Granted Patent B2

US 12,223,666 · App. 18/448,289 · Granted Feb 11, 2025

Inventors: Nitin Tandon (Houston, TX); Mehmet Kadipasaoglu (Houston, TX); Kevin Pham (Sugar Lang, TX); Cristian Donos (Bucharest, RO); Kiefer Forseth (Houston, TX); Patrick Sarahan Rollo (Houston, TX)

Assignee: THE BOARD OF REGENTS OF THE UNIVERSITY OF TEXAS SYSTEM

G06T7/37A61B34/10G01R33/5607G06T7/11G06T7/38A61B2034/102A61B2034/107G06T2207/10081G06T2207/10088G06T2207/10104G06T2207/30016

Abstract

Claims (109)

1. A method, comprising:

obtaining a first imaging scan and a second imaging scan of a single subject brain;

converting the first imaging scan to a first dataset, and the second imaging scan to a second dataset;

applying an adaptive segmentation algorithm to the first dataset and the second dataset, wherein the adaptive segmentation algorithm performs automatic intensity-based tissue classification to generate a first labeled dataset and a second labeled dataset;

automatically co-registering the first labeled dataset and the second labeled dataset to each other to generate a transformation matrix based on the first labeled dataset and the second labeled dataset; and

applying the transformation matrix to align the first dataset and the second dataset.

2. The method of claim 1 , wherein:

the single subject brain comprises a cerebrospinal fluid region;

the first imaging scan is a contrast weighted scan and the first dataset is a contrast weighted dataset; and

the method further comprises:

selecting voxels of the first dataset identified as belonging to the cerebrospinal fluid region;

applying a filtering algorithm to identify voxels of the first dataset representing blood vessels and assign a vesselness weight value to each voxel;

integrating the vesselness weight values into the first dataset; and

after aligning the first dataset and the second dataset, converting the first dataset to a surface anatomical mesh model.

3. The method of claim 1 , wherein the adaptive segmentation algorithm assigns a numeric label value to each voxel of the first dataset or the second dataset.

4. The method of claim 1 wherein the method further comprises:

defining predicted target point coordinates and entry point coordinates for a probe based on target point coordinates and entry point coordinates of previously implanted probes or by user defined target and entry points;

defining a trajectory for the probe based on a mean target coordinates and mean entry point coordinates;

adjusting the trajectory to intersect with a nearest voxel assigned a label of an anatomical region of interest;

checking proximity of the trajectory to critical structures based on user defined constraints and/or user defined modification of the trajectory to satisfy the user defined constraints; and

superimposing the trajectory on the second data set to form a planning dataset.

5. The method of claim 1 , wherein:

the first imaging scan is an anatomical scan, the second imaging scan is a post-implantation imaging scan, the first dataset is an anatomical dataset, and the second dataset is a post-implantation imaging dataset; and

the method further comprises:

obtaining a third imaging scan used to guide electrode implantation during surgery;

converting the third imaging scan to a third dataset;

aligning a third dataset with the first dataset;

obtaining a trajectory implant data file created during the electrode implantation;

generating a planned trajectory dataset, based on trajectory implant data file, that includes dummy objects disposed at locations of electrode geometry;

aligning the planned trajectory dataset to the imaging dataset; and

automatically identifying and labelling electrodes in an electrode dataset based on the dummy objects of the trajectory implant data file.

6. A non-transitory computer-readable medium encoded with instructions that are executable by one or more processors to:

obtain a first imaging scan and a second imaging scan of a single subject brain;

convert the first imaging scan to a first dataset, and the second imaging scan to a second dataset;

apply an adaptive segmentation algorithm to the first dataset and the second dataset, wherein the adaptive segmentation algorithm performs automatic intensity-based tissue classification to generate a first labelled dataset and a second labeled dataset;

automatically co-register the first labeled dataset and the second labeled dataset to each other to generate a transformation matrix based on the first labeled dataset and the second labeled dataset; and

apply the transformation matrix to align the first dataset and the second dataset.

7. The non-transitory computer-readable medium of claim 6 , wherein:

the single subject brain comprises a cerebrospinal fluid region;

the first imaging scan is a contrast weighted scan and the first dataset is a contrast weighted dataset; and

the instructions are executable by the one or more processors to:

select, based on the labeled dataset, voxels of the first dataset identified as belonging to the cerebrospinal fluid region;

apply a filtering algorithm to identify voxels of the first dataset representing blood vessels and assign a vesselness weight value to each voxel;

integrate the vesselness weight values into the first dataset; and

after aligning the first dataset and the second dataset, convert the first dataset to a surface anatomical mesh model.

8. The non-transitory computer-readable medium of claim 6 , wherein the adaptive segmentation algorithm assigns a numeric label value to each voxel of the first dataset or the second dataset.

