Real time interactive segmentation of pulmonary nodules with control parameters
View Patent ↗Segmentation of pulmonary nodules from digital volumetric image includes segmenting, automatically, the pulmonary nodule from attached anatomical structures by analyzing a structure of interest, and providing a template according to an analyzed structure of interest, wherein the template displays a segmentation of a volume of interest including an object of interest. The template can be adjusted according to a one or more adjustable parameters. The method stores values of the parameters according to the object of interest, and stores a segmentation of the object of interest according to the values of the parameters. The segmentation is refined by extracting and labeling surrounding anatomical structures, defining each structure touching a boundary of a volume of interest as an elongated object, determining a size and shape for each structure, and determining a distance of a current structure to the segmentation result, upon determining the distance to be small compared to a threshold.
1. A method for refining a segmentation of an object of interest from a digital volumetric image comprising the steps of:
providing the segmentation of object of interest;
determining a core of the object of interest;
initializing a template based on the core, the template having an adjustable parameter for determining a refined segmentation of the object of interest, wherein the core of the object of interest is a three-dimensional volume within the object of interest and the initialized template has a volume smaller than the volume of the core; and
adjusting the parameter to add or delete a structure to or from the refined segmentation of the object of interest.
2. The method of claim 1 , further comprising the steps of:
storing a value of the parameter;
storing a refined segmentation of the object of interest according to the value of the parameter; and
comparing a stored refined segmentation to a second segmentation of the object of interest determined using the value of the parameter.
3. The method of claim 1 , further comprising the step of extracting the object of interest using an intensity threshold and three-dimensional connectivity information.
4. The method of claim 3 , further comprising the step of selecting the intensity threshold for segmentation according to a local histogram analysis of the digital volumetric image.
5. The method of claim 1 , wherein the core is determined according to morphological operations.
6. The method of claim 1 , further comprising the step of determining, recursively, a cross correlation to the structure of interest at a plurality of growth steps.
7. The method of claim 1 , further comprising the steps of:
determining a cross correlation for the object of interest; and
determining a cutoff value.
8. The method of claim 7 , wherein the template is suggested according to the cutoff value.
9. The method of claim 1 , further comprising the step of determining an orientation of the object of interest according to an eigenvlues and an eignenvector.
10. The method of claim 1 , further comprising the step of adjusting, interactively, the parameter in real time.