Methods, systems, and apparatuses for medical image enhancement to optimize transducer array placement

Patent metadata

Field	Value
Publication number	US-12002153-B2
Application number	US-202217578241-A
Country	US
Kind code	B2
Filing date	Jan 18, 2022
Priority date	Jan 22, 2021
Publication date	Jun 4, 2024
Grant date	Jun 4, 2024

Abstract

A computer-implemented method to generate a three-dimensional model, wherein the computer comprises one or more processors and memory accessible by the one or more processors, and the memory stores instructions that when executed by the one or more processors cause the computer to perform the computer-implemented method, includes: receiving first image data of a first portion of the patient's body in a first image modality, receiving second image data of a second portion of the patient's body in a second image modality, modifying the second image data from the second image modality to the first image modality, and generating, based on the first image data in the first image modality and the modified second image data in the second image modality, a three-dimensional model of the first portion and the second portion of the patient's body.

First claim

What is claimed is:

1. A computer-implemented method to generate a three-dimensional model, the computer comprising one or more processors and memory accessible by the one or more processors, the memory storing instructions that when executed by the one or more processors cause the computer to perform the method, the method comprising:
generating an image modality translation model for converting image data in a second image modality to image data in a first image modality;
receiving first image data of a first portion of the patient's body in the first image modality;
receiving second image data of a second portion of the patient's body in the second image modality;
modifying the second image data from the second image modality to the first image modality by applying the image modality translation model to the second image data; and
generating, based on the first image data in the first image modality and the modified second image data in the first image modality, a three-dimensional model of the first portion and the second portion of the patient's body.

2. The method of claim 1 , wherein generating the image modality translation model comprises:
receiving a plurality of image data for the first portion of the patient's body in the first image modality for a plurality of subjects; and
receiving a second plurality of image data for the second portion of the patient's body in the second image modality for the plurality of subjects,
wherein the image modality translation model is generated based on an analysis of the first plurality of image data and the second plurality of image data.

3. The method of claim 2 , wherein the analysis comprises at least one of a Generative Adversarial Network (GAN) analysis, a MedGAN analysis, a super resolution GAN analysis, a pix2pix GAN analysis, a cycleGAN analysis, a discoGAN analysis, a fila-sGAN analysis, a projective adversarial network (PAN) analysis, a variational autoencoders (VAE) analysis, or a regression analysis.

4. The method of claim 1 , further comprising determining, based on the three dimensional model of the first portion and the second portion of the patient's body, a transducer array layout map along at least one of the first portion and the second portion of the patient's body.

5. The method of claim 1 , wherein the first image modality comprises magnetic resonance imaging (MRI).

6. The method of claim 1 , wherein the first portion of the patient's body is a first portion of a body part of the patient and the second portion of the patient's body is a second portion of the body part of the patient.

7. The method of claim 6 , wherein the body part is one of a head, a torso, an arm, or a leg.

8. A computer-implemented method to generate a three-dimensional model, the computer comprising one or more processors and memory accessible by the one or more processors, the memory storing instructions that when executed by the one or more processors cause the computer to perform the method, the method comprising:
receiving first image data of a first portion of a body part of a patient, wherein the first portion of the body part is less than a complete body part;
receiving a plurality of second image data of the body part for a plurality of subjects;
generating, based on the plurality of second image data, a body part completion model;
generating, based on the body part completion model and the first image data, third image data of a second portion of the body part; and
generating, based on the first image data and the third image data, a three-dimensional model of the body part of the patient.

9. The method of claim 8 , further comprising splitting each of the plurality of second image data into a first portion image data and a second portion image data, wherein the first portion image data comprises the first portion of the body part for a corresponding subject and the second portion image data comprises another portion of the body part for the corresponding subject.

10. The method of claim 9 , further comprising conducting an analysis of the first portion image data and the second portion image data for each of the plurality of subjects.

11. The method of claim 10 , wherein the analysis comprises at least one of a statistical shape analysis, an active appearance analysis, or a global image statistical analysis.

12. The method of claim 8 , further comprising determining, based on the first image data, that image data of the second portion of the body part of the patient's body is needed to generate the three-dimensional model of the body part of the patient.

13. The method of claim 8 , further comprising determining, based on the three-dimensional model of the body part of the patient, a transducer array layout map along the body part of the patient.

14. The method of claim 8 , wherein the three-dimensional model is a complete model of the body part of the patient.

15. The method of claim 8 , wherein the body part is a head and wherein the first image data of the first portion of the body part does not include a top portion of the head of the patient.

16. A computer-implemented method to generate a three-dimensional model, the computer comprising one or more processors and memory accessible by the one or more processors, the memory storing instructions that when executed by the one or more processors cause the computer to perform the method, the method comprising:
receiving first image data of a portion of a patient's body at a first image resolution;
receiving a plurality of second image data for a plurality of subjects;
generating, based on the plurality of second image data, a super resolution model for increasing a resolution of the first image data; and
generating, based on the super resolution model and the first image data, third image data of the portion of the patient's body at a second image resolution, wherein the second image resolution is greater than the first image resolution.

17. The method of claim 16 , wherein receiving the plurality of second image data for the plurality of subjects comprises:
receiving a first plurality of second image data of a same portion of a body as the portion of the patient's body for the plurality of subjects at the first image resolution; and
receiving a second plurality of second image data of the same portion of the body for the plurality of subjects at the second image resolution,
wherein generating the super resolution model comprises conducting an analysis of the first plurality of second image data and the second plurality of second image data.

18. The method of claim 17 , wherein the analysis comprises at least one of a regression analysis, a convolutional networks analysis, a Generative Adversarial Network (GAN) analysis, a MedGAN analysis, a super resolution GAN analysis, a pix2pix GAN analysis, a cycleGAN analysis, a discoGAN analysis, or a fila-sGAN analysis.

19. The method of claim 17 , wherein the first image resolution comprises magnetic resonance imaging.

Assignees

• Novocure Gmbh

Inventors

• Shamir Reuven Ruby
• Urman Noa
• Glozman Yana

Classifications

• G06T17/00 Primary

  Three-dimensional [3D] modelling for computer graphics · CPC title

• A61B5/055

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

• A61B34/10

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

• G06T3/4053

  based on super-resolution, i.e. the output image resolution being higher than the sensor resolution · CPC title

• A61B2034/105

  Modelling of the patient, e.g. for ligaments or bones · CPC title