Elastic registration of prostate MR images based on state estimation of dynamical systems

Marami, Bahram; Ghoul, Suha; Sirouspour, Shahin; Capson, David W.; Davidson, Sean M.; Trachtenberg, John; Fenster, Aaron

doi:10.1117/12.2043884

Cited by 2 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on our implementation on graphics processing units (GPUs) (Mousazadeh et al 2011), it required 2.15 ms to compute the deformation and interpolate an image of the size 128×128×50. Our recent C++ implementation of the proposed 3D-3D registration in a multi-core CPU showed that the real-time tasks can be done in less than 10 sec for the registration of prostate MR images reported in (Marami, Ghoul, Sirouspour, Capson, Davidson, Trachtenberg & Fenster 2014).…”

Section: Discussionmentioning

confidence: 99%

“…A finite element mesh in domain of Ω could be employed for registration of any given set of images. Therefore, the same deformation model can be used for all breast images acquired from different patients as we showed in (Marami, Ghoul, Sirouspour, Capson, Davidson, Trachtenberg & Fenster 2014) for prostate images. Any given set of 3D reference and template images in domain ofΏ and resolution of m x ×m y ×m z can be transformed to be encompassed by the FE mesh.…”

Section: Discussionmentioning

confidence: 99%

“…This would reduce the realtime computations of the registration algorithm. Furthermore, as previously was shown in (Marami, Ghoul, Sirouspour, Capson, Davidson, Trachtenberg & Fenster 2014), in case of 3D-3D registration the computed Kalman gain can be used for the registration of any image pair. In this case, the relative power of the process and measurement noises are considered to be the same in all images.…”

Section: State Estimationmentioning

confidence: 96%

“…Previously, we have presented preliminary results of this work in two conference papers in (Marami, Sirouspour & Capson 2011a, Marami, Sirouspour & Capson 2011b for 3D-3D and 3D-2D registration of MR images acquired from a realistic breast phantom. In (Marami, Ghoul, Sirouspour, Capson, Davidson, Trachtenberg & Fenster 2014), the method was also assessed in the 3D-3D registration of prostate MR images applicable to the focal therapy of clinically localized prostate cancer. Moreover, dynamic deformation of a breast phantom was tracked based on registering pre-operative 3D MR images to the real-time intra-operative 2D US images using the proposed method of this paper in .…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Non-rigid registration of medical images based on estimation of deformation states

2014

Self Cite

View full text Add to dashboard Cite

A unified framework for automatic non-rigid 3D-3D and 3D-2D registration of medical images with static and dynamic deformations is proposed in this paper. The problem of non-rigid image registration is approached as a classical state estimation problem using a generic deformation model for the soft tissue. The registration technique employs a dynamic linear elastic continuum mechanics model of the tissue deformation, which is discretized using the finite element method. In the proposed method, the registration is achieved through a Kalman-like filtering process, which incorporates information from the deformation model and a vector of observation prediction errors computed from an intensity-based similarity/distance metric between images. With this formulation, single and multiple-modality, 3D-3D and 3D-2D image registration problems can all be treated within the same framework. The performance of the proposed registration technique was evaluated in a number of different registration scenarios. First, 3D magnetic resonance (MR) images of uncompressed and compressed breast tissue were co-registered. 3D MR images of the uncompressed breast tissue were also registered to a sequence of simulated 2D interventional MR images of the compressed breast. Finally, the registration algorithm was employed to dynamically track a target sub-volume inside the breast tissue during the process of the biopsy needle insertion based on registering pre-insertion 3D MR images to a sequence of real-time simulated 2D interventional MR images. Registration results indicate that the proposed method can be effectively employed for the registration of medical images in image-guided procedures, such as breast biopsy in which the tissue undergoes static and dynamic deformations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: State Estimationmentioning

confidence: 96%