A Novel Framework for Pelvic Bone Fracture Detection using Computed Tomography Images

Medical images such asComputed Tomography (CT) images contain a significantamount of information, and it is crucial for physicians tomake diagnostic decisions as well as treatment planning onthe basis of this information and other patients‟ data. Currently,a large portion of the data is not optimally and comprehensivelyutilized, because information held in the data isinaccessible through visual observation or simple traditionalcomputationalmethods. Information contained in pelvic CTimages is a very important resource for the assessment of theseverity and prognosis of the injuries. Each pelvic CT scan consists of several slices; each slice contains a large amount ofdata that may not be thoroughly and accurately analyzed viavisual inspection. In addition, in the field of trauma, physiciansfrequently need to make quick decisions based on largeamount of information.From the experimental results, it is evident that the proposed model produces images, which are visually clean and smooth, in fast manner.