Computer vision-guided virtual craniofacial surgery
Chowdhury, Ananda Shankar
MetadataShow full item record
Craniofacial fractures are very frequent in the present society, the major causes being gunshot wounds, motor vehicle accidents and sports related injuries. The surgical reconstruction is challenging because the surgeons have to accurately register the broken fragments within a limited amount of time. Detection of the fractures, the other integral component of any surgical process, often becomes difficult because of the fracture pattern, intensity inhomogeneity, and noise. In this thesis we explore the reconstruction and detection of craniofacial fractures using computer vision. Within the broad class of craniofacial fractures, our emphasis is on mandibular fractures. A typical input for us is a sequence of Computed Tomography (CT) images of a fractured human mandible. In chapter 1, we discuss in detail the overall significance of our work and the lay-out of this thesis. Chapter 2 is devoted to different aspects of virtual single fracture reconstruction, including the use of bipartite graph matching for establishment of correspondence in the Iterative Closest Point (ICP) algorithm, various means of improving the registration error from the ICP algorithm, exploration of anatomical symmetry and biomechanical stability of the human mandible in the reconstruction process, etc. In Chapter 3, the problem of virtual multi-fracture reconstruction, which resembles the assembly of a 3D jigsaw puzzle, is shown to have an worst case exponential time complexity. The problem is modeled as one of maximum weight graph matching, which even in the worst case, runs in polynomial time. Chapter 4 discusses the hairline/minor fracture detection and target pattern generation in a hierarchical Bayesian restoration framework. We use the Markov Random Field (MRF)- Maximum A Posteriori (MAP) approach of Geman and Geman and model the fracture as a local stochastic degradation of an hypothetical intact mandible. The MAP estimate corresponds to the target pattern (reconstructed jaw) and the differences in intensity between the input data and MAP estimate at specific pixel locations mark the occurrence of a fracture. In Chapter 5, we apply traditional scale-space theory for corner detection, followed by Kalman filter within a Bayesian inference paradigm to identify well-displaced/major fracture points. Bayesian credible sets are constructed to establish a spatial consistency check among the 2D corners/fracture points, already identified using the scale space theory. In chapter 6, a fracture is modeled as a minimum cut in an appropriate weighted network. Ford-Fulkerson’s algorithm is employed to obtain the minimum cut and the magnitude of the flow is used as an approximate estimate of the extent of the fracture. Chapter 7 summarizes our overall contributions and discusses directions for future research.