Prior-constrained mean shift analysis
AssigneeSiemens Medical Solutions USA, Inc.
InventorsKazunori Okada, Maneesh K. Singh, Arun Krishnan, Visvanathan Ramesh
Life of this patent
Estimating the term…
Abstract
A system and method are provided for prior-constrained mean shift analysis of a data array, the system including a processor, an input adapter in signal communication with the processor for receiving at least one data array, and a prior constraints unit in signal communication with the processor for performing a prior-constrained mean shift analysis on the at least one data array; and the method including receiving initialization data, selecting an initial point relative to the initialization data, Gaussian fitting with a prior-constrained mean shift responsive to the initial point to parse a structure, and setting the parsed structure as a prior constraint.
Claims20
A method for identifying a structure of interest within image data, comprising:
- receiving image data;
- receiving an initial point within the received image data;
- transforming the received image data into a scale-space;
- performing geometric fitting using prior-constrained mean shift on the scale-space image data to identify a structure candidate in a vicinity of the initial point;
- using the identified structure candidate to set up a prior constraint for subsequent iterations;
- presenting the identified structure candidate to a user and querying the user to determine whether the identified structure candidate is a structure of interest;
- and
- when the identified structure candidate is determined to not be a structure of interest, repeating the steps of performing geometric fitting using prior-constrained mean shift and presenting an identified structure candidate until it is determined that an identified structure candidate is a structure of interest,
- wherein the above steps are performed by a computer system.
A system for identifying a structure of interest within image data, comprising:
- an image receiving unit for receiving image data;
- a first graphical user interface for displaying the received image data and soliciting an initial point within the received image data from a user;
- an image processing unit for transforming the received image data into a scale-space for performing geometric fitting using prior-constrained mean shift on the scale-space image data to identify a structure candidate in a vicinity of the initial point and for setting up a prior constraint for subsequent iterations;
- and
- a second graphical user interface for presenting the identified structure candidate to a user and querying the user to determine whether the identified structure candidate is a structure of interest,
- wherein when the identified structure candidate is determined to not be a structure of interest, performing geometric fitting using prior-constrained mean shift and presenting an identified structure candidate are repeated until it is determined that an identified structure candidate is a structure of interest.
A computer system comprising:
- a processor;
- and
- a program storage device readable by the computer system, embodying a program of instructions executable by the processor to perform method steps for identifying a structure of interest within image data, the method comprising:
- receiving image data;
- receiving an initial point within the received image data;
- transforming the received image data into a scale-space;
- performing geometric fitting using prior-constrained mean shift on the scale-space image data to identify a structure candidate in a vicinity of the initial point;
- using the identified structure candidate to set up a prior constraint for subsequent iterations;
- presenting the identified structure candidate to a user and querying the user to determine whether the identified structure candidate is a structure of interest;
- and
- when the identified structure candidate is determined to not be a structure of interest, repeating the steps of performing geometric fitting using prior-constrained mean shift and presenting an identified structure candidate until it is determined that an identified structure candidate is a structure of interest.
Dependencies are inferred from the claim text.