Methods of, and apparatuses for, producing augmented images of a spine

Patent metadata

Field	Value
Publication number	US-10105120-B2
Application number	US-201514620063-A
Country	US
Kind code	B2
Filing date	Feb 11, 2015
Priority date	Feb 11, 2014
Publication date	Oct 23, 2018
Grant date	Oct 23, 2018

Abstract

A computer-implemented method of producing an augmented image of a spine of a patient is disclosed. The method involves: receiving a first ultrasonic volumetric dataset representing a three-dimensional depiction of anatomical features of the spine in a first volume; instantiating a three-dimensional atlas of at least two vertebrae according to the first ultrasonic volumetric dataset; and causing a display to display a rendering of the first ultrasonic volumetric dataset together with a rendering of the atlas. An apparatus for producing the augmented image of the spine of the patient is also disclosed.

First claim

The invention claimed is:

1. A computer-implemented method of producing an augmented image of a spine of a patient, the method comprising:
receiving a first ultrasonic volumetric dataset representing a three-dimensional depiction of anatomical features of the spine in a first volume;
instantiating a three-dimensional atlas of at least two vertebrae according to the first ultrasonic volumetric dataset, wherein the atlas links together modes of variation of at least a mean shape of the at least two vertebrae; and
causing a display to display a rendering of the first ultrasonic volumetric dataset together with a rendering of the atlas.

2. The method of claim 1 further comprising:
receiving a second ultrasonic volumetric dataset representing a three-dimensional depiction of anatomical features of the spine in a second volume different from the first volume;
registering the three-dimensional atlas according to the second ultrasonic volumetric dataset, wherein registering the atlas comprises updating a rigid transform of the atlas according to the second ultrasonic volumetric dataset; and
causing the display to display a rendering of the second ultrasonic volumetric dataset and a rendering of the registered atlas.

3. The method of claim 1 wherein instantiating the three-dimensional atlas according to the first ultrasonic volumetric dataset comprises:
identifying a rigid-body transformation that aligns the mean shape to the first ultrasonic volumetric dataset; and
identifying weights for respective modes of variation of the mean shape.

4. The method of claim 3 wherein instantiating the three-dimensional atlas according to the first ultrasonic volumetric dataset further comprises:
identifying weights for respective modes of variation of a mean pose representing relative positions in the spine of the at least two vertebrae of the three-dimensional atlas.

5. The method of claim 1 wherein receiving the first ultrasonic volumetric dataset comprises receiving the first ultrasonic volumetric dataset from an ultrasonic probe defining a needle guide.

6. The method of claim 5 further comprising causing the display to display a rendering of an anticipated trajectory of a needle in the needle guide.

7. The method of claim 1 further comprising identifying a target defined by two of the at least two vertebrae of the atlas.

8. The method of claim 7 further comprising:
extracting features from the first ultrasonic volumetric dataset;
identifying a target defined by two of the at least two vertebrae of the extracted features from the first ultrasonic volumetric dataset;
generating a comparison of the target defined by two of the at least two vertebrae of the atlas to the target defined by two of the at least two vertebrae of the extracted features from the first ultrasonic volumetric dataset; and
causing the display to display an estimation of reliability of the target defined by two of the at least two vertebrae of the atlas.

9. The method of claim 8 wherein extracting the features from the first ultrasonic volumetric dataset comprises:
recognizing the features in at least some planes in the first ultrasonic volumetric dataset; and
classifying patterns in the features in the at least some planes in the first ultrasonic volumetric dataset.

10. The method of claim 9 wherein recognizing the features in the at least some planes in the first ultrasonic volumetric dataset comprises:
transforming portions the at least some planes in the first ultrasonic volumetric dataset into a sequency domain; and
filtering the sequency domain.

11. The method of claim 9 wherein classifying the patterns in the features in the at least some planes in the first ultrasonic volumetric dataset comprises receiving outputs from a statistical learning algorithm trained to classify patterns in human spines.

12. An apparatus for producing an augmented image of a spine of a patient, the apparatus comprising:
a display; and
at least one processor circuit in communication with the display and configured to:
receive a first ultrasonic volumetric dataset representing a three-dimensional depiction of anatomical features of the spine in a first volume;
instantiate a three-dimensional atlas of at least two vertebrae according to the first ultrasonic volumetric dataset, wherein the atlas links together modes of variation of at least a mean shape of the at least two vertebrae; and
cause the display to display a rendering of the first ultrasonic volumetric dataset together with a rendering of the atlas.

13. The apparatus of claim 12 wherein the at least one processor circuit is further configured to:
receive a second ultrasonic volumetric dataset representing a three-dimensional depiction of anatomical features of the spine in a second volume different from the first volume;
register the three-dimensional atlas according to the second ultrasonic volumetric dataset, wherein the at least one processor circuit is configured to register the atlas by updating a rigid transform of the atlas according to the second ultrasonic volumetric dataset; and
cause the display to display a rendering of the second ultrasonic volumetric dataset and a rendering of the registered atlas.

14. The apparatus of claim 12 wherein the at least one processor circuit is configured to instantiate the three-dimensional atlas according to the first ultrasonic volumetric dataset by:
identifying a rigid-body transformation that aligns the mean shape to the first ultrasonic volumetric dataset; and
identifying weights for respective modes of variation of the mean shape.

15. The apparatus of claim 14 wherein the at least one processor circuit is further configured to instantiate the three-dimensional atlas according to the first ultrasonic volumetric dataset by:
identifying weights for respective modes of variation of a mean pose representing relative positions in the spine of the at least two vertebrae of the three-dimensional atlas.

16. The apparatus of claim 12 further comprising an ultrasonic probe in communication with the at least one processor circuit, wherein the ultrasonic probe defines a needle guide.

17. The apparatus of claim 16 wherein the at least one processor circuit is further configured to cause the display to display a rendering of an anticipated trajectory of a needle in the needle guide.

18. The apparatus of claim 12 wherein the at least one processor circuit is further configured to identify a target defined by two of the at least two vertebrae of the atlas.

19. The apparatus of claim 18 wherein the at least one processor circuit is further configured to:
extract features from the first ultrasonic volumetric dataset;
identify a target defined by two of the at least two vertebrae of the extracted features from the first ultrasonic volumetric dataset;
generate a comparison of the target defined by two of the at least two vertebrae of the atlas to the target defined by two of the at least two vertebrae of the extracted features from the first ultrasonic volumetric dataset; and
cause the display to display an estimation of reliability of the target defined by two of the at least two vertebrae of the atlas.

20. The apparatus of claim 19 wherein the at least one processor circuit is configured to extract the features from the first ultrasonic volumetric dataset by:
recognizing the features in at least some planes in the first ultrasonic volumetric dataset; and
classifying patterns in the features in the at least some planes in the firs

Assignees

• Univ British Columbia

Inventors

• Rasoulian Abtin
• Rohling Robert
• Abolmaesumi Purang
• Pesteie Mehran

Classifications

• A61B8/483

  involving the acquisition of a 3D volume of data · CPC title

• A61B8/4461

  Features of the scanning mechanism, e.g. for moving the transducer within the housing of the probe · CPC title

• G06T2200/04

  involving 3D image data · CPC title

• A61B8/0875 Primary

  for diagnosis of bone · CPC title

• A61B8/4444

  related to the probe · CPC title