A statistical deformation model based regularizer for registration of histology and MRI

Free form deformation (FFD) is a popular algorithm for non-linear image registration because of its ability to accurately recover deformations. However, due to the unconstrained elastic registration, FFD may introduce unrealistic deformations, especially when differences between template and target image are large, thereby necessitating a regularizer to constrain the registration to a physically meaning transformation. Prior knowledge in the form of a Statistical Deformation Model (SDM) in a registration scheme has been shown to function as an effective regularizer. With a similar underlying premise, in this paper, we present a novel regularizer for FFD that leverages knowledge of known, valid deformations to train a statistical deformation model (SDM). At each iteration of the FFD registration, the SDM is utilized to calculate the likelihood of a given deformation occurring and appropriately influence the similarity metric to limit the registration to only realistic deformations. Qualitative evaluation of the SDM regularizer was performed for registration of ex vivo pseudo-whole mount histology (WMH) and in vivo prostate MRI to quantify multiprotocol MRI signatures of prostate cancer (CaP). Knowledge from a training set of 6 deformation fields gathered from a single patient study is used to deliver accurate overlays of prostate histology and MRI.