Image analysis – Applications – Biomedical applications
Reexamination Certificate
1999-04-02
2002-04-02
Johns, Andrew W. (Department: 2621)
Image analysis
Applications
Biomedical applications
Reexamination Certificate
active
06366684
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates to a method for processing an intensity image formed of points, which method involves steps for contour detection of an object represented in the image, including a step for a dynamic programming procedure. The invention also relates to a system with means for carrying out such a method and to an X-ray apparatus associated with such a system.
The invention is advantageously used in the medical imaging industry.
2. Description of the Related Art
A method for the detection of contours in an image is already known from the publication “Encoding of a priori Information in Active Contour Models” in “IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 18, NO. 9, SEPTEMBER 1996”. This publication uses the theory of active contours to model the problem of contour recovery as an energy minimization process. The computational solutions based on dynamic programming require that the energy associated with a contour candidate is decomposed into an integral of local energy distributions. The cited publication discloses a grammatical framework that models different local energy models and a set of allowable transitions between these models. The grammatical encoding is utilized to represent a priori knowledge about the shape of the object and intensity elements of the associated image. The variability encountered in numerical experiments is addressed with the energy minimization procedure which is embedded in the grammatical framework. The cited publication discloses an algorithmic solution that combines an algorithm, denoted as the Knuth-Morris-Pratt algorithm for string matching with a dynamic programming algorithm for energy minimization.
The method disclosed in the above publication necessarily includes an initialization step. Furthermore, the method uses only local information to represent the a priori knowledge.
SUMMARY OF THE INVENTION
It is an object of the present invention to provide a completely automated method of contour detection in a complicated image, that is to say in a noisy and blurred image. For example, the invention aims to process a medical image so as to detect the contour of the left ventricle of the heart.
The object of the invention is achieved by means of a method for processing an intensity image formed of points representing an object, including steps for automatically supplying points determining a minimal path representing the object contour, involving: acquiring data of the intensity image, evaluating probability values indicating the probability that a given point of the image belongs to predefined regions of the image relating to the object, and deriving a contour model of the object from said probability values, transforming the image into a three-dimensional matrix image based on said contour model and said probability values, performing dynamic programming in order to determine said minimum path in said three-dimensional matrix image.
The method according to the invention mitigates the three major drawbacks of the known active contour detection method: initialization dependency, exclusive use of local information and occlusion sensitivity. An important feature of the method of the invention is the introduction of high-order a priori information in each step of the method. Furthermore, the initialization step is completely automated by way of close cooperation between a multi-resolution neural network and a hidden Markov model-enhanced dynamic programming procedure.
An X-ray apparatus associated with a system for carrying out the automatic contour detection of the left ventricle in a digital X-ray image is also proposed.
REFERENCES:
patent: 5768415 (1998-06-01), Jagadish et al.
patent: 5871019 (1999-02-01), Belohlavek
patent: 6072496 (2000-06-01), Guenter et al.
patent: 6072903 (2000-06-01), Maki et al.
patent: 6106466 (2000-08-01), Sheehan et al.
patent: 6154560 (2000-11-01), Cothren et al.
“Encoding of a priori information in Active Contour Models” in III Transactions of Pattern Analysis and Machine Intelligence, vol. 18, No. 9, Sep. 1996.
Gerard Olivier
Makram-Ebeid Sherif
Johns Andrew W.
Nakhjavan Shervin
U.S. Philips Corporation
Vodopia John F.
LandOfFree
Image processing method and system involving contour... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Image processing method and system involving contour..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Image processing method and system involving contour... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2889933