Elastic Registration Based on Compliance Analysis and Biomechanical Graph Matching
- PDF / 4,396,257 Bytes
- 16 Pages / 593.972 x 792 pts Page_size
- 63 Downloads / 226 Views
Annals of Biomedical Engineering (Ó 2019) https://doi.org/10.1007/s10439-019-02364-4
Original Article
Elastic Registration Based on Compliance Analysis and Biomechanical Graph Matching JAIME GARCIA GUEVARA ,1,2 IGOR PETERLIK,1 MARIE-ODILE BERGER,1,2 and STEPHANE COTIN1 1
Inria Nancy Grand Est, Villers-les-Nancy, France; and 2Universite´ de Lorraine, Nancy, France (Received 1 March 2019; accepted 12 September 2019) Associate Editor Elena S. Di Martino oversaw the review of this article.
Abstract—An automatic elastic registration method suited for vascularized organs is proposed. The vasculature in both the preoperative and intra-operative images is represented as a graph. A typical application of this method is the fusion of pre-operative information onto the organ during surgery, to compensate for the limited details provided by the intraoperative imaging modality (e.g. cone beam CT) and to cope with changes in the shape of the organ. Due to image modalities differences and organ deformation, each graph has a different topology and shape. The adaptive compliance graph matching (ACGM) method presented does not require any manual initialization, handles intra-operative nonrigid deformations of up to 65 mm and computes a complete displacement field over the organ from only the matched vasculature. ACGM is better than the previous biomechanical graph matching method (Garcia Guevara et al. IJCARS, 2018) (BGM) because it uses an efficient biomechanical vascularized liver model to compute the organ’s transformation and the vessels bifurcations compliance. This allows to efficiently find the best graph matches with a novel compliance-based adaptive search. These contributions are evaluated on 10 realistic synthetic and 2 porcine automatically segmented datasets. ACGM obtains better target registration error (TRE) than BGM, with an average TRE in the real datasets of 4.2 mm compared to 6.5 mm, respectively. It also is up to one order of magnitude faster, less dependent on the parameters used and more robust to noise. Keywords—Non-rigid registration, fusion, Graph matching.
Biomechanics,
Data
INTRODUCTION Providing enhanced visualization (e.g. of an organ internal structures) during an intervention can significantly improve surgical procedures. Since each image
Address correspondence to Jaime Garcia Guevara, Universite´ de Lorraine, Nancy, France. Electronic mail: [email protected]
modality provides different and often complementary information on tissue structures or deformation changes, the fusion of intra-operative and preoperative images into a unique coordinate frame adds significant value.14 Registration of the preoperative image onto an intra-operative image [X-ray, ultrasound, cone beam CT (CBCT), etc.] can be handled in many different manners, given the application, the image modality, the parameter space, or the optimization process. The literature is vast on the topic and several surveys classify the different methods for this problem.22 Regardless of the targeted clinical application, this paper foc
Data Loading...
