Description:PLEASE REFER THE ATTACHMENT ,

WE CLAIM:
1. A method of guiding navigation of an imaging tool, the method comprising:
receiving a first three-dimensional (3D) model representative of a bronchial tree
structure associated with lungs, wherein a location of an abnormality associated with the
lungs within the first 3D model is predetermined;
receiving a second 3D model representative of blood vessels associated with the
lungs;
superimposing the first 3D model and the second 3D model, to obtain a superimposed
3D model representative of a combination of the bronchial tree structure and the blood
vessels associated with the lungs;
generating a path from an origin location to an abnormality location within the
superimposed 3D model, wherein the path bypasses the blood vessels;
receiving, in real-time, at least one real-time image from an imaging tool when the
imaging tool moves through bronchial tree associated with the lungs; and
plotting a location of the imaging tool in the superimposed 3D model, based on a
mapping of the at least one real-time image with the superimposed 3D model.
2. The method as claimed in claim 1 comprising:
generating the first 3D model from a plurality of two-dimensional (2D) images
associated with the lungs, wherein a location of an abnormality associated with the lungs is
predetermined in the plurality of 2D images; and
locating the abnormality associated with the lungs in the first 3D model, by spatially
correlating the abnormality location within the plurality of 2D images with the first 3D
model.
3. The method as claimed in claim 1 comprising:
wherein the abnormality location associated with the lungs in the 2D images is
determined, using a Machine Learning (ML) model.
4. The method as claimed in claim 2, wherein the first 3D model is generated from the
plurality of 2D images associated with the lungs, using a region-growing procedure.
5. The method as claimed in claim 4, wherein the second 3D model representative of the
blood vessels is generated by:
applying segmented lung as a mask to the plurality of 2D images; and
generating the second 3D model from the plurality of 2D images associated with the
lungs based on the mask applied, using the Otsu segmentation procedure.
6. The method as claimed in claim 1, wherein locating the abnormality associated with the
lungs in the first 3D model comprises:
extracting pixel spacing data and slice thickness data associated with the 2D images;
and
converting 2D pixel coordinates of each pixel of the 2D images to corresponding 3D
coordinates based on the pixel spacing information and the slice thickness data, wherein the
3D model is generated based on 3D coordinates.
7. The method as claimed in claim 2, wherein the first 3D model is generated from the
plurality of 2D images using a region-growing procedure, and wherein each of the plurality
of 2D images is a Computed Tomography (CT) scan.
8. The method as claimed in claim 1, wherein generating the path from the origin location to
the abnormality location within the superimposed 3D model comprises:
identifying a plurality of points representative of end-points of a plurality of branches
of the bronchial tree structure;
generating a centerline through the plurality of points;
selecting an origin point and a destination point corresponding to the abnormality
location within the superimposed 3D model; and
generating the path along a shortest centerline connecting the origin point to the
destination point.
9. The method as claimed in claim 8, wherein the centerline is generated using Voronoi
technique.
10. The method as claimed in claim 9 further comprising:
upon generating the centerline through the plurality of points, identifying one or more
branches within the centerline; and
labelling each of the one or more branches within the centerline, with a predetermined
label.