Registration and Fusion Techniques for Medical Images: Demonstration and Evaluation

In this work, we present an integrated system for the registration and fusion of medical images, named «dIaGnosis». It is often necessary to align medical images to illustrate the changes between the data retrieved at different times so as to assess the progress of a disease, or to assess the effectiveness of a treatment. The proposed system supports the storage, retrieval, distribution and presentation of medical images from different modalities, such as CT and MRI, in DICOM format. It also supports multiple examinations per patient and uses parallel processing threads to perform the processing of the acquired three-dimensional (3D) images in almost real time. In this paper, the architecture and the working environment of the implemented system are presented in detail, along with a pilot scenario that demonstrates the system in use. Additionally, the registration and fusion algorithms implemented are presented and evaluated, along with the image processing techniques used for the enhancement of medical images. The contribution of the proposed work is multilayered. It provides automatic matching methods based on both segmented surfaces and on different levels of gray, and it improves the alignment process when there is a relative movement and / or distortion of images in the data collected from different imaging systems.

[1]  M. Viergever,et al.  Medical image matching-a review with classification , 1993, IEEE Engineering in Medicine and Biology Magazine.

[2]  Robert J. Maciunas,et al.  Registration of head volume images using implantable fiducial markers , 1997, IEEE Transactions on Medical Imaging.

[3]  Akram Aldroubi,et al.  B-spline signal processing. II. Efficiency design and applications , 1993, IEEE Trans. Signal Process..

[4]  D. Hill,et al.  Medical image registration , 2001, Physics in medicine and biology.

[5]  Luiz Velho,et al.  A system's architecture for warping and morphing of graphical objects , 1998, Proceedings SIBGRAPI'98. International Symposium on Computer Graphics, Image Processing, and Vision (Cat. No.98EX237).

[6]  George K. Matsopoulos,et al.  Automatic Correspondence Methods towards Point-Based Medical Image Registration: An Evaluation Study , 2009 .

[7]  N. A. Mouravliansky,et al.  A comparative study of surface- and volume-based techniques for the automatic registration between CT and SPECT brain images. , 2002, Medical physics.

[8]  Steven W. Zucker,et al.  Region growing: Childhood and adolescence* , 1976 .

[9]  Luiz Velho,et al.  Warping and morphing of graphical objects , 1998 .

[10]  Akram Aldroubi,et al.  B-SPLINE SIGNAL PROCESSING: PART II-EFFICIENT DESIGN AND APPLICATIONS , 1993 .

[11]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[12]  George K Matsopoulos,et al.  CT-MRI automatic surface-based registration schemes combining global and local optimization techniques. , 2003, Technology and health care : official journal of the European Society for Engineering and Medicine.

[13]  Max A. Viergever,et al.  A survey of medical image registration , 1998, Medical Image Anal..

[14]  T D Cradduck,et al.  National electrical manufacturers association , 1983, Journal of the A.I.E.E..

[15]  Derek L. G. Hill,et al.  Multi-modal data fusion to combine anatomical and physiological information in the head and heart , 1992 .

[16]  Konstantina S. Nikita,et al.  A COMBINATION OF GLOBAL AND ELASTIC TRANSFORMATIONS FOR THE AUTOMATIC MEDICAL SURFACE REGISTRATION , 2000 .