Method and device for automatic or semi-automatic segmentation of a 3D image data set
View Patent ↗In a method and apparatus for automatic or semi-automatic segmentation of a 3D image data set, acquired by a medical imaging apparatus, of an examination region that includes an organ, the 3D image data set is provided to a computer/processor, which is also provided with information with designating the type of organ imaged in the examination region. The 3D image data set is automatically segmented in the computer/processor using a model-based segmentation algorithm, wherein the designated type of organ is used as a basis of the model. The 3D data set is also automatically or semi-automatically segmented using a greyscale value-based segmentation algorithm. At least one of the segmentation results is displayed.
1. A method for automatic or semi-automatic segmentation of a 3D image data set, comprising:
providing a computerized processor with a 3D image data set, acquired with a medical imaging apparatus, representing an examination region of an examination subject, said examination region comprising an anatomical organ;
providing information to said computerized processor designating a type of said organ in said examination region;
in said computerized processor, using the designated type of said organ to obtain a model-based segmentation algorithm wherein the designated type of said organ is a basis of the model in the model-based segmentation algorithm;
in said computerized processor, automatically segmenting the 3D image data set by executing said model-based segmentation algorithm based on said designated type of said organ, to produce a segmentation result;
after executing said model-based segmentation algorithm, automatically or semi-automatically segmenting said 3D image data set in said computerized processor by executing a greyscale value-based segmentation algorithm that uses said segmentation result produced by said model, to produce another segmentation result; and
at a display screen in communication with said computerized processor, visually displaying at least one of said segmentation results.
2. A method as claimed in claim 1 comprising comparing the segmentation result obtained by said segmentation with said model-based segmentation algorithm with said segmentation result obtained with said greyscale value-based segmentation algorithm, to obtain a comparison result, and displaying said comparison result at said display screen.
3. A method as claimed in claim 1 comprising providing said computerized processor with a manually-entered input that designates which of said model-based segmentation algorithm and said greyscale value-based segmentation algorithm should be implemented in said computerized processor, and implementing the model-based segmentation algorithm and the greyscale value-based segmentation algorithm in said computerized processor in a sequence as designated by said input.
4. A method as claimed in claim 1 comprising implementing said greyscale value-based segmentation algorithm semi-automatically in said computerized processor dependent on a manual input entered into said computerized processor that designates image points associated with at least a portion of said organ.
5. A method as claimed in claim 1 comprising executing said greyscale value-based segmentation algorithm automatically in said computerized processor.
6. A method as claimed in claim 5 comprising using at least one image point in said segmentation result of said model-based segmentation algorithm as being associated with at least a portion of said organ in executing said greyscale value-based segmentation algorithm.
7. A method as claimed in claim 1 comprising, after obtaining said segmentation result and said another segmentation result by respectively executing said model-based segmentation algorithm and said greyscale value-based segmentation algorithm, manually entering an input into said computerized processor that associates at least one image point with at least a portion of said organ and, in said computerized, automatically correcting said another segmentation result dependent on said input.
8. A method as claimed in claim 1 comprising providing said computerized processor with said 3D image data set as a 3D image data set selected from the group consisting of a magnetic resonance data set, a computed tomography data set, and an angiography data set.
9. A method as claimed in claim 1 comprising providing said computerized processor with a 3D cardiac image data set as said 3D image data set, and designating the left atrium of the heart of the examination subject as said type of said organ.
10. An apparatus for automatic or semi-automatic segmentation of a 3D image data set, comprising:
a computerized processor provided with a 3D image data set, acquired with a medical imaging apparatus, representing an examination region of an examination subject, said examination region comprising an anatomical organ;
said computerized processor being provided with information designating a type of said organ in said examination region;
said computerized processor being configured to use the designated type of said organ to obtain a model-based segmentation algorithm wherein the designated type of said organ is a basis of the model in the model-based segmentation algorithm;
said computerized processor being configured to automatically segment the 3D image data set by executing said model-based segmentation algorithm based on said designated type of said organ, to produce a segmentation result;
said computerized processor being configured to automatically or semi-automatically segment said 3D image data set after executing said model-based segmentation algorithm, by executing a greyscale value-based segmentation algorithm that uses said segmentation result produced by said model, to produce another segmentation result; and
a display screen in communication with said computerized processor, said computerized processor being configured to visually display at least one of said segmentation results.
11. A medical imaging apparatus comprising:
a data acquisition device configured to obtain a 3D image data set representing an examination region of an examination subject with which the data acquisition device interacts, said 3D image data set including a representation of an anatomical organ in said examination region;
a computerized processor provided with a 3D image data set, acquired with a medical imaging apparatus, representing an examination region of an examination subject, said examination region comprising an anatomical organ;
said computerized processor being provided with information designating a type of said organ in said examination region;
said computerized processor being configured to use the designated type of said organ to obtain a model-based segmentation algorithm wherein the designated type of said organ is a basis of the model in the model-based segmentation algorithm;
said computerized processor being configured to automatically segment the 3D image data set by executing said model-based segmentation algorithm based on said designated type of said organ, to produce a segmentation result;
said computerized processor being configured to automatically or semi-automatically segment said 3D image data set after executing said model-based segmentation algorithm, by executing a greyscale value-based segmentation algorithm that uses said segmentation result produced by said model, to produce another segmentation result; and
a display screen in communication with said computerized processor, said computerized processor being configured to visually display at least one of said segmentation results.