TY - JOUR
T1 - Computer vision guided virtual craniofacial reconstruction
AU - Bhandarkar, Suchendra M.
AU - Chowdhury, Ananda S.
AU - Tang, Yarong
AU - Yu, Jack C.
AU - Tollner, Ernest W.
N1 - Funding Information:
The research was supported in part by a research grant from the University of Georgia–Medical College of Georgia Joint Research Program administered by the Biomedical and Health Sciences Institute at the University of Georgia and by an Engineering Research Grant by the Faculty of Engineering at the University of Georgia. The authors sincerely acknowledge the help of Professor Robert W. Robinson, Department of Computer Science, The University of Georgia for fruitful discussions on the bipartite graph matching algorithm and Dr. Ramon Figueroa, Department of Radiology, Medical College of Georgia for providing the CT scans. The authors also thank the anonymous reviewers for their insightful comments which greatly improved the paper.
PY - 2007/9
Y1 - 2007/9
N2 - The problem of virtual craniofacial reconstruction from a sequence of computed tomography (CT) images is addressed and is modeled as a rigid surface registration problem. Two different classes of surface matching algorithms, namely the data aligned rigidity constrained exhaustive search (DARCES) algorithm and the iterative closest point (ICP) algorithm are first used in isolation. Since the human bone can be reasonably approximated as a rigid body, 3D rigid surface registration techniques such as the DARCES and ICP algorithms are deemed to be well suited for the purpose of aligning the fractured bone fragments. A synergistic combination of these two algorithms, termed as the hybrid DARCES-ICP algorithm, is proposed. The hybrid algorithm is shown to result in a more accurate mandibular reconstruction when compared to the individual algorithms used in isolation. The proposed scheme for virtual reconstructive surgery would prove to be of tremendous benefit to the operating surgeons as it would allow them to pre-visualize the reconstructed mandible (i.e., the end-product of their work), before performing the actual surgical procedure. Experimental results on both phantom and real (human) patient datasets are presented.
AB - The problem of virtual craniofacial reconstruction from a sequence of computed tomography (CT) images is addressed and is modeled as a rigid surface registration problem. Two different classes of surface matching algorithms, namely the data aligned rigidity constrained exhaustive search (DARCES) algorithm and the iterative closest point (ICP) algorithm are first used in isolation. Since the human bone can be reasonably approximated as a rigid body, 3D rigid surface registration techniques such as the DARCES and ICP algorithms are deemed to be well suited for the purpose of aligning the fractured bone fragments. A synergistic combination of these two algorithms, termed as the hybrid DARCES-ICP algorithm, is proposed. The hybrid algorithm is shown to result in a more accurate mandibular reconstruction when compared to the individual algorithms used in isolation. The proposed scheme for virtual reconstructive surgery would prove to be of tremendous benefit to the operating surgeons as it would allow them to pre-visualize the reconstructed mandible (i.e., the end-product of their work), before performing the actual surgical procedure. Experimental results on both phantom and real (human) patient datasets are presented.
KW - Bipartite graph matching
KW - Computed tomography
KW - DARCES
KW - ICP
UR - http://www.scopus.com/inward/record.url?scp=34447284782&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34447284782&partnerID=8YFLogxK
U2 - 10.1016/j.compmedimag.2007.03.003
DO - 10.1016/j.compmedimag.2007.03.003
M3 - Article
C2 - 17499969
AN - SCOPUS:34447284782
SN - 0895-6111
VL - 31
SP - 418
EP - 427
JO - Computerized Medical Imaging and Graphics
JF - Computerized Medical Imaging and Graphics
IS - 6
ER -