Method and system for image processing
AssigneeShanghai United Imaging Healthcare Co., Ltd.
InventorCe WANG
Life of this patent
Estimating the term…
Abstract
A method and system for image processing is provided. The technique includes acquiring data related to the processing, performing a pre-processing of the data, performing a segmentation of a subject, performing a post-processing of the result of the segmentation and managing storage of the data. The post-process includes a calibrating and a rendering of the da
Claims21
1-49. (canceled)
A system for segmenting a nodule region from a lung image, comprising:
- a storage device storing a set of instructions;
- and
- at least one processor in communication with the storage device, wherein when executing the instructions, the at least one processor is configured to cause the system to:
- obtain the lung image having one or more nodules, the lung image including a plurality of slices;
- identify a slice from the plurality of slices;
- determine a long axis on the identified slice of the lung image based on a user input, the long axis traversing an abnormal region of the slice;
- determine a region of interest (ROI) based on the long axis;
- perform a coarse segmentation in the ROI of the lung image to obtain a target region in the lung image, the target region including a central region and a boundary region;
- perform a fine segmentation on the boundary region of the image to obtain a parting segmentation region, the fine segmentation including classifying and labelling each voxel in the boundary region;
- and
- fuse the central region and the parting segmentation region to obtain the nodule region.
A method implemented on a computing device which has at least one processor and a storage device for segmenting a nodule region from a lung image, comprising:
- obtaining, by the at least one processor, the lung image having one or more nodules, the lung image including a plurality of slices;
- identifying a slice from the plurality of slices;
- determining, by the at least one processor, a long axis on the identified slice of the lung image based on a user input, the long axis traversing an abnormal region of the slice;
- determining, by the at least one processor, a region of interest (ROI) based on the long axis;
- performing, by the at least one processor, a coarse segmentation in the ROI of the lung image to obtain a target region in the lung image, the target region including a central region and a boundary region;
- performing, by the at least one processor, a fine segmentation on the boundary region of the image to obtain a parting segmentation region, the fine segmentation including classifying and labelling each voxel in the boundary region;
- and
- fusing, by the at least one processor, the central region and the parting segmentation region to obtain the nodule region.
A non-transitory computer readable medium comprising executable instructions that, when executed by a computing device, cause the computing device to:
- obtain the lung image having one or more nodules, the lung image including a plurality of slices;
- identify a slice from the plurality of slices;
- determine a long axis on the identified slice of the lung image based on a user input, the long axis traversing an abnormal region of the slice;
- determine a region of interest (ROI) based on the long axis;
- perform a coarse segmentation in the ROI of the lung image to obtain a target region in the lung image, the target region including a central region and a boundary region;
- perform a fine segmentation on the boundary region of the image to obtain a parting segmentation region, the fine segmentation including classifying and labelling each voxel in the boundary region;
- and
- fuse the central region and the parting segmentation region to obtain the nodule region.
Dependencies are inferred from the claim text.