Method and device of extracting label in medical image
AssigneeBoe Technology Group Co., Ltd.
InventorYingying Li
Life of this patent
Estimating the term…
Abstract
A method and a device of extracting a label in a medical image are provided. The method includes: performing an edge detection on the medical image by using an edge detection algorithm, to acquire edge information in the medical image; determining at least one target area defined by the edge information; performing a fitting process on the at least one target area, to obtain a fitting area; and extracting the label in the medical image by selecting, from the fitting areas, at least one target fitting area matching a preset condition, wherein the preset condition is set based on a characteristic of the fitting area.
Claims17
A method of extracting a label in a medical image, comprising:
- performing an edge detection on the medical image by using an edge detection algorithm, to acquire edge information in the medical image;
- determining at least one target area defined by the edge information;
- performing a fitting process on the determined at least one target area, to obtain at least one fitting area;
- and
- extracting the label in the medical image by selecting, from the fitting areas, at least one target fitting area matching a preset condition, wherein the preset condition is set based on a characteristic of the fitting area,
- wherein performing the fitting process on the determined at least one target area comprises:
- sorting the at least one target area into categories corresponding to different lesion types in the medical image;
- and
- performing the fitting process on the at least one target area of a same category, to obtain the fitting area of the category.
A device for extracting a label in a medical image, comprising a memory, a processor and a computer instruction stored in the memory, wherein the processor is configured to execute the computer instruction, to implement steps of:
- performing an edge detection on the medical image by using an edge detection algorithm, to acquire edge information in the medical image;
- determining at least one target area defined by the edge information;
- performing a fitting process on the determined at least one target area, to obtain at least one fitting area;
- and
- extracting the label in the medical image by selecting, from the fitting areas, at least one target fitting area matching a preset condition, wherein the preset condition is set based on a characteristic of the fitting area,
- wherein performing the fitting process on the determined at least one target area comprises:
- sorting the at least one target area into categories corresponding to different lesion types in the medical image;
- and
- performing the fitting process on the at least one target area of a same category, to obtain the fitting area of the category.
Dependencies are inferred from the claim text.