Abstract: A segmentation method includes several steps wherein a single data space is selected by the user in an n-dimensional feature space in a first step. This selected data space is basically interpreted by the system as containing at least two classes of objects to be segmented. In the following steps, the system first determines a separation function in the n-dimensional feature space for differentiating the at least two classes and then applies this separation function to the entire data space or a large part of the data space. The segmentation result is then visually presented to the user in real time. The invention also relates to a method for classifying objects on the basis of geometric characteristics of objects previously segmented according to any method in an n-dimensional data space. In a first step, at least two objects are selected as representatives of two different categories, then a number (m) of geometric characteristics per object is determined by calculating various whole-number wave functions.

Abstract: A segmentation method includes several steps wherein a single data space is selected by the user in an n-dimensional feature space in a first step. This selected data space is basically interpreted by the system as containing at least two classes of objects to be segmented. In the following steps, the system first determines a separation function in the n-dimensional feature space for differentiating the at least two classes and then applies this separation function to the entire data space or a large part of the data space. The segmentation result is then visually presented to the user in real time. The invention also relates to a method for classifying objects on the basis of geometric characteristics of objects previously segmented according to any method in an n-dimensional data space. In a first step, at least two objects are selected as representatives of two different categories, then a number (m) of geometric characteristics per object is determined by calculating various whole-number wave functions.

Abstract: An ultrasound medical imaging system having a flexible, versatile and programmable architecture, particularly with respect to a back end subsystem. The architecture for the back end subsystem is generalized and includes multiple identical and interchangeable processing elements or boards that combine to produce sufficient processing power to support real time imaging in the various modes of ultrasound operations. The architecture may also tune front end parameters for a front end subsystem based on back end processing, bypass faulty processing elements or boards, and/or distribute processing load across operational processing elements or boards. A method for operating such an ultrasound medical imaging system is also disclosed.

Abstract: Reflected-back ultrasound waves are recorded and rebinned in accordance with a particular data classification scheme. In a post processing step, the data is processed to remove the effect of stationary scatterers (such as slowly-moving body structure) and features of the processed data are computer-traced to determine e.g. the velocity of the patient's blood stream.