Practical contour segmentation algorithm for small animal digital radiography image

In this paper a practical, automated contour segmentation technique for digital radiography image is described. Digital radiography is an imaging mode based on the penetrability of x-ray. Unlike reflection imaging mode such as visible light camera, the pixel brightness represents the summation of the attenuations on the photon thoroughfare. It is not chromophotograph but gray scale picture. Contour extraction is of great importance in medical applications, especially in non-destructive inspection. Manual segmentation techniques include pixel selection, geometrical boundary selection and tracing. But it relies heavily on the experience of the operators, and is time-consuming. Some researchers try to find contours from the intensity jumping characters around them. However these characters also exist in the juncture of bone and soft tissue. The practical way is back to the primordial threshold algorithm. This research emphasizes on how to find the optimal threshold. A high resolution digital radiography system is used to provide the oriental gray scale image. A mouse is applied as the sample of this paper to show the feasibility of the algorithm.

[1]  Doron Levy,et al.  Registration-based morphing of active contours for segmentation of ct scans. , 2004, Mathematical biosciences and engineering : MBE.

[2]  Wenyuan Wang An Active Contour Model for Selective Segmentation , 2005, CGIV.

[3]  Guido Gerig,et al.  User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability , 2006, NeuroImage.

[4]  Luo Xi-ping An Algorithm for Segmentation of Medical Image Series Based on Active Contour Model , 2002 .

[5]  M. Flower,et al.  Automated CT marker segmentation for image registration in radionuclide therapy. , 2001, Physics in medicine and biology.

[6]  Johan Wagemans,et al.  Contour-based object identification and segmentation: Stimuli, norms and data, and software tools , 2004, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[7]  Frits Mastik,et al.  Fully automatic luminal contour segmentation in intracoronary ultrasound imaging-a statistical approach , 2004, IEEE Transactions on Medical Imaging.

[8]  Yang Xiang,et al.  An active contour model for image segmentation based on elastic interaction , 2006, J. Comput. Phys..

[9]  U. Pal,et al.  Automatic Cell Segmentation in Cyto- and Histometry Using Dominant Contour Feature Points , 1998, Analytical cellular pathology : the journal of the European Society for Analytical Cellular Pathology.

[10]  Qingming Luo,et al.  Characterization of a digital x-ray imaging system for small-animal studies based on CCD detector , 2003, International Conference on Photonics and Imaging in Biology and Medicine.

[11]  Qingming Luo,et al.  In vivo observing x-ray attenuation of intratumor injection of indocyanine green , 2003, International Conference on Photonics and Imaging in Biology and Medicine.

[12]  K. Ramakrishnan,et al.  Zero Crossing Edge Detection and Contour Tracing for Segmentation of Cervical Cell Nucleus . , 1993 .

[13]  Qingming Luo,et al.  Effective method for automatic contour extraction in computerized tomography reconstruction , 2008, J. Electronic Imaging.

[14]  Peter Maass,et al.  Contour reconstruction in 3-D X-ray CT , 1993, IEEE Trans. Medical Imaging.

[15]  Xun Wang,et al.  A comparative study of deformable contour methods on medical image segmentation , 2008, Image Vis. Comput..