Heterogeneous Computing for Vertebra Detection and Segmentation in X-Ray Images

The context of this work is related to the vertebra segmentation. The method we propose is based on the active shape model (ASM). An original approach taking advantage of the edge polygonal approximation was developed to locate the vertebra positions in a X-ray image. Despite the fact that segmentation results show good efficiency, the time is a key variable that has always to be optimized in a medical context. Therefore, we present how vertebra extraction can efficiently be performed in exploiting the full computing power of parallel (GPU) and heterogeneous (multi-CPU/multi-GPU) architectures. We propose a parallel hybrid implementation of the most intensive steps enabling to boost performance. Experimentations have been conducted using a set of high-resolution X-ray medical images, showing a global speedup ranging from 3 to 22, by comparison with the CPU implementation. Data transfer times between CPU and GPU memories were included in the execution times of our proposed implementation.

[1]  Mohammed Benjelloun,et al.  Points of interest detection in cervical spine radiographs by polygonal approximation , 2010, 2010 2nd International Conference on Image Processing Theory, Tools and Applications.

[2]  Aly A. Farag,et al.  A Novel 3D Segmentation of Vertebral Bones from Volumetric CT Images Using Graph Cuts , 2009, ISVC.

[3]  Shang-Hong Lai,et al.  Learning-Based Vertebra Detection and Iterative Normalized-Cut Segmentation for Spinal MRI , 2009, IEEE Transactions on Medical Imaging.

[4]  Timothy F. Cootes,et al.  Segmentation of Lumbar Vertebrae Using Part-Based Graphs and Active Appearance Models , 2009, MICCAI.

[5]  Tim Cootes,et al.  Automatic segmentation of lumbar vertebrae on digitised radiographs using linked active appearance models , 2006 .

[6]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[7]  David H. Douglas,et al.  ALGORITHMS FOR THE REDUCTION OF THE NUMBER OF POINTS REQUIRED TO REPRESENT A DIGITIZED LINE OR ITS CARICATURE , 1973 .

[8]  Christopher J. Taylor,et al.  Automatic Measurement of Vertebral Shape using Active Shape Models , 1996, BMVC.

[9]  Jürgen Weese,et al.  Shape Constrained Deformable Models for 3D Medical Image Segmentation , 2001, IPMI.

[10]  Timothy F. Cootes,et al.  Linking Sequences of Active Appearance Sub-Models via Constraints: An Application in Automated Vertebral Morphometry , 2003, BMVC.

[11]  Farida Cheriet,et al.  Texture Analysis for Automatic Segmentation of Intervertebral Disks of Scoliotic Spines From MR Images , 2009, IEEE Transactions on Information Technology in Biomedicine.

[12]  Timothy F. Cootes,et al.  Active Shape Models - 'smart snakes' , 1992, BMVC.

[13]  Timothy F. Cootes,et al.  Active Appearance Models , 1998, ECCV.

[14]  Ramani Duraiswami,et al.  Canny edge detection on NVIDIA CUDA , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[15]  Lixu Gu,et al.  GPU-based Volume Rendering for Medical Image Visualization , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[16]  Francesca Cecchi,et al.  Segmental vertebral motion in the assessment of neck range of motion in whiplash patients , 2004, International Journal of Legal Medicine.

[17]  Mohammed Benjelloun,et al.  X-ray image segmentation for vertebral mobility analysis , 2008, International Journal of Computer Assisted Radiology and Surgery.

[18]  Sidi Ahmed Mahmoudi,et al.  GPU-based segmentation of cervical vertebra in X-Ray images , 2010, 2010 IEEE International Conference On Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS).

[19]  Rüdiger Westermann,et al.  MR image reconstruction using the GPU , 2006, SPIE Medical Imaging.

[20]  P P Smyth,et al.  Vertebral shape: automatic measurement with active shape models. , 1999, Radiology.

[21]  Pradeep Dubey,et al.  Mapping High-Fidelity Volume Rendering for Medical Imaging to CPU, GPU and Many-Core Architectures , 2009, IEEE Transactions on Visualization and Computer Graphics.

[22]  Guoyan Zheng,et al.  Automated Vertebra Identification from X-Ray Images , 2010, ICIAR.

[23]  William R. Mark,et al.  Cg: a system for programming graphics hardware in a C-like language , 2003, ACM Trans. Graph..

[24]  Eduard Ayguadé,et al.  An Extension of the StarSs Programming Model for Platforms with Multiple GPUs , 2009, Euro-Par.

[25]  Cédric Augonnet,et al.  StarPU: a unified platform for task scheduling on heterogeneous multicore architectures , 2011, Concurr. Comput. Pract. Exp..

[26]  Steve Mann,et al.  OpenVIDIA: parallel GPU computer vision , 2005, ACM Multimedia.

[27]  Hong Shen,et al.  Localized priors for the precise segmentation of individual vertebras from CT volume data. , 2008, Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention.

[28]  Cristian Lorenz,et al.  Automated model-based vertebra detection, identification, and segmentation in CT images , 2009, Medical Image Anal..

[29]  Gilberto Zamora,et al.  Hierarchical segmentation of vertebrae from x-ray images , 2003, SPIE Medical Imaging.

[30]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[31]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[32]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[33]  Timothy F. Cootes,et al.  Vertebral Shape: Automatic Measurement with Dynamically Sequenced Active Appearance Models , 2005, MICCAI.

[34]  Philippe Fortemps,et al.  MEDIACYCLE: BROWSING AND PERFORMING WITH SOUND AND IMAGE LIBRARIES , 2009 .

[35]  Zhiyi Yang,et al.  Parallel Image Processing Based on CUDA , 2008, 2008 International Conference on Computer Science and Software Engineering.

[36]  L. Rodney Long,et al.  Use of shape models to search digitized spine X-rays , 2000, Proceedings 13th IEEE Symposium on Computer-Based Medical Systems. CBMS 2000.

[37]  Thomas K. Peucker,et al.  2. Algorithms for the Reduction of the Number of Points Required to Represent a Digitized Line or its Caricature , 2011 .

[38]  Ronald M. Summers,et al.  Level set based vertebra segmentation for the evaluation of Ankylosing Spondylitis , 2006, SPIE Medical Imaging.

[39]  C. Goodall.  Procrustes methods in the statistical analysis of shape , 1991 .