{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-graph-cut-based-optimization-for","title":"Fast Graph-Cut Based Optimization for Practical Dense Deformable Registration of Volume Images","arxiv_id":"1810.08427","date":"2018-10-19","proceeding":null,"authors":["Simon Ekström","Filip Malmberg","Håkan Ahlström","Joel Kullberg","Robin Strand"],"abstract":"Objective: Deformable image registration is a fundamental problem in medical\nimage analysis, with applications such as longitudinal studies, population\nmodeling, and atlas based image segmentation. Registration is often phrased as\nan optimization problem, i.e., finding a deformation field that is optimal\naccording to a given objective function. Discrete, combinatorial, optimization\ntechniques have successfully been employed to solve the resulting optimization\nproblem. Specifically, optimization based on $\\alpha$-expansion with minimal\ngraph cuts has been proposed as a powerful tool for image registration. The\nhigh computational cost of the graph-cut based optimization approach, however,\nlimits the utility of this approach for registration of large volume images.\nMethods: Here, we propose to accelerate graph-cut based deformable registration\nby dividing the image into overlapping sub-regions and restricting the\n$\\alpha$-expansion moves to a single sub-region at a time. Results: We\ndemonstrate empirically that this approach can achieve a large reduction in\ncomputation time -- from days to minutes -- with only a small penalty in terms\nof solution quality. Conclusion: The reduction in computation time provided by\nthe proposed method makes graph cut based deformable registration viable for\nlarge volume images. Significance: Graph cut based image registration has\npreviously been shown to produce excellent results, but the high computational\ncost has hindered the adoption of the method for registration of large medical\nvolume images. Our proposed method lifts this restriction, requiring only a\nsmall fraction of the computational cost to produce results of comparable\nquality.","url_abs":"http://arxiv.org/abs/1810.08427v1","url_pdf":"http://arxiv.org/pdf/1810.08427v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-graph-cut-based-optimization-for","repo_url":"https://github.com/simeks/deform","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fast-graph-cut-based-optimization-for","repo_url":"https://github.com/tarolangner/mri-biometry","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"combinatorial-optimization","task_name":"Combinatorial Optimization"},{"task_slug":"image-registration","task_name":"Image Registration"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}