Applications of automatic anatomy recognition in medical tomographic imagery based on fuzzy anatomy models
AssigneeThe Trustees of the University of Pennsylvania
InventorsJayaram K. Udupa, Dewey Odhner, Drew A. Torigian, Yubing Tong
Life of this patent
Estimating the term…
Abstract
A computerized method of providing automatic anatomy recognition (AAR) includes gathering image data from patient image sets, formulating precise definitions of each body region and organ and delineating them following the definitions, building hierarchical fuzzy anatomy models of organs for each body region, recognizing and locating organs in given images by employing the hierarchical models, and delineating the organs following the hierarchy. The method may be applied, for example, to body regions including the thorax, abdomen and neck regions to identify organs.
Claims21
A computerized method, comprising the steps of:
- building a fuzzy anatomy model of a body region of interest from an existing set of patient images for the body region;
- obtaining an image of a particular patient body region of interest, wherein obtaining the image comprises mapping slice locations associated with the particular patient body region of interest from a scanner coordinate system to slice locations in a standardized anatomic space;
- identifying where a volume-to-area correlation becomes maximal for one or more of an abdomen, a chest, or a neck of the patient;
- using automatic anatomy recognition (AAR) to recognize objects in the particular patient body region of interest and to output spatial information associated with the recognized objects;
- and
- delineating, using automatic anatomy recognition (AAR) and based at least on the spatial information associated with the recognized objects, the recognized objects to determine one or more contours or boundaries of the recognized objects.
A system, comprising:
- a database that stores image data from patient image sets;
- an imaging device that obtains an image of a particular patient body region of interest, wherein slice locations associated with the particular patient body region of interest are mapped from a scanner coordinate system to slice locations in a standardized anatomic space;
- a memory storing computer instructions;
- and
- a processor that processes said computer instructions to build a fuzzy anatomy model of the body region of interest from existing patient image sets, uses automatic anatomy recognition (AAR) to recognize and delineate objects in the particular patient body region of interest, and provides contours of delineated objects,
- wherein the processor further processes said computer instructions to identify where a volume-to-area correlation becomes maximal for one or more of a subject's abdomen, chest, or neck.
Dependencies are inferred from the claim text.