures in chest radiographs.
|
|
KEYWORD
|
|
Rib Fractures, Radiography, Computer-Aided Radiographic Image Interpretation, Image Processing, Decision Support Techniques
|
|
FullTexts / Linksout information
|
|
|
|
Listed journal information
|
|
|
|