Local spectral-covariance or local spectral covariance deficits computation and display for highlighting of relevant material transitions in spectral CT and MR

Patent metadata

Field	Value
Publication number	US-12465294-B2
Application number	US-202118038546-A
Country	US
Kind code	B2
Filing date	Nov 28, 2021
Priority date	Dec 1, 2020
Publication date	Nov 11, 2025
Grant date	Nov 11, 2025

Abstract

The present invention relates to multispectral imaging. In order to improve an identification of relevant multispectral material transitions (in particular caused by injected contrast agent), an apparatus is proposed to use the local maxima of the variances and/or covariances of the intensities of the multi-channel images to locate material transitions. In comparison to gradient vectors, the local variance is not directed and not prone to noise. An alternative apparatus is proposed to use the local covariance deficits of the intensities of the multi-channel images to locate material transitions. The proposed alternative approach is independent of spatial drifts across the image volume.

First claim

The invention claimed is:

1 . A computer-implemented method for processing image data of an object of interest, comprising:
receiving the image data of the object of interest; determining local covariance matrices at a plurality of image positions in at least two mono-energetic images acquired from different spectral channels, wherein each local covariance matrix is a matrix of local variances and local covariances between image intensities at one of the plurality image positions in the at least two mono-energetic images; determining local multispectral covariance deficits based on a comparison between a product of local variances and a product of local covariances through all spectral channel combinations; and providing the local covariance deficits as a machine-learning feature for performing material classification.

2 . The method according to claim 1 , further comprising overlaying values of local covariance deficits at the plurality of image positions with one or more of the at least two mono-energetic images.

3 . The method according to claim 2 , further comprising displaying an overlaying result.

4 . The method according to claim 1 , further comprising applying a pre-trained classifier to perform material classification at one or more of the plurality of image positions based on the local covariance deficits.

5 . The method according to claim 1 , further comprising determining the local covariance deficits in an image space or a projection space.

6 . An apparatus for processing image data of an object of interest, comprising:
a memory that stores a plurality of instructions; and a processor coupled to the memory and configured to execute the plurality of instructions to:
receive the image data of the object of interest;
determine local covariance matrices at a plurality of image positions in at least two mono-energetic images acquired from different spectral channels, wherein each local covariance matrix is a matrix of local variances and local covariances between image intensities at one of the plurality image positions in the at least two mono-energetic images;
determine local multispectral covariance deficits based on a comparison between a product of local variances and a product of local covariances through all spectral channel combinations; and
provide the local covariance deficits as a machine-learning feature for performing material classification.

7 . The apparatus according to claim 6 , wherein the processor is further configured to compute each local variance matrix by a Gaussian convolutions operation.

8 . The apparatus according to claim 6 , wherein the processor is further configured to apply a pre-trained classifier to classify each of the local covariance matrices into a material transition type.

9 . The apparatus according to claim 6 , wherein the plurality of image positions comprises locations of a material transition.

10 . The apparatus according to claim 6 , wherein the processor is further configured to overlay values of local covariance deficits at the plurality of image positions with one or more of the at least two mono-energetic images.

11 . The apparatus according to claim 10 , further comprising a display configured to display an overlaying result.

Assignees

• Koninklijke Philips Nv

Inventors

• Wiemker Rafael
• Goshen Liran
• Nickisch Hannes
• Bontus Claas
• Brosch Tom
• Peters Jochen
• Weese Rolf Jürgen

Classifications

• A61B5/055

  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06F18/251

  of input or preprocessed data · CPC title

• G06F18/2413

  based on distances to training or reference patterns · CPC title