Fast graph-cut based optimization for practical dense deformable registration of volume images. (September 2020)

• Record Type: Journal Article
• Authors: Ekström, Simon; Malmberg, Filip; Ahlström, Håkan; Kullberg, Joel; Strand, Robin
• Is Part Of: Computerized medical imaging and graphics. Volume 84(2020)
• Publication Date: 2020-09
• Subjects: Image registration -- Optimization; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2020.101745
• Languages: English
• ISSNs: 0895-6111

Abstract

Graphical abstract: Highlights: Optimization based on minimal graph cuts is a powerful tool for image registration. The high computational cost limits has limited the use of this approach. We propose a simple method for accelerating graph-cut based deformable registration. Our approach achieves a large reduction in computation time – from days to minutes. The penalty in terms of solution quality negligible. Abstract: Deformable image registration is a fundamental problem in medical image analysis, with applications such as longitudinal studies, population modeling, and atlas-based image segmentation. Registration is often phrased as an optimization problem, i.e., finding a deformation field that is optimal according to a given objective function. Discrete, combinatorial, optimization techniques have successfully been employed to solve the resulting optimization problem. Specifically, optimization based on α -expansion with minimal graph cuts has been proposed as a powerful tool for image registration. The high computational cost of the graph-cut based optimization approach, however, limits the utility of this approach for registration of large volume images. Here, we propose to accelerate graph-cut based deformable registration by dividing the image into overlapping sub-regions and restricting the α -expansion moves to a single sub-region at a time. We demonstrate empirically that this approach can achieve a large reduction in computation time – from days to minutes – with only a small penalty in terms of solution quality. The reduction in computation time provided by the proposed method makes graph-cut based deformable registration viable for large volume images. Graph-cut based image registration has previously been shown to produce excellent results, but the high computational cost has hindered the adoption of the method for registration of large medical volume images. Our proposed method lifts this restriction, requiring only a small fraction of the computational cost to produce results of comparable quality.