Three-dimensional Motion Tracking for Beating Heart Surgery Using a Thin-plate Spline Deformable Model

Abstract

Minimally invasive cardiac surgery offers important benefits for the patient but it also imposes several challenges for the surgeon. Robotic assistance has been proposed to overcome many of the difficulties inherent to the minimally invasive procedure, but so far no solutions for compensating physiological motion are present in the existing surgical robotic platforms. In beating heart surgery, cardiac and respiratory motions are important sources of disturbance, hindering the surgeon’s gestures and limiting the types of procedures that can be performed in a minimally invasive fashion. In this context, computer vision techniques can be used for retrieving the heart motion for active motion stabilization, which improves the precision and repeatability of the surgical gestures. However, efficient tracking of the heart surface is a challenging problem due to the heart surface characteristics, large deformations and the complex illumination conditions. In this article, we present an efficient method for active cancellation of cardiac motion where we combine an efficient algorithm for 3D tracking of the heart surface based on a thin-plate spline deformable model and an illumination compensation algorithm able to cope with arbitrary illumination changes. The proposed method has two novelties: the thin-plate spline model for representing the heart surface deformations and an efficient parametrization for 3D tracking of the beating heart using stereo images from a calibrated stereo endoscope. The proposed tracking method has been evaluated offline on in vivo images acquired by a DaVinci surgical robotic platform.

Robust 3D Visual Tracking for Robotic-Assisted Cardiac Interventions

“…For evaluating the performance of the proposed hybrid tracking concept, two sets of experiments on recorded images of a minimally invasive CABG using the DaVinci robotic platform have been conducted. The first set aims to compare the performance of the hybrid tracker with the individual techniques ( [4,2,6]) while the second focuses on the prediction quality of the predictive EKF described in section 2.2.…”

“…For this purpose, rectified images of a calibrated stereo endoscope were used. Three different tracking methods are employed: two feature-based approachesthe modified Lucas-Kanade tracker proposed in Stoyanov et al [2] and the SIFT [6] -and the region-based iterative registration technique proposed in Richa et al [4]. Since the proposed framework is modular, additional methods can be easily incorporated for increased tracking quality.…”

“…Here, the Thin-Plate Spline (TPS) model proposed in [4] is employed since it offers a good approximation of the heart surface shape in comparison with similar parametric deformable models. However, it can also be replaced by models that handle surface topological changes [7] or consider the biomechanical tissue properties [8].…”

“…For the method proposed in Richa et al [4], 14 control points distributed on textured parts of the region of interest are used. The maximal number of iterations for the minimization loop are fixed to 20.…”

“…Mainly, visual cues such as salient features [2,3], texture [4] or shading [5] have been explored. However, most techniques display poor performance in the presence of the large heart surface deformations, illumination variations and specular reflections.…”