Characterizing permeability, neovascularization, necrosis, collagen breakdown, or inflammation

Patent metadata

Field	Value
Publication number	US-12236595-B2
Application number	US-202318545550-A
Country	US
Kind code	B2
Filing date	Dec 19, 2023
Priority date	Aug 14, 2015
Publication date	Feb 25, 2025
Grant date	Feb 25, 2025

Abstract

Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

First claim

The invention claimed is:

1. A system for implementing a layered analytics framework, the system comprising:
a processor configured to:
receive imaging data of Computed Tomography (CT), Magnetic resonance (MR), Ultrasound (US), or Positron Emission Tomography (PET) of a patient, imaged at two or more points in time;
for each of the points in time, determine, based on the received imaging data at each respective point in time, a set of segmentations including lumen, wall, or a combination thereof, wherein the set of segmentation includes one or more cross sectional slices of a vessel;
determine, based on the set of segmentations, a change in a set of quantities that identify or characterize permeability, neovascularization, necrosis, collagen breakdown, or inflammation, across the points in time; and
output the identification or characterization of the permeability, neovascularization, necrosis, collagen breakdown, or inflammation for each of the points in time.

2. The system of claim 1 wherein the determination of the quantities is based on machine learning.

3. The system of claim 1 wherein the processor is further configured to determine hemodynamic properties based on the set of segmentations.

4. The system of claim 1 wherein the processor is further configured to determine one or more of blood pressure, blood flow velocity, flow reserve, or vessel wall shear stress based on the set of segmentations.

5. A method for implementing a layered analytics framework, the method comprising:
a processor configured to:
receiving imaging data of Computed Tomography (CT), Magnetic resonance (MR), Ultrasound (US), or Positron Emission Tomography (PET) of a patient, imaged at two or more points in time;
for each of the points in time, determining, based on the received imaging data at each respective point in time, a set of segmentations including lumen, wall, or a combination thereof, wherein the set of segmentation includes one or more cross sectional slices of a vessel;
determining, based on the set of segmentations, a change in a set of quantities that identify or characterize permeability, neovascularization, necrosis, collagen breakdown, or inflammation, across the points in time; and
outputting the identification or characterization of the permeability, neovascularization, necrosis, collagen breakdown, or inflammation for each of the points in time.

6. The method of claim 5 wherein determining the quantities further comprises applying one or more machine learning algorithms.

7. The method of claim 5 further comprising determining hemodynamic properties based on the set of segmentations.

8. The method of claim 5 further comprising determining one or more of blood pressure, blood flow velocity, flow reserve, or vessel wall shear stress based on the set of segmentations.

9. One or more non-transitory computer-readable storage media comprising instructions that are executable to cause one or more processors to:
receive imaging data of Computed Tomography (CT), Magnetic resonance (MR), Ultrasound (US), or Positron Emission Tomography (PET) of a patient, imaged at two or more points in time;
for each of the points in time, determine, based on the received imaging data at each respective point in time, a set of segmentations including lumen, wall, or a combination thereof, wherein the set of segmentation includes one or more cross sectional slices of a vessel;
determine, based on the set of segmentations, a change in a set of quantities that identify or characterize permeability, neovascularization, necrosis, collagen breakdown, or inflammation, across the points in time; and
output the identification or characterization of the permeability, neovascularization, necrosis, collagen breakdown, or inflammation for each of the points in timer inflammation.

10. The one or more non-transitory computer-readable storage media of claim 9 where the instructions when executed further cause one or more processors to determine the quantities based on machine learning.

11. The one or more non-transitory computer-readable storage media of claim 9 where the instructions when executed further cause one or more processors to determine hemodynamic properties based on the set of segmentations.

12. The one or more non-transitory computer-readable storage media of claim 9 where the instructions when executed further cause one or more processors to determine one or more of blood pressure, blood flow velocity, flow reserve, vessel wall shear stress based on the set of segmentations.

Assignees

• Elucid Bioimaging Inc

Inventors

• Buckler Andrew J
• Johnson Kjell
• Ma Xiaonan
• Moulton Keith A
• Paik David S

Classifications

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/096

  Transfer learning · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06T2207/30104

  Vascular flow; Blood flow; Perfusion · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title