Title: Non-rigid registration (computed tomography - ultrasound) of liver using B-splines and free form deformation
Authors: Romel Bhattacharjee; Ashish Verma; Neeraj Sharma; Shiru Sharma
Addresses: School of Biomedical Engineering, Indian Institute of Technology (BHU) Varanasi, 221005 Uttar Pradesh, India ' Department of Radio Diagnosis & Imaging, Institute of Medical Sciences, Banaras Hindu University, Varanasi, 221005, India ' School of Biomedical Engineering, Indian Institute of Technology (BHU) Varanasi, 221005 Uttar Pradesh, India ' School of Biomedical Engineering, Indian Institute of Technology (BHU) Varanasi, 221005 Uttar Pradesh, India
Abstract: Medical image registration is a key enabling technology and a highly challenging task. By iteratively minimising a cost function and optimising transformation parameters, the registration is achieved. In this paper, the semi-automatic non-rigid registration method is utilised to register computed tomography (CT) and ultrasound (US) images of the liver. The global motion is modelled by an affine transformation, while the local motion is described by free form deformation (FFD) based on B-splines. Two different techniques are included for registration refinement of the local deformation: transformation using multi-level B-splines and using gradient orientation information. This work also includes three different types of optimisation strategies: steepest gradient descent, quasi-Newton and Levenberg-Marquardt method. Visual examinations and experimental results on six clinical datasets verify a lower level of registration error and a higher degree of accuracy when the method is employed using Levenberg-Marquardt optimisation while utilising the gradient orientation information for registration refinement.
Keywords: non-rigid registration; free form deformation; FFD; multilevel B-splines; gradient orientation information.
DOI: 10.1504/IJBET.2022.124662
International Journal of Biomedical Engineering and Technology, 2022 Vol.39 No.4, pp.327 - 346
Received: 05 Mar 2019
Accepted: 05 Jul 2019
Published online: 05 Aug 2022 *