Liver disease assessment in medical imaging

Patent metadata

Field	Value
Publication number	US-10610302-B2
Application number	US-201715641514-A
Country	US
Kind code	B2
Filing date	Jul 5, 2017
Priority date	Sep 20, 2016
Publication date	Apr 7, 2020
Grant date	Apr 7, 2020

Abstract

For liver modeling from medical scan data, multiple modalities of imaging are used. By using multiple modalities of imaging in combination with generative modeling, a more comprehensive and informed assessment may be performed. The generative modeling may allow feedback of effects of proposed therapy on function of the liver. This feedback is used to update the liver function information based on the imaging. Based on the computerized modeling with information from various imaging modes, an output based on more comprehensive information and patient personalized modeling and feedback may be provided to assist the physician.

First claim

We claim:

1. A method for liver modeling from medical scan data, the method comprising:
generating an anatomy model of structures of a liver of a patient from scan data of at least a first imaging system of corresponding first imaging modality;
generating a substrate model of stiffness of the liver of the patient from scan data of a second imaging modality different than the first imaging modality;
generating a perfusion model of fluid perfusion of the liver of the patient from scan data of a third imaging modality different than the first and second imaging modalities;
inferring a microvascular model of the liver of the patient from the anatomy model, substrate model, and perfusion model;
estimating a computational model of physiology of the liver from the substrate model, perfusion model, anatomy model, and the microvascular model;
modeling a change in the liver due to therapy with the computational model;
updating, in response to the modeling of the change, the anatomy model, the substrate model, the perfusion model, the microvascular model, or combinations thereof; and
outputting an image representing function of the liver based on the updated anatomy model, the substrate model, the perfusion model, the microvascular model, or combinations thereof.

2. The method of claim 1 wherein generating the anatomy model comprises generating the anatomy model from magnetic resonance as the first imaging modality and computed tomography as a fourth imaging modality, different ones of the structures being from different ones of the first and fourth imaging modalities.

3. The method of claim 1 wherein generating the anatomy model comprises generating the anatomy model of soft tissue, vasculature, biliary system, and lesions as the structures.

4. The method of claim 1 wherein generating the substrate model comprise generating the substrate model from elasticity imaging as the second imaging modality.

5. The method of claim 1 wherein generating the substrate model comprises generating the substrate model from direct measurement of the stiffness or inverse modeling.

6. The method of claim 1 wherein generating the perfusion model comprises measuring perfusion with perfusion imaging as the third imaging modality.

7. The method of claim 1 wherein inferring the microvascular model comprises inferring from inverse angiogenesis modeling.

8. The method of claim 1 wherein estimating the computational model comprises estimating biomechanics, vessel hemodynamics, and metabolism.

9. The method of claim 8 wherein estimating the computational model comprises estimating bio-heat diffusion and cellular viability.

10. The method of claim 1 further comprising recommending a next step in a clinical workflow based on the computational model, the anatomy model, the substrate model, the perfusion model, the microvascular model, or combinations thereof.

11. The method of claim 1 wherein modeling the change comprises modeling therapy applied to the liver with the computational model, and wherein updating comprises updating to reflect results of the therapy.

12. The method of claim 1 wherein updating comprises updating with feedback from the computational model.

13. The method of claim 1 wherein outputting comprises outputting the image with an indication of liver failure.

Assignees

• Siemens Healthcare Gmbh

Inventors

• Comaniciu Dorin
• Pheiffer Thomas
• Liu David
• Kapoor Ankur
• Mansi Tommaso

Classifications

• G16H50/50

  for simulation or modelling of medical disorders · CPC title

• A61B34/10 Primary

  Computer-aided planning, simulation or modelling of surgical operations · CPC title

• A61B18/02

  by cooling, e.g. cryogenic techniques · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• A61B2018/00529

  Liver · CPC title