Non-spectral computed tomography (CT) scanner configured to generate spectral volumetric image data

Patent metadata

Field	Value
Publication number	US-11986336-B2
Application number	US-202217979061-A
Country	US
Kind code	B2
Filing date	Nov 2, 2022
Priority date	Jan 31, 2018
Publication date	May 21, 2024
Grant date	May 21, 2024

Abstract

A non-spectral computed tomography scanner includes a radiation source configured to emit x-ray radiation, a detector array configured to detect x-ray radiation and generate non-spectral data, and a memory configured to store a spectral image module that includes computer executable instructions including a neural network trained to produce spectral volumetric image data. The neural network is trained with training spectral volumetric image data and training non-spectral data. The non-spectral computed tomography scanner further includes a processor configured to process the non-spectral data with the trained neural network to produce spectral volumetric image data.

First claim

The invention claimed is:

1. A non-spectral computed tomography scanner, comprising:
a radiation source configured to emit x-ray radiation;
a detector array configured to detect the x-ray radiation and generate non-spectral data;
a memory configured to store a trained neural network; and
a processor configured to process the non-spectral data with the trained neural network to produce spectral volumetric image data.

2. The scanner of claim 1 , wherein the neural network is trained with training spectral volumetric image data and training non-spectral data.

3. The scanner of claim 2 , wherein the neural network is trained to minimize a difference between the spectral volumetric image data generated by the neural network and the training non-spectral data.

4. The scanner of claim 2 , wherein the training non-spectral data includes training non-spectral volumetric image data.

5. The scanner of claim 1 , wherein the neural network is trained with scanner geometry and physics information.

6. The scanner of claim 1 , wherein the non-spectral data includes non-spectral projection data, and the processor is configured to process the non-spectral projection data using the trained neural network to produce the spectral volumetric image data.

7. A non-transitory computer readable storage medium encoded with computer readable instructions, which, when executed by a processor of a computing system, cause the processor to perform a method for using a non-spectral computed tomography scanner, the method comprising:
emitting x-ray radiation by a radiation source;
generating non-spectral data in response to the x-ray radiation detected by a radiation detector;
storing a trained neural network in a memory; and
processing the non-spectral data with the trained neural network to produce spectral volumetric image data.

8. The non-transitory computer readable storage medium of claim 7 , wherein the neural network is trained with scanner geometry and physics information.

9. A method for using a non-spectral computed tomography scanner, comprising:
emitting x-ray radiation by a radiation source;
generating non-spectral data in response to the x-ray radiation detected by a radiation detector;
storing a trained neural network in a memory; and
processing the non-spectral data with the trained neural network to produce spectral volumetric image data.

10. The method of claim 9 , further comprising training the neural network with training spectral volumetric image data and training non-spectral data.

11. The method of claim 10 , further comprising training the neural network to minimize a difference between the spectral volumetric image data generated by the neural network and the training non-spectral data.

12. The method of claim 10 , wherein the training non-spectral data includes training non-spectral volumetric image data.

13. The method of claim 9 , further comprising training the neural network with scanner geometry and physics information.

14. The method of claim 9 , wherein the non-spectral data includes non-spectral projection data, and further comprising processing the non-spectral projection data using the trained neural network to produce the spectral volumetric image data.

Assignees

• Koninklijke Philips Nv

Inventors

• Bai Chuanyong
• Zhu Yang-Ming
• Lu Sheng
• Xu Shiyu
• Dang Hao
• Lai Hao
• Mcknight Douglas
• Wang Hui

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• A61B6/52 Primary

  Devices using data or image processing specially adapted for radiation diagnosis · CPC title

• A61B6/032 Primary

  Transmission computed tomography [CT] · CPC title

• G06N3/08

  Learning methods · CPC title