System, method, and computer program product for predicting, anticipating, and/or assessing tissue characteristics

Patent metadata

Field	Value
Publication number	US-11915361-B2
Application number	US-202017753564-A
Country	US
Kind code	B2
Filing date	Sep 17, 2020
Priority date	Sep 18, 2019
Publication date	Feb 27, 2024
Grant date	Feb 27, 2024

Abstract

A system, method, and computer program product for predicting, anticipating, and/or assessing tissue characteristics obtains measurement information associated with a parameter of a voxel of tissue of a patient measured at two or more time points, the two or more time points occurring before one or more characteristics of the voxel of the tissue are separable in an image generated based on the parameter of the voxel measured at a single time point of the two or more time points, and determines, based on the parameter of the voxel at the two or more time points, the one or more characteristics of the voxel of the tissue.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining measurement information associated with a parameter of a voxel of an image of tissue of a patient, wherein the measurement information is measured at two or more time points to provide first measurement information associated with the parameter of the voxel at a first time point of the two or more time points and second measurement information associated with the parameter of the voxel at a second time point of the two or more time points, wherein the two or more time points occur before one or more tissue characteristics are separable or discernible in another image generated based on the parameter of the voxel measured at a time point, and wherein the one or more tissue characteristics comprise:
a concentration of contrast agent in arteries;
a concentration of contrast agent in veins;
a concentration of contrast agent in cells;
a summed enhancement of a concentration of contrast agent in arteries, veins, and cells;
one or more pharmacokinetic parameters associated with contrast agent movement through tissue spaces; or
any combination thereof; and

determining one or more characteristics of the voxel of the image of tissue based on the first measurement information associated with the parameter of the voxel at the first time point, the second measurement information associated with the parameter of the voxel at the second time point, and a desired rate and/or plateau level of a concentration of a contrast agent delivered to the patient.

2. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are further determined based on at least one of the following: a height of the patient, a weight of the patient, an age of the patient, a gender of the patient, a heart rate of the patient, a cardiac output of the patient, a clinical symptom of the patient, a bilirubin level of the patient, or any combination thereof.

3. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point corresponding to at least one of the two or more time points.

4. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point subsequent to the two or more time points, and the method further comprising:
generating, based on the one or more tissue characteristics, one or more images including the one or more characteristics of the voxel of the image of tissue at the time point after the two or more time points.

5. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point subsequent to the two or more time points, and further comprising:
determining that the measurement information associated with the parameter of the voxel of the image of tissue of the patient includes a threshold amount of measurement information associated with determining the one or more characteristics of the voxel of the image of tissue; and
in response to determining that the measurement information includes the threshold amount of measurement information, controlling an imaging system to automatically stop acquisition of the measurement information.

6. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point subsequent to the two or more time points, and wherein determining the one or more characteristics of the voxel of the image of tissue includes:
feeding the measurement information associated with the parameter of the voxel of the image of tissue of the patient to a prediction model, the prediction model having been trained by means of supervised learning to predict, on the basis of the measurement information associated with the parameter at the two or more time points, the one or more characteristics of the voxel of the image of tissue.

7. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point subsequent to the two or more time points, and wherein determining the one or more characteristics of the voxel of the image of tissue includes:
fitting a pharmacokinetic/pharmacodynamic (PK/PD) model of the voxel of the image of tissue to the parameter of the voxel of the image of tissue measured at the two or more time points; and
determining, based on the PK/PD model fitted to the parameter of the voxel of the image of tissue measured at the two or more time points, the one or more characteristics of the voxel of the image of tissue.

8. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point subsequent to the two or more time points, and wherein determining the one or more characteristics of the voxel of the image of tissue includes:
fitting a PK/PD curve of a plurality of PK/PD curves precomputed for the parameter to the parameter of the voxel of the image of tissue measured at the two or more time points; and
determining, based on the PK/PD curve fitted to the parameter at the two or more time points, the one or more characteristics of the voxel of the image of tissue.

9. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point subsequent to the two or more time points, and wherein determining the one or more characteristics of the voxel of the image of tissue includes:
approximating a curve representing the one or more characteristics of the voxel of the image of tissue with a set of basis functions;
fitting the approximated curve to the parameter of the voxel of the image of tissue measured at the two or more time points; and
determining, based on the approximated curve fitted to the parameter of the voxel of the image of tissue measured at the two or more time points, the one or more characteristics of the voxel of the image of tissue.

10. The computer-implemented method of claim 1 , wherein the one or more characteristics of the voxel of the image of tissue are determined for a time point subsequent to the two or more time points, and wherein determining the one or more characteristics of the voxel of the image of tissue includes:
fitting a curve of a plurality of curves precomputed for the parameter with a set of basis functions to the parameter of the voxel of the image of tissue measured at the two or more time points; and
determining, based on the curve fitted to the parameter of the voxel of the image of tissue measured at the two or more time points, the one or more characteristics of the voxel of the image of tissue.

11. A system comprising:
one or more processors programmed and/or configured to:
obtain measurement information associated with a parameter of a voxel of an image of tissue of a patient, wherein the measurement information is measured at two or more time points to provide first measurement information associated with the parameter of the voxel at a first time point of the two or more time points and second measurement information associated with the parameter of the voxel at a second time point of the two or more time points, wherein the two or more time points occur before one or more tissue characteristics are separable or discernible in another image generated based on the parameter of the voxel measured at a time point, and wherein the one or more tissue characteristics comprise:
a concentration of contrast agent in ar

Assignees

• Bayer Ag

Inventors

• Rohrer Martin
• Knobloch Gesine
• Uber Iii Arthur

Classifications

• A61B5/055 Primary

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

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06T15/08 Primary

  Volume rendering · CPC title

• G06T7/0016

  involving temporal comparison · CPC title