9. The non-transitory computer-readable medium of claim 6 , wherein:

the first imaging scan is a contrast weighted scan and the second imaging scan is an anatomical scan; and

the instructions are executable by the one or more processors to:

define predicted target point coordinates and entry point coordinates for a probe based on target point coordinates and entry point coordinates of previously implanted probes or by user defined target and entry points;

define a trajectory for the probe based on a mean target coordinates and mean entry point coordinates;

adjust the trajectory to intersect with a nearest voxel assigned a label of an anatomical region of interest;

check proximity of the trajectory to critical structures based on user defined constraints and/or user defined modification of the trajectory to satisfy the user defined constraints; and

superimpose the trajectory on the second data set to form a planning dataset.

10. The non-transitory computer-readable medium of claim 6 , wherein:

the first imaging scan is an anatomical scan, the second imaging scan is a post-implantation imaging scan, the first dataset is an anatomical dataset, and the second dataset is a post-implantation dataset; and

the instructions are executable by the one or more processors to:

obtain a third imaging scan used to guide electrode implantation during surgery;

convert the third imaging scan to a third dataset;

align a third dataset with the first dataset;

obtain a trajectory implant data file created during the electrode implantation;

generate a planned trajectory dataset, based on trajectory implant data file, that includes dummy objects disposed at locations of electrode geometry;

align the planned trajectory dataset to the post-implantation dataset; and

automatically identify and label electrodes in an electrode dataset based on the dummy objects of the trajectory implant data file.

11. A system, comprising:

one or more processors; and

a memory coupled to the one or more processors, wherein the memory stores instructions that configure the one or more processors to:

obtain a first imaging scan and a second imaging scan of a subject brain;

convert the first imaging scan to a first dataset, and the second imaging scan to a second dataset;

apply an adaptive segmentation algorithm to the first dataset and the second dataset, wherein the adaptive segmentation algorithm performs automatic intensity-based tissue classification to generate a first labeled dataset and a second labeled dataset;

automatically co-register the first labeled dataset and the second labeled dataset to each other to generate a transformation matrix based on the first labeled dataset and the second labeled dataset; and

apply the transformation matrix to align the first dataset and the second dataset.

12. The system of claim 11 , wherein:

the single subject brain comprises a cerebrospinal fluid region;

the first imaging scan is a contrast weighted scan and the first dataset is a contrast weighted dataset; and

the instructions configure the one or more processors to:

select, based on the labeled dataset, voxels of the first dataset identified as belonging to the cerebrospinal fluid region;

apply a filtering algorithm to identify voxels of the first dataset representing blood vessels and assign a vesselness weight value to each voxel;

integrate the vesselness weight values into the first dataset; and

after aligning the first dataset and the second dataset, convert the first dataset to a surface anatomical mesh model.

13. The system of claim 11 , wherein the adaptive segmentation algorithm assigns a numeric label value to each voxel of the first dataset or the second dataset.

14. The system of claim 11 , wherein the instructions configure the one or more processors to:

extract voxels from the first dataset having a label corresponding to a subcortical region of interest;

form a third dataset containing the voxels extracted from the first dataset;

convert the third dataset into a first subcortical surface mesh model;

compute curvature and sulcal features of the first subcortical surface mesh model;

align the first subcortical surface mesh model to a subcortical atlas of the region of interest using the curvature and sulcal features; and

overlay the first subcortical surface mesh model aligned to an atlas of the subcortical region of interest on a second subcortical surface mesh model, the second subcortical surface mesh model having a standardized number of nodes that enables a one-to-one correspondence between node identity and atlas location; and

assign coordinates of nodes of the first subcortical surface mesh model to the second subcortical structure surface mesh model such that the second subcortical surface mesh model assumes a topology of the first subcortical structure surface mesh model.

15. The system of claim 11 , wherein:

the first imaging scan is a contrast weighted scan and the second imaging scan is an anatomical scan; and

the instructions configure the one or more processors to:

define predicted target point coordinates and entry point coordinates for a probe based on target point coordinates and entry point coordinates of previously implanted probes or by user defined target and entry points;

define a trajectory for the probe based on a mean target coordinates and mean entry point coordinates;

adjust the trajectory to intersect with a nearest voxel assigned a label of an anatomical region of interest;

check proximity of the trajectory to critical structures based on user defined constraints and/or user defined modification of the trajectory to satisfy the user defined constraints; and

superimpose the trajectory on the second data set to form a planning dataset.

16. The system of claim 11 , wherein:

the first imaging scan is an anatomical scan, the second imaging scan is a post-implantation imaging scan, the first dataset is an anatomical dataset, and the second dataset is a post-implantation imaging dataset; and

the instructions configure the one or more processors to:

obtain a third imaging scan used to guide electrode implantation during surgery;

convert the third imaging scan to a third dataset;

align a third dataset with the first dataset;

obtain a trajectory implant data file created during the electrode implantation;

generate a planned trajectory dataset, wherein:

the planned trajectory dataset is based on trajectory implant data file; and

the planned trajectory dataset includes dummy objects disposed at locations of electrode geometry;

align the planned trajectory dataset to the post-implantation imaging dataset; and

identify electrodes in an electrode dataset based on the dummy objects of the trajectory implant data file.

Continuity (3)

References Cited (33)