Lossy Compression of 3D Statistical Shape and Intensity Models of Femoral Bones Using JPEG 2000

Abstract: Recent development of computer-assisted medical systems, based on statistical shape analysis, leads to a growing number of emerging shape and appearance models. In this paper, we propose a novel method for a lossy compression of 3D statistical shape and intensity models exploiting the JPEG 2000 image coding system. We also investigate the influence of the lossy compression on the accuracy of an atlas-based 2D/3D reconstruction, which is one of the common applications of the statistical appearance models. The results revealed the method is highly efective for the intensity information, reaching thousandfold compression ratios without affecting the 2D/3D reconstruction accuracy. The bitrate of shape information can be compressed several times without signifcant influence on the reconstruction accuracy.

[1]  Philippe C. Cattin,et al.  Statismo - A framework for PCA based statistical models , 2012, The Insight Journal.

[2]  Michael Kistler,et al.  The Virtual Skeleton Database: An Open Access Repository for Biomedical Research and Collaboration , 2013, Journal of medical Internet research.

[3]  A. James Stewart,et al.  Multiple-Object 2-D–3-D Registration for Noninvasive Pose Identification of Fracture Fragments , 2011, IEEE Transactions on Biomedical Engineering.

[4]  Hans-Christian Hege,et al.  Fast Generation of Virtual X-ray Images for Reconstruction of 3D Anatomy , 2013, IEEE Transactions on Visualization and Computer Graphics.

[5]  Pavel Zemcík,et al.  Intensity-based femoral atlas 2D/3D registration using Levenberg-Marquardt optimisation , 2016, SPIE Medical Imaging.

[6]  Russell H. Taylor,et al.  Deformable 2D-3D Registration of the Pelvis with a Limited Field of View, Using Shape Statistics , 2007, MICCAI.

[7]  Pavel Zemcík,et al.  Single-Loop Architecture for JPEG 2000 , 2016, ICISP.

[8]  Timothy F. Cootes,et al.  Trainable method of parametric shape description , 1992, Image Vis. Comput..

[9]  Ren Hui Gong,et al.  2D/3D registration with the CMA-ES method , 2008, SPIE Medical Imaging.

[10]  Yoshinobu Sato,et al.  A Survey on Statistical Modeling and Machine Learning Approaches to Computer Assisted Medical Intervention: Intraoperative Anatomy Modeling and Optimization of Interventional Procedures , 2013, IEICE Trans. Inf. Syst..

[11]  Pavel Zemcik,et al.  Single-Loop Software Architecture for JPEG 2000 , 2016, DCC 2016.

[12]  A. James Stewart,et al.  Reduction of multi-fragment fractures of the distal radius using atlas-based 2D/3D registration , 2009, Medical Imaging.

[13]  Hans-Christian Hege,et al.  Atlas-based 3D-Shape Reconstruction from X-Ray Images , 2006, 18th International Conference on Pattern Recognition (ICPR'06).