# US 2010/0166275 A1 · Model-based method and system for image segmentation and modelling > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2010/0166275 A1 - Document ID: US20100166275A1 - Status: Published application - Kind: A1 - Application number: 12/438,078 - Filed: 2007-08-24 - Published: 2010-07-01 - Earliest claimed: 2006-08-24 - Assignees: Agency for Science Tecnology and Research - Inventors: Jimin Liu - Web page: https://patentgrep.com/patent/US20100166275A1 ## CPC - G06T 7/12: Edge-based segmentation - G06T 7/149: involving deformable models, e.g. active contour models - G06V 10/755: {Deformable models or variational models, e.g. snakes or active contours} - G06T 2207/10088: Magnetic resonance imaging [MRI] - G06T 2207/20161: Level set - G06T 2207/30016: Brain - G06V 2201/03: Recognition of patterns in medical or anatomical images - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method is proposed for segmenting a 2- or 3-D space, spanned by a set of medical data comprising intensity values at locations within the space, to estimate the position of an object of medical significance. The method using a level set function having a level set which provides a model of boundary of the object. The level set function is iteratively updated by a force defined based on the medical data. For computational efficiency, only the force in the narrowband of the model boundary needs to be calculated. Minimisation of an energy function, related to the force, provides a termination condition for the iteration. High level knowledge can be incorporated in several ways, such as by an explicit force term which takes over from the force based on the medical data when prior knowledge of the object is about to be violated by the model. ## Claims ### Claim 1 A method of image segmentation and modelling, within a space spanned by a set of medical data, the portion of the space occupied by an object, the method comprising: (a) defining a level set function, a level set of the level set function being the boundary of a deformable model of the object; (b) iteratively performing at least once the set of steps: (i) calculating, at each of a plurality of locations, a corresponding force, said force being calculated using the medical data and the boundary of the model; and (ii) modifying the level set function at the plurality of locations according to the calculated corresponding forces; and (c) modelling the boundary of said object as the level set of the modified level set function. ### Claim 2 (depends on 1) A method according to claim 1 in which said plurality of locations are within a narrowband region of the model boundary, and consisting of first locations which are on the boundary of the model, and second locations which are not on the boundary of the model. ### Claim 3 (depends on 1, 2) A method according to claim 1 or claim 2 in which said step (i) of calculating the force at the locations within the narrowband region, is performed by: calculating said force at said first locations; and calculating said force at the second locations using said calculated forces at the first locations, and said step (ii) of modifying the level set function is performed at each of said locations using the corresponding calculated force. ### Claim 4 (depends on 3) A method according to claim 3 in which the force at said second locations is calculated by defining, for each said second location, a corresponding neighbourhood, and calculating the force at the second location using the average of said calculated forces at each first location within the corresponding neighbourhood. ### Claim 5 A method according to any preceding claim in which the force at each point at the level set of the level set function is calculated, selectively according to whether a predefined criterion is met, as either: (i) a first force which is a function of the medical data; or (ii) an intensity-based force which encodes prior information about the object. ### Claim 6 (depends on 5) A method according to claim 5 in which the first force is a gradient flux-based force which is a function of the gradient of intensity values of the medical data. ### Claim 7 (depends on 6) A method according to claim 6 in which the gradient flux-based force at each point on the level set of the level set function is obtained by searching along a line segment passing through that point and normal to the level set at that point, for a location which is a stationary point of a gradient flux density which is a function of the gradient of the intensity values, and obtaining the force as the gradient flux density at the stationary point. ### Claim 8 (depends on 7) A method according to claim 7 in which the gradient flux density varies as a linear function of the gradient of the intensity values divided by a linear function of the square of the distance of the location from the level set. ### Claim 9 A method according to any preceding claim in which iterative step (b) terminates when a minimum of an energy function is reached. ### Claim 10 (depends on 9) A method according to claim 9 in which the energy function is the average over the level set of an energy value. ### Claim 11 (depends on 6, 7, 10) A method according to claim 10 when dependent upon claims 6 and 7 in which the energy value is the gradient flux density. ### Claim 12 A method according to any preceding claim in which, in said step (ii) of modifying the level set function, the level set function is only modified if the topology of the level set is not thereby caused to disobey a geometrical criterion obtained based on prior knowledge of the object. ### Claim 13 A system for modelling, within a space spanned by a set of medical data, the portion of the space occupied by an object, the system having a processor arranged to: (a) receive medical data; (b) define a level set function, a level set of the level set function being the boundary of a deformable model of the object: (c) iteratively perform at least once the set of steps: (i) calculating, at each of a plurality of locations, a corresponding force, said force being calculated using the medical data and the boundary of the model; and (ii) modifying the level set function at the plurality of locations according to the corresponding calculated forces; and (d) output a model of the boundary of said object which is the level set of the modified level set function. ### Claim 14 A computer program product having program instructions which, when implemented by a computer system, cause the computer system to generate a model, within a space spanned by a set of medical image data, of the portion of the space occupied by an object, by (a) defining a level set function, a level set of the level set function being an initial model of the boundary of the object; (b) iteratively performing at least once the set of steps: (i) calculating, at each of a plurality of locations, a corresponding force, said force being calculated using the medical image data and the boundary of the model; and (ii) modifying the level set function at the plurality of locations according to the corresponding calculated forces; and (c) generating said model as the level set of the modified level set function.