# US 2019/0378271 A1 · Medical information processing apparatus, magnetic resonance imaging apparatus, and medical information processing method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0378271 A1
- Document ID: US20190378271A1
- Status: Published application
- Kind: A1
- Application number: 16/436,132
- Filed: 2019-06-10
- Published: 2019-12-12
- Earliest claimed: 2018-06-11
- Assignees: Canon Medical Systems Corporation
- Applicants: Canon Medical Systems Corporation
- Inventors: Hidenori TAKESHIMA
- Web page: https://patentgrep.com/patent/US20190378271A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 3/09: Supervised learning
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 30/00: ICT specially adapted for the handling or processing of medical images (computed tomography A61B6/03)
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06N 20/00: Machine learning
- G06Q 10/10: Office automation; Time management
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

According to one embodiment, a medical information processing apparatus includes at least one processor. The processor is configured to execute a program to acquire first data collected from a test object, input the acquired first data into a first model, determine whether second data, which is output from the first model receiving the first data, is to be input into a second model, and in a case where the processor determines that the second data is to be input into the second model, input the second data into the second model, and output third data which is output from the second model receiving the second data.

## Claims

### Claim 1

A medical information processing apparatus comprising
at least one processor configured to execute a program to:
acquire first data collected from a test object;
input the acquired first data into a first model;
determine whether second data, which is output from the first model receiving the first data, is to be input into a second model; and
in a case where the processor determines that the second data is to be input into the second model, input the second data into the second model, and output third data which is output from the second model receiving the second data.

### Claim 2 (depends on 1)

The medical information processing apparatus according to claim 1, wherein in a case where the processor determines that the second data is not to be input into the second model, the processor outputs at least the second data without inputting the second data into the second model.

### Claim 3 (depends on 1)

The medical information processing apparatus according to claim 1, wherein in a case where an index value representing quality of the second data is equal to or more than a threshold value, the processor inputs the second data into the second model,
in a case where the index value is less than the threshold value, the processor does not input the second data into the second model.

### Claim 4 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the processor determines whether the second data is input into the second model based on an acceptable processing time for the first model.

### Claim 5 (depends on 4)

The medical information processing apparatus according to claim 4, wherein in a case where an index value representing quality of the second data is equal to or more than a threshold value, the processor inputs the second data into the second model,
in a case where the index value is less than the threshold value, the processor does not input the second data into the second model, and
the processor increases the threshold value as the processing time is shorter.

### Claim 6 (depends on 5)

The medical information processing apparatus according to claim 5, wherein the processor determines the processing time based on an external environment.

### Claim 7 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the processor determines whether the second data is to be input into the second model based on a processing load required for processing using the first model.

### Claim 8 (depends on 1)

The medical information processing apparatus according to claim 1, wherein in a case where the first data and the second data are not consistent, the processor inputs the second data into the second model,
in a case where the first data and the second data are consistent, the processor does not input the second data into the second model.

### Claim 9 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the first model generates the second data from the first data in first processing, and
the second model generates the third data from the second data in second processing, the second processing being of the same type as the first processing.

### Claim 10 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the first model is a model that is learned to output the second data when the first model receives the first data, and
the second model is a model that is learned to output the third data when the second model receives the second data.

### Claim 11 (depends on 10)

The medical information processing apparatus according to claim 10, wherein the first model and the second model are neural networks based on a composite function acquired by combining one or more linear functions and one or more non-linear functions.

### Claim 12 (depends on 10)

The medical information processing apparatus according to claim 10, wherein the first model and the second model are neural networks based on a composite function acquired by combining one or more non-linear functions.

### Claim 13 (depends on 1)

The medical information processing apparatus according to claim 1, wherein the first data is k-space data corresponding to a space in which the test object is present, and
the second data is a magnetic resonance image.

### Claim 14 (depends on 1)

The medical information processing apparatus according to claim 1, wherein in a case where the first data and the second data are not consistent, the processor updates the second data with fourth data based on the first data, and inputs the fourth data into the second model.

### Claim 15

A magnetic resonance imaging apparatus comprising:
at least one coil configured to apply radio frequency magnetic field to a test object; and
at least one processor configured to execute a program to:
acquire a magnetic resonance signal from the test object to which the radio frequency magnetic field is applied;
input, into a first model, k-space data based on the acquired magnetic resonance signal;
determine whether to input, into a second model, a first MR image reconstructed by the first model receiving the k-space data;
in a case where the processor determines to input the first MR image into the second model, input the first MR image into the second model; and
output at least second MR image from among the first MR image and the second MR image reconstructed by the second model receiving the first MR image.

### Claim 16

A medical information processing apparatus comprising:
a first processing circuit; and
a second processing circuit,
wherein the first processing circuit is configured to:
acquire first data collected from a test object;
generate second data from the acquired first data;
determine whether the generated second data is to be input into the second processing circuit; and
in a case where the processor determines that the second data is to be input into the second processing circuit, input the second data into the second processing circuit,
wherein the second processing circuit is configured to:
generate third data from the second data received from the first processing circuit; and
output the generated third data.

### Claim 17

A medical information processing method for causing a computer to execute operations comprising:
acquiring first data collected from a test object;
inputting the acquired first data into a first model;
determining whether second data, which is output from the first model receiving the first data, is to be input into a second model; and
in a case where the computer determines that the second data is to be input into the second model, inputting the second data into the second model, and outputting at least third data which is output from the second model receiving the second data.