Koninklijke Philips Corporation N.V.

Thomas D Deschamps

Laurent Cohen

Olivier Gerard

Sh&eacute;rif Makram-Ebeid

Myriam Greff

The invention relates to a method for segmenting an image [IM] by path extraction using minimization of at least a potential [POT], said potential being calculated [CAS] from a feature [FEA] of the image [IM] using a cost assignment function [CAF], said calculation [CAS] being realized using the definition of two groups of points [NP and PP] in a neighborhood of a drawn [DRW] contour: the ones that are considered to be relevant to a boundary, called positive points [PP] and the ones that are not considered to be relevant to said boundary, called negative points [NP]. A refined characterization of positive points is constructed by combining characterizations of positive and negative points and the cost assignment function [CAF] is modified [CAL] using this refined characterization. The invention proposes also a fully automatic simultaneous adaptation of the different cost assignment functions of the individual potentials in a total function of potentials, and their relative weightings.

Adaptation of potential terms in real-time optimal path extraction

The invention relates to a medical imaging station including acquisition means ACQ for obtaining images IM exhibiting levels of gray, means DIS of displaying images IM, segmentation means SEG for segmenting at least one imaged object, said segmentation means SEG determining a so-called segmentation zone IMS delimiting the image object on the image, and means TR of extracting at least one path PAT within the segmentation IMS. The station according to the invention is such that the extraction means include means POS of positioning an initial point on the segmentation, means PROP of propagating an edge within the segmentation IMS from the initial point, means TES of testing the connectedness of the edge, means LAB of labeling portions of the edge, referred to as ramifications, when a non-connected edge is detected, means IDE of identifying final points PF of the propagation on the ramifications, path tracing means TRA for tracing a path PAT from final points PF and the initial point. Application: Medical imaging

Medical imaging station with a function of extracting a path within a ramified object

The invention concerns a medical imaging station including segmentation means for segmenting at least one imaged object in an image having gray levels, by propagating an edge from at least one initial point positioned in the image on the imaged object. The speed of propagation of the edge depends on said gray levels at each point referred to as a current point and the segmentation means segmenting the image between the points over which the edge passes and the points over which the edge does not pass. According to the invention, the edge propagation means are coupled with means of automatically detecting an emergence of the propagation edge from the imaged object at a current point. Means of locally fixing the speed of propagation at zero at this current point are activated in the event of detection of an emergence of the propagation edge.

Medical imaging station with rapid image segmentation

The invention relates to an image processing method for processing an image representing a tubular structure having walls, comprising steps for determining a flight path (EP) inside this tubular structure between a first and a second predetermined end points, said flight path being both the shortest path between said end points and the farthest from the structure walls (NB ). Said steps may comprise locating the structure wall points, determining a surface at a predetermined constant distance from said wall points, inside the structure, for forming a central region (CR), and determining, in said central region, the shortest path (EP) between the first and second end points.

Image processing method, system and apparatus for processing an image representing tubular structure and for constructing a path related to said structure

Growing community of inventors

Boulogne-Billancourt, France

Thomas D Deschamps