Chunliang Wang1, Hans Frimmel2, Örjan Smedby1. 1. Center for Medical Image Science and Visualization (CMIV), Linköping University, SE-58185 Linköping, Sweden and Division of Radiological Sciences (IMH), Linköping University, SE-58185 Linköping, Sweden. 2. Division of Scientific Computing, Uppsala University, Uppsala SE-75105, Sweden.
Abstract
PURPOSE: The level-set method is known to require long computation time for 3D image segmentation, which limits its usage in clinical workflow. The goal of this study was to develop a fast level-set algorithm based on the coherent propagation method and explore its character using clinical datasets. METHODS: The coherent propagation algorithm allows level set functions to converge faster by forcing the contour to move monotonically according to a predicted developing trend. Repeated temporary backwards propagation, caused by noise or numerical errors, is then avoided. It also makes it possible to detect local convergence, so that the parts of the boundary that have reached their final position can be excluded in subsequent iterations, thus reducing computation time. To compensate for the overshoot error, forward and backward coherent propagation is repeated periodically. This can result in fluctuations of great magnitude in parts of the contour. In this paper, a new gradual convergence scheme using a damping factor is proposed to address this problem. The new algorithm is also generalized to non-narrow band cases. Finally, the coherent propagation approach is combined with a new distance-regularized level set, which eliminates the needs of reinitialization of the distance. RESULTS: Compared with the sparse field method implemented in the widely available ITKSnap software, the proposed algorithm is about 10 times faster when used for brain segmentation and about 100 times faster for aorta segmentation. Using a multiresolution approach, the new method achieved 50 times speed-up in liver segmentation. The Dice coefficient between the proposed method and the sparse field method is above 99% in most cases. CONCLUSIONS: A generalized coherent propagation algorithm for level set evolution yielded substantial improvement in processing time with both synthetic datasets and medical images.
PURPOSE: The level-set method is known to require long computation time for 3D image segmentation, which limits its usage in clinical workflow. The goal of this study was to develop a fast level-set algorithm based on the coherent propagation method and explore its character using clinical datasets. METHODS: The coherent propagation algorithm allows level set functions to converge faster by forcing the contour to move monotonically according to a predicted developing trend. Repeated temporary backwards propagation, caused by noise or numerical errors, is then avoided. It also makes it possible to detect local convergence, so that the parts of the boundary that have reached their final position can be excluded in subsequent iterations, thus reducing computation time. To compensate for the overshoot error, forward and backward coherent propagation is repeated periodically. This can result in fluctuations of great magnitude in parts of the contour. In this paper, a new gradual convergence scheme using a damping factor is proposed to address this problem. The new algorithm is also generalized to non-narrow band cases. Finally, the coherent propagation approach is combined with a new distance-regularized level set, which eliminates the needs of reinitialization of the distance. RESULTS: Compared with the sparse field method implemented in the widely available ITKSnap software, the proposed algorithm is about 10 times faster when used for brain segmentation and about 100 times faster for aorta segmentation. Using a multiresolution approach, the new method achieved 50 times speed-up in liver segmentation. The Dice coefficient between the proposed method and the sparse field method is above 99% in most cases. CONCLUSIONS: A generalized coherent propagation algorithm for level set evolution yielded substantial improvement in processing time with both synthetic datasets and medical images.
Authors: Adriënne M Mendrik; Koen L Vincken; Hugo J Kuijf; Marcel Breeuwer; Willem H Bouvy; Jeroen de Bresser; Amir Alansary; Marleen de Bruijne; Aaron Carass; Ayman El-Baz; Amod Jog; Ranveer Katyal; Ali R Khan; Fedde van der Lijn; Qaiser Mahmood; Ryan Mukherjee; Annegreet van Opbroek; Sahil Paneri; Sérgio Pereira; Mikael Persson; Martin Rajchl; Duygu Sarikaya; Örjan Smedby; Carlos A Silva; Henri A Vrooman; Saurabh Vyas; Chunliang Wang; Liang Zhao; Geert Jan Biessels; Max A Viergever Journal: Comput Intell Neurosci Date: 2015-12-02
Authors: Irene Brusini; Miguel Carneiro; Chunliang Wang; Carl-Johan Rubin; Henrik Ring; Sandra Afonso; José A Blanco-Aguiar; Nuno Ferrand; Nima Rafati; Rafael Villafuerte; Örjan Smedby; Peter Damberg; Finn Hallböök; Mats Fredrikson; Leif Andersson Journal: Proc Natl Acad Sci U S A Date: 2018-06-25 Impact factor: 11.205
Authors: Mehdi Astaraki; Mara Severgnini; Vittorino Milan; Anna Schiattarella; Francesca Ciriello; Mario de Denaro; Aulo Beorchia; Hossein Aslian Journal: Phys Imaging Radiat Oncol Date: 2018-03-05
Authors: Fernando Uliana Kay; Marcelo A Beraldo; Maria A M Nakamura; Roberta De Santis Santiago; Vinicius Torsani; Susimeire Gomes; Rollin Roldan; Mauro R Tucci; Suhny Abbara; Marcelo B P Amato; Edson Amaro Journal: J Comput Assist Tomogr Date: 2018 Nov/Dec Impact factor: 1.826