Topogram-based fat quantification for a computed tomography examination

Patent metadata

Field	Value
Publication number	US-11925501-B2
Application number	US-201916697363-A
Country	US
Kind code	B2
Filing date	Nov 27, 2019
Priority date	Dec 6, 2018
Publication date	Mar 12, 2024
Grant date	Mar 12, 2024

Abstract

In one embodiment, a method is for calculating an examination parameter for a computed tomography examination of an area of interest of a patient. The method includes receiving a topogram of the area of interest of the patient; determining fat distribution information by applying a trained machine learning algorithm onto the topogram; and calculating the examination parameter for the computed tomography examination of the area of interest of the patient based on the fat distribution information.

First claim

What is claimed is:

1. A method for calculating at least one examination parameter for a computed tomography examination of an area of interest of a patient, the method comprising:
receiving a topogram of the area of interest of the patient;
determining a fat distribution of the patient by applying a trained machine learning algorithm to the topogram, the fat distribution including a distribution of visceral fat of the patient and a distribution of subcutaneous fat of the patient, the distribution of visceral fat of the patient being a distribution of visceral fat of the patient along a patient length axis and the distribution of subcutaneous fat of the patient being a distribution of subcutaneous fat along the patient length axis; and
calculating the at least one examination parameter for the computed tomography examination of the area of interest of the patient based on the fat distribution, wherein the calculated at least one examination parameter includes an x-ray tube current that is dependent on a percentage of visceral fat and a percentage of subcutaneous fat within the area of interest; and
irradiating the area of interest of the patient with x-rays from an x-ray source based on the at least one examination parameter.

2. The method of claim 1 , wherein at least one of
the at least one examination parameter further includes an x-ray exposure parameter and
the x-ray exposure parameter is calculated by applying an automatic exposure control algorithm to the fat distribution.

3. The method of claim 2 , wherein the at least one examination parameter further includes a contrast medium administration parameter.

4. The method of claim 2 , further comprising:
receiving a plurality of training samples, each training sample of the plurality of training samples including a topogram sample and a corresponding fat distribution sample,
training a machine learning algorithm based on the plurality of training samples, wherein the machine learning algorithm is the trained machine learning algorithm upon being trained.

5. The method of claim 4 , wherein each training sample of the plurality of training samples further includes a computed tomography image sample corresponding to the topogram sample, the computed tomography image sample being different from the topogram sample.

6. The method of claim 1 , wherein the at least one examination parameter further includes a contrast medium administration parameter.

7. The method of claim 1 , further comprising:
receiving a plurality of training samples, each training sample of the plurality of training samples including a topogram sample and a corresponding fat distribution sample, and
training a machine learning algorithm based on the plurality of training samples, wherein the machine learning algorithm is the trained machine learning algorithm upon being trained.

8. The method of claim 7 , wherein each training sample of the plurality of training samples further includes a computed tomography image sample corresponding to the topogram sample, the computed tomography image sample being different from the topogram sample.

9. The method of claim 7 , wherein at least one of
each training sample of the plurality of training samples further includes a corresponding fat quantification sample, the corresponding fat quantification sample indicating an overall fat content of each training sample, and
wherein the trained machine learning algorithm is configured for determining a fat quantification, the fat quantification indicating an overall fat content of each training sample.

10. The method of claim 1 , further comprising:
acquiring projection data of the area of interest of the patient based on the x-rays;
generating a medical image based on the projection data; and
providing the medical image.

11. A computed tomography device for calculating at least one examination parameter for a computed tomography examination of an area of interest of a patient, the device comprising:
one or more processors; and
a memory storing computer-executable instructions that, when executed by the one or more processors, causes the computed tomography device to perform the method of claim 1 .

12. A non-transitory computer-readable medium storing executable instructions that, when executed by a processor, causes the processor to perform the method of claim 1 .

13. A computed tomography device for calculating at least one examination parameter for a computed tomography examination of an area of interest of a patient, the computed tomography device comprising:
one or more processors; and
a memory storing computer-executable instructions, when executed by the one or more processors, causes the computed tomography device to
receive a topogram of the area of interest of the patient;
determine a fat distribution of the patient by applying a trained machine learning algorithm to the topogram, the fat distribution including a distribution of visceral fat of the patient and a distribution of subcutaneous fat of the patient, the distribution of visceral fat of the patient being a distribution of visceral fat of the patient along a patient length axis and the distribution of subcutaneous fat of the patient being a distribution of subcutaneous fat along the patient length axis;
calculate the at least one examination parameter for the computed tomography examination based on the fat distribution, wherein the calculated at least one examination parameter includes an x-ray tube current that is dependent on a percentage of visceral fat and a percentage of subcutaneous fat within the area of interest; and
irradiate the area of interest of the patient with x-rays from an x-ray source of the computed tomography device based on the examination parameter.

14. The computed tomography device of claim 13 , wherein, the memory storing computer-executable instructions, when executed by the one or more processors, further causes the computed tomography device to
receive a plurality of training samples, each training sample of the plurality of training samples including a topogram sample and a corresponding fat distribution sample; and
train a machine learning algorithm based on the plurality of training samples, wherein the machine learning algorithm is the trained machine learning algorithm upon being trained.

15. The computed tomography device of claim 13 , wherein the at least one examination parameter further includes a contrast medium administration parameter.

Assignees

• Siemens Healthcare Gmbh
• Siemens Healthineers Ag

Inventors

• Grasruck Michael
• Flohr Thomas
• Schmidt Bernhard

Classifications

• A61B6/545 Primary

  involving automatic set-up of acquisition parameters · CPC title

• A61B5/0033

  Features or image-related aspects of imaging apparatus, e.g. for MRI, optical tomography or impedance tomography apparatus; Arrangements of imaging apparatus in a room · CPC title

• A61B5/4872

  Body fat · CPC title

• A61B6/032

  Transmission computed tomography [CT] · CPC title

• A61B6/5205

  involving processing of raw data to produce diagnostic data · CPC title