An interactive medical image segmentation system based on the optimal management of regions of interest using topological medical knowledge

This paper presents an original interactive system for efficient medical image segmentation in computer aided diagnosis. The main originality concerns the method used to manage, according to an a priori topological-based structural model, regions of interest (ROIs) within which computations can be constrained. The goal is then to avoid the processing of irrelevant image points, therefore improving and accelerating segmentations. In the case of a hierarchical modeling procedure, our ROI management method enables, for delineating a given medical structure, to optimally determine image points of interest by taking previously segmented structures into account. We propose a mathematical formulation of the method as well as a possible implementation within an interactive system. We also detail an experience report focussing on the segmentation of several abdominal structures from a CT image. It illustrates the behavior and the potential of our method.

[1]  Cyril S. Ku,et al.  Design Patterns , 2008, Wiley Encyclopedia of Computer Science and Engineering.

[2]  Russell H. Taylor,et al.  Medical robotics in computer-integrated surgery , 2003, IEEE Trans. Robotics Autom..

[3]  Frans Vos,et al.  Interactive 3D segmentation using connected orthogonal contours , 2004, Comput. Biol. Medicine.

[4]  Isabelle Bloch,et al.  Representation and fusion of heterogeneous fuzzy information in the 3D space for model-based structural recognition--Application to 3D brain imaging , 2003, Artif. Intell..

[5]  Thomas Rodt,et al.  Specially adapted interactive tools for an improved 3D-segmentation of the spine. , 2004, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[6]  Marco Nolden,et al.  The Medical Imaging Interaction Toolkit , 2005, Medical Image Anal..

[7]  Luc Vincent,et al.  Morphological transformations of binary images with arbitrary structuring elements , 1991, Signal Process..

[8]  Jean-Francois Mangin,et al.  Automatic recognition of cortical sulci of the human brain using a congregation of neural networks , 2002, Medical Image Anal..

[9]  Christopher G. Lasater,et al.  Design Patterns , 2008, Wiley Encyclopedia of Computer Science and Engineering.

[10]  Jean-Francois Mangin,et al.  Coordinate-based versus structural approaches to brain image analysis , 2004, Artif. Intell. Medicine.

[11]  G Wagenknecht,et al.  MRI-based individual 3D region-of-interest atlases of the human brain: a new method for analyzing functional data. , 2004, Methods of information in medicine.

[12]  Hans-Peter Meinzer,et al.  Computerized planning of liver surgery - an overview , 2002, Comput. Graph..

[13]  Jean-Baptiste Fasquel,et al.  An efficient and generic extension to ITK to process arbitrary shaped regions of interest , 2006, Comput. Methods Programs Biomed..

[14]  Shusaku Tsumoto,et al.  Rough representation of a region of interest in medical images , 2005, Int. J. Approx. Reason..

[15]  Nicholas Ayache,et al.  Medical Image Analysis: Progress over Two Decades and the Challenges Ahead , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Yan Kang,et al.  Interactive 3D editing tools for image segmentation , 2004, Medical Image Anal..

[17]  Isabelle Bloch,et al.  Computational modeling of thoracic and abdominal anatomy using spatial relationships for image segmentation , 2004, Real Time Imaging.

[18]  Konstantinos Konstantinides,et al.  The Khoros software development environment for image and signal processing , 1994, IEEE Trans. Image Process..

[19]  Max A. Viergever,et al.  Automatic cardiac region-of-interest computation in cine 3D structural MRI , 2004, CARS.

[21]  Hans-Peter Meinzer,et al.  An interactive system for volume segmentation in computer-assisted surgery , 2004, Medical Imaging: Image-Guided Procedures.

[22]  Arnold W. M. Smeulders,et al.  Interaction in the segmentation of medical images: A survey , 2001, Medical Image Anal..