Systems and methods for image segmentation using a deformable atlas
AssigneeGeneral Electric Company
InventorsXiaofeng Liu, Albert Montillo, Ek Tsoon Tan, John F. Schenck
Life of this patent
Estimating the term…
Abstract
Systems and methods for image segmentation using a deformable atlas are provided. One method includes obtaining one or more target images, obtaining one or more propagated label probabilities for the one or more target images, and segmenting the one or more target images using a cost function of a deformable atlas model. The method further includes identifying segmented structures within the one or more target images based on the segmented one or more target images.
Claims20
A non-transitory computer readable storage medium for segmenting an image using a processor, the non-transitory computer readable storage medium including instructions to command the processor to:
- obtain one or more target images;
- obtain one or more propagated label probabilities for the one or more target images;
- segment the one or more target images using a cost function of a deformable atlas model;
- and
- identify segmented structures within the one or more target images based on the segmented one or more target images.
A Magnetic Resonance Imaging (MRI) system comprising:
- an imaging portion configured to acquire one or more target images of an object;
- and
- a processing portion configured to determine one or more propagated label probabilities for the one or more target images, the processing portion further comprising a deformable atlas module configured to segment the one or more target images using a cost function of a deformable atlas model to identify segmented structures within the one or more target images based on the segmented one or more target images.
A method for image segmentation, the method comprising:
- obtaining one or more target images;
- obtaining one or more propagated label probabilities for the one or more target images;
- segmenting the one or more target images using a cost function of a defotinable atlas model;
- and
- identifying segmented structures within the one or more target images based on the segmented one or more target images.
Dependencies are inferred from the claim text.