Sparse deformation prediction using Markove Decision Processes (MDP) for Non-rigid registration of MR image. (August 2018)

• Record Type: Journal Article
• Authors: Fu, Tianyu; Li, Qin; Zhu, Jianjun; Ai, Danni; Huang, Yong; Song, Hong; Jiang, Yurong; Wang, Yongtian; Yang, Jian
• Is Part Of: Computer methods and programs in biomedicine. Volume 162(2018)
• Page Start: 47
• Page End: 59
• Publication Date: 2018-08
• Subjects: Deformation prediction -- Markove decision processes -- Patch-wise registration -- MR image; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2018.04.024
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Based on the training image set, a rapid and accurate non-rigid registration is proposed. The proposed method combines the constructions of Minimum Spanning Tree (MST) and Markove Decision Processes (MDP) at patch scale to provide a suitable initial deformation for the registration from test to template images. MST provides the registration paths which decomposes the large-deformation registration between the test and the template images into multiple fast registrations with small deformations. MDP selects the optimal registration path which achieves the most accurate registration. The proposed method rapidly registers the inter-subject brains and achieves the high mean Dice for the different tissues of the brain. Abstract: Background and Objective: A framework of sparse deformation prediction using Markove Decision Processes is proposed for achieving a rapid and accurate registration by providing a suitable initial deformation. Methods: In the proposed framework, the tree is built based on the training set for each patch from the template image. The template patch is considered as the root. The node is the patch group in which multiple similar patches are extracted around a key point on the training image. Given the linkages between patch groups in the tree, MDP is introduced to select the optimal path with highest registration accuracy from each training patch to the template patch. The deformation between them is estimated along the selected path by patch-wise registration which can be realized by a non-learning-based method. Given the patches on a testing image, their best matching patches are fast chosen from the training patches and the corresponding deformations constitute a sparse deformation. A dense deformation for the entire test image is subsequently interpolated and used as an initial deformation for further registration. Results: With the non-learning-based registration as the baseline method, the proposed framework is evaluated using three datasets of inter-subject brain MR images with three learning-based methods. Experimental results of the non-learning-based method using the proposed framework reveal that the computation time is reduced by fivefold after using the proposed framework. And, with the same baseline method, the proposed framework demonstrates the higher accuracy than three learning-based methods which predicts the initial deformation at image scale. The mean Dice of three datasets for the tissues of the brain are 73.52%, 70.73% and 64.82%, respectively. Conclusions: The proposed framework rapidly registers the inter-subject brains and achieves the high mean Dice for the tissues of the brain.