Medical information processing apparatus

Patent metadata

Field	Value
Publication number	US-11244480-B2
Application number	US-201916451207-A
Country	US
Kind code	B2
Filing date	Jun 25, 2019
Priority date	Jun 29, 2018
Publication date	Feb 8, 2022
Grant date	Feb 8, 2022

Abstract

According to one embodiment, a medical information processing apparatus includes processing circuitry. The processing circuitry is configured to receive data acquired by scan for an object, and output a reconstructed image data based on the data and a trained model that accepts the data as input data and outputs the reconstructed image data corresponding to the data. The trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom.

First claim

The invention claimed is:

1. A medical information processing apparatus comprising:
a memory; and
processing circuitry configured to:
receive raw data acquired by scan for an object; and
output reconstructed image data based on the received raw data and a trained model that accepts the received raw data as input data and outputs reconstructed image data corresponding to the received raw data, wherein

the trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom,
the memory is configured to store a plurality of trained models in accordance with a scan condition including at least one of a count of gamma rays concerning the received raw data, a count rate of the gamma rays, and a nuclide name concerning generation of the gamma rays, and
the processing circuitry is configured to:
receive a selection of a trained model corresponding to the scan condition from the plurality of trained models stored in the memory, based on the scan condition in the scan; and
input the received raw data to the selected trained model, thereby generating the reconstructed image data.

2. The medical information processing apparatus according to claim 1 , wherein the received raw data is formed by a detection event of gamma rays.

3. A medical information processing apparatus comprising:
a memory; and
processing circuitry configured to:
receive raw data acquired by scan for an object; and
output reconstructed image data based on the received raw data and a trained model that accepts the received raw data as input data and outputs reconstructed image data corresponding to the received raw data, wherein

the trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom,
the memory is configured to store a plurality of trained models in accordance with a scan condition including at least one of a scan method concerning acquisition of the received raw data, a number of views used for reconstruction, a tube voltage, and a tube current, and
the processing circuitry is configured to:
receive a selection of a trained model corresponding to the scan condition from the plurality of trained models stored in the memory, based on the scan condition in the scan; and
input the received raw data to the selected trained model, thereby generating the reconstructed image data.

4. The medical information processing apparatus according to claim 3 , wherein
the trained model corresponds to a geometrical arrangement of a plurality of detectors concerning acquisition of the received raw data.

5. The medical information processing apparatus according to claim 3 , wherein the received raw data is formed by a detection event of gamma rays.

6. A medical information processing apparatus comprising:
a memory; and
processing circuitry configured to:
receive raw data acquired by scan for an object; and
output reconstructed image data based on the received raw data and a trained model that accepts the received raw data as input data and outputs reconstructed image data corresponding to the received raw data, wherein

the trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom,
the memory is configured to store a plurality of trained models in accordance with an application purpose of the reconstructed image data, and
the processing circuitry is configured to:
receive a selection of a trained model corresponding to the application purpose from the plurality of trained models stored in the memory, based on the application purpose; and
input the received raw data to the selected trained model, thereby generating the reconstructed image data.

7. A medical information processing apparatus comprising:
a memory; and
processing circuitry configured to:
receive raw data acquired by scan for an object; and
output reconstructed image data based on the received raw data and a trained model that accepts the received raw data as input data and outputs reconstructed image data corresponding to the received raw data, wherein

the trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom, and
the memory is configured to store a plurality of trained models in accordance with a scan condition including at least one of a count of gamma rays concerning the received raw data, a count rate of the gamma rays, and a nuclide name concerning generation of the gamma rays.

8. A medical information processing apparatus comprising:
a memory; and
processing circuitry configured to:
receive raw data acquired by scan for an object; and
output reconstructed image data based on the received raw data and a trained model that accepts the received raw data as input data and outputs reconstructed image data corresponding to the received raw data, wherein

the trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom, and
the memory is configured to store a plurality of trained models in accordance with a scan condition including at least one of a scan method concerning acquisition of the received raw data, a number of views used for reconstruction, a tube voltage, and a tube current.

9. A medical information processing apparatus comprising:
a memory; and
processing circuitry configured to:
receive raw data acquired by scan for an object; and
output reconstructed image data based on the received raw data and a trained model that accepts the received raw data as input data and outputs reconstructed image data corresponding to the received raw data, wherein

the trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom, and
the memory is configured to store a plurality of trained models in accordance with an application purpose of the reconstructed image data.

10. A medical information processing apparatus, comprising:
a memory; and
processing circuitry configured to:
receive data acquired by scan for an object, and
output reconstructed image data based on the data and a trained model that accepts the data as input data and outputs reconstructed image data corresponding to the data, wherein

the trained model is trained by learning using raw data generated based on a numerical phantom and the numerical phantom,
the memory is configured to store a plurality of trained models in accordance with an application purpose of the reconstructed image data, and
the processing circuitry is further configured to:
receive a selection of a trained model corresponding to the application purpose from the plurality of trained models stored in the memory, based on the application purpose, and
input the data to the selected trained model, thereby generating the reconstructed image data.

Assignees

• Canon Medical Systems Corp

Inventors

• Teshigawara Manabu
• Yoda Takahiro
• Okuda Ryo
• Tawara Hiroki

Classifications

• G06T12/10 Primary

  Image preprocessing, e.g. calibration, positioning of sources or scatter correction · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06T12/20

  Inverse problem, i.e. transformations from projection space into object space · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title