Non-rigid point set registration of curves: registration of the superficial vessel centerlines of the brain
2016 (English)In: Medical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling, SPIE - International Society for Optical Engineering, 2016, Vol. 9786, 8 p.978611-1-978611-8 p.Conference paper (Refereed)
In this study we present a non-rigid point set registration for 3D curves (composed by 3D set of points). Themethod was evaluated in the task of registration of 3D superficial vessels of the brain where it was used to matchvessel centerline points. It consists of a combination of the Coherent Point Drift (CPD) and the Thin-PlateSpline (TPS) semilandmarks. The CPD is used to perform the initial matching of centerline 3D points, whilethe semilandmark method iteratively relaxes/slides the points.
For the evaluation, a Magnetic Resonance Angiography (MRA) dataset was used. Deformations were appliedto the extracted vessels centerlines to simulate brain bulging and sinking, using a TPS deformation where afew control points were manipulated to obtain the desired transformation (T1). Once the correspondences areknown, the corresponding points are used to define a new TPS deformation(T2). The errors are measured in thedeformed space, by transforming the original points using T1 and T2 and measuring the distance between them.To simulate cases where the deformed vessel data is incomplete, parts of the reference vessels were cut and thendeformed. Furthermore, anisotropic normally distributed noise was added.
The results show that the error estimates (root mean square error and mean error) are below 1 mm, even inthe presence of noise and incomplete data.
Place, publisher, year, edition, pages
SPIE - International Society for Optical Engineering, 2016. Vol. 9786, 8 p.978611-1-978611-8 p.
, Progress in Biomedical Optics, ISSN 1605-7422 ; 9786
Non-rigid registration, brain shift correction, vessel registration
Medical Image Processing
IdentifiersURN: urn:nbn:se:liu:diva-126347DOI: 10.1117/12.2208421ISI: 000382315800036ISBN: 978-1-5106-0021-8OAI: oai:DiVA.org:liu-126347DiVA: diva2:913783
Medical Imaging 2016: Image-Guided Procedures, Robotic Interventions, and Modeling, San Diego, California, United States, February 27, 2016
FunderSwedish Childhood Cancer Foundation, MT2013-0036