Sungjun Kim, Presenter: Nothing to Disclose

Kwanggi Kim PhD, Abstract Co-Author: Nothing to Disclose

Jinah Park, Abstract Co-Author: Nothing to Disclose

Jaeil Kim, Abstract Co-Author: Nothing to Disclose

Young Han Lee MD, Abstract Co-Author: Nothing to Disclose

Ho-Taek Song MD, Abstract Co-Author: Nothing to Disclose

Jin-Suck Suh MD, Abstract Co-Author: Nothing to Disclose

To propose a method to quantify the local texture and shape changes of ribs caused by rib fracture in chest radiographs.

Our measurement method consists of two steps: (1) measurement area assignment and sampling step using a spline curve and sampling lines orthogonal to the spline curve, and (2) fracture-ness measurement step with three measures, asymmetry and Gray-level Co-occurrence Matrix based measures (contrast and homogeneity). They were designed to quantify the symmetric characteristics of ribs along the centerline. The discriminating ability of our method was evaluated through region of interest (ROI) analysis and rib fracture classification test using support vector machine.

The statistically significant difference was found between the measured values from fracture ROIs and normal ROIs; asymmetry (P < 0.0001), contrast (P < 0.001) and homogeneity (P = 0.022). The rib fracture classifier, trained with the measured values in ROI analysis, detected every rib fracture from chest radiographs used for ROI analysis, but it also classified some unbroken parts of ribs as abnormal parts (8 ~ 17 line sets, Length of each line set: 2.998±2.652 mm, Length of centerlines: 131.067±29.460 mm).

Our measurement method, which includes the flexible measurement technique for the curved shape of ribs and the proposed shape and texture measures, could discriminate the suspicious region of ribs for possible rib fractures in chest radiographs.

With the use of the proposed method, routine screening of rib fracture on digital chest radiographs would become more feasible.

Kim, S, Kim, K, Park, J, Kim, J, Lee, Y, Song, H, Suh, J, A Quantitative Measurement Method Using Shape and Texture Features for Possible Rib Fractures in Chest Radiographs.  Radiological Society of North America 2012 Scientific Assembly and Annual Meeting, November 25 - November 30, 2012 ,Chicago IL. http://archive.rsna.org/2012/12031703.html