Information processing apparatus, information processing method, and program

• US 11,334,990 B2
• Filed: 10/22/2019
• Issued: 05/17/2022
• Est. Priority Date: 10/29/2018
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Inventors: Yamada, Kenta
• Primary Examiner(s): Akinyemi, Ajibola A
• Application Number:
  US16/660,749
• Publication Number:
  US 20200134819A1
• Time in Patent Office: 938 Days
• Field of Search: 382128
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/084 Backpropagation, e.g. using gradient descent
• CPC Class Codes: G06T 2207/10072 Tomographic images
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/10088 Magnetic resonance imaging [MRI]
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/20084 Artificial neural networks [ANN]
• CPC Class Codes: G06T 2207/30008 Bone
• CPC Class Codes: G06T 2207/30061 Lung
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06T 7/11 Region-based segmentation

Abstract

Provided are an information processing apparatus, an information processing method, and a program capable of accurately extracting a target region from a medical image. An information processing apparatus includes an extraction unit that extracts information indicating a physique of a subject from an image acquired by imaging the subject, a specification unit that specifies a group into which the subject is classified by using the information indicating the physique of the subject extracted by the extraction unit, and a generation unit that generates a learned model for each group through machine learning using, as learning data, image data indicating a medical image acquired by imaging the subject for each group and information indicating a region extracted from the medical image.

Claims

1. An information processing apparatus comprising:

a processor, configured to;

extract information indicating a physique of a target subject from an image acquired by imaging the target subject;

specify a group into which the target subject is classified by using the extracted information indicating the physique of the target subject; and

generate a learned model for each of a plurality of groups using, as an input, image data indicating medical images acquired by imaging a plurality of subjects for each of the groups and using, as an output, information indicating a region extracted from each of the medical images through machine learning using, as learning data, the image data indicating the medical images and the information indicating the regions, wherein the learned model for each of the groups respectively corresponds to a different physique.

2. The information processing apparatus according to claim 1, wherein the processor is further configured to:

input image data indicating the medical images to one learned model acquired in advance through the machine learning using, as the learning data, the image data indicating the medical images and the information indicating the regions; and

acquire the information indicating the regions output from the one learned model,

wherein the processor generates the learned model for each of the groups by causing the one learned model to relearn for each of the groups by using, as the learning data, the medical image data and the information indicating the regions.

3. The information processing apparatus according to claim 1,

wherein the extracted information indicating the physique of the target subject is a skeleton of the target subject.

4. The information processing apparatus according to claim 1,

wherein the extracted information indicating the physique of the target subject is a body surface of the target subject.

5. The information processing apparatus according to claim 1,

wherein the image used for extracting the information indicating the physique of the target subject is a medical image of the target subject.

6. The information processing apparatus according to claim 1,

wherein the specified group is a group into which the target subject is classified according to an age, a gender, a race, or a species of the target subject