Automated detection of stable fracture points in computed tomography image sequences

Automated detection of stable fracture points in a sequence of Computed Tomography (CT) images is found to be a challenging task. In this paper, an innovative scheme for automatic fracture detection in CT images is presented. The input to the system is a sequence of CT image slices of a fractured human mandible. Techniques from the curvature scale-space theory and graph based filtering (using prior anatomical knowledge) to first detect candidate fracture points in the individual CT slices. Subsequently, a Kalman filter incorporating a Bayesian perspective is used for testing the consistency of the candidate fracture points across all the CT slices in a given sequence. For the purpose of checking statistical consistency, both 95% and 99% high posterior density (HPD) prediction intervals are constructed. A spatial consistency term is coined for each candidate fracture point in terms of the number of slices in the CT image sequence, the number of times a fracture point detected in that s...

• Type: Conference
• Year: 2006
• Where: ISBI
• Authors: Ananda S. Chowdhury, Suchendra M. Bhandarkar, Gauri Datta, Jack C. Yu
• Keywords: Candidate Fracture Point, Ct Image, Fracture Points, ISBI 2006, Medical Imaging