Identification method based on connectivity profiles

Patent metadata

Field	Value
Publication number	US-9740946-B2
Application number	US-201314903806-A
Country	US
Kind code	B2
Filing date	Jul 8, 2013
Priority date	Jul 8, 2013
Publication date	Aug 22, 2017
Grant date	Aug 22, 2017

Abstract

The present invention relates to a medical data processing method for identifying an entity of the nervous system, in particular the brain, of a patient, wherein the method is designed to be executed by a computer and comprises the following steps: a) acquiring target connectivity data comprising target connectivity information about the probability of a target entity being connected to other entities of the nervous system; b) acquiring candidate connectivity data comprising candidate connectivity information about the probability of at least one candidate entity being connected to other entities of the nervous system; and c) determining similarity data for each of the at least one candidate entities on the basis of the candidate connectivity data and the target connectivity data, wherein the similarity data comprise similarity information about the similarity between the candidate entity and the target entity.

First claim

The invention claimed is:

1. A medical image analysis system for identifying an entity of the nervous system, comprising:
a computer having one or more processors operable to execute instructions in memory, the instructions operable for:
receiving by the processor target connectivity data including target connectivity information about the probability of a target entity being connected to other entities of the nervous system;
wherein the target connectivity data includes at least a target connectivity data image data set and can be at least one voxel, region or structure within the target connectivity data image data set;
receiving by the processor candidate connectivity data including candidate connectivity information about a probability of one of a plurality of candidate entities being connected to other entities of the nervous system;
wherein the candidate connectivity data includes at least a candidate connectivity data image data set and can be a at least one voxel, region or structure within the candidate connectivity data image data set; and
determining, by the instructions operating on the at least one processor, similarity data for each of the plurality of candidate entities on the basis of the candidate connectivity data and the target connectivity data, wherein the similarity data comprise similarity information about the similarity between the candidate entity and the target entity, wherein criteria are defined to find the candidate entity from the plurality of candidate entities which most likely represents the target entity.

2. A medical image analysis system, comprising a computer having a processor configured to execute a computer-implemented medical image analysis method for identifying an entity of the nervous system, of a patient, wherein the method comprises the following steps:
a) receiving, at the processor, target connectivity data comprising target connectivity information about the probability of a target entity being connected to other entities of the nervous system;
b) receiving, at the processor, candidate connectivity data comprising candidate connectivity information about a probability of one of a plurality of candidate entities being connected to other entities of the nervous system; and
c) determining, by the processor, similarity data for each of the plurality of candidate entities on the basis of the candidate connectivity data and the target connectivity data, wherein the similarity data comprise similarity information about the similarity between the candidate entity and the target entity, wherein criteria are defined to find the candidate entity from the plurality of candidate entities which most likely represents the target entity.

3. A computer implemented medical image analysis method for identifying an entity of the nervous system of a patient, the method executed by a computer having a processor, comprising:
a) receiving, at the processor, target connectivity data comprising target connectivity information about the probability of a target entity being connected to other entities of the nervous system;
b) receiving, at the processor, candidate connectivity data comprising candidate connectivity information about a probability of one of a plurality of candidate entities being connected to other entities of the nervous system; and
c) determining, by the processor, similarity data for each of the plurality of candidate entities on the basis of the candidate connectivity data and the target connectivity data, wherein the similarity data comprise similarity information about the similarity between the candidate entity and the target entity, wherein criteria are defined to find the candidate entity from the plurality of candidate entities which most likely represents the target entity.

4. The method according to claim 3 , wherein the connectivity information comprises information about at least one of the anatomical connectivity probability and the functional connectivity probability.

5. The method according claim 3 , wherein the at least one candidate entity is constituted by a voxel, a region or a structure within a data set of the nervous system.

6. The method according to claim 5 , wherein the data set is an image data set which is in particular obtained by diffusion tensor imaging (DTI)-based tractography.

7. The method according to claim 3 , wherein the target entity is constituted by a voxel, a region or a structure within a previously acquired medical image data set obtained by DTI-based tractography.

8. The method according to claim 3 , wherein a feature space is determined which comprises n dimensions for n connectivity features assigned to the target entity, wherein each of the features describes the connectivity probability between the target entity and another entity which is constituted by a voxel, a region or a structure.

9. The method according to claim 8 , wherein a connectivity vector is determined for each of the at least one candidate entities and the target entity, wherein the connectivity vector comprises n dimensions and is based on the connectivity information about the assigned entity.

10. The method according to claim 3 , wherein the similarity data comprise similarity information about the similarity between the target entity and the at least one candidate entity, such as the similarity between the connectivity vector assigned to the target entity and the connectivity vector(s) assigned to the at least one candidate entity.

11. The method according to claim 10 , wherein the similarity data are determined by determining distance data which comprises distance information about the distance between the end points of the connectivity vectors in the feature space.

12. The method according to claim 11 , wherein the distance is constituted by a measure of distance which is obtained from a plurality of subjects.

13. The method according to claim 3 , wherein the connectivity information acquired comprises information about direct-path connectivity and/or indirect-path connectivity.

14. The method according to claim 3 , wherein probability data are determined on the basis of at least one logical query which provides at least one criterion for considering and/or excluding one or more candidate entities.

15. The method according to claim 3 , wherein an elastic fusion procedure, is performed on an image data set of the nervous system on the basis of the similarity data determined.

16. The method according claim 3 , wherein a map of the nervous system is created on the basis of the similarity data determined.

17. A non-transitory computer readable program storage medium storing a computer program which, when executed on a processor of a computer or loaded into the memory of a computer, causes the computer to perform a computer-implemented method for identifying an entity of the nervous system of a patient the method comprising:
a) receiving, at the processor, target connectivity data comprising target connectivity information about the probability of a target entity being connected to other entities of the nervous system;
b) receiving, at the processor, candidate connectivity data comprising candidate connectivity information about a probability of one of a plurality of candidate entities being connected to other entities of the nervous system; and
c) determining, by the processor, similarity data for each of the plurality of candidate entities on the basis of the candidate connectivity data and the target connectivity data, wherein the similarity data comprise similarity information about the similarity between the candidate

Assignees

• Brainlab Ag

Inventors

• Varkuti Bálint
• Lachner Rainer

Classifications

• G06V40/10

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title

• G06T7/11 Primary

  Region-based segmentation · CPC title

• G06F18/2415

  based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate · CPC title

• G06F18/2413

  based on distances to training or reference patterns · CPC title

• G06T7/187

  involving region growing; involving region merging; involving connected component labelling · CPC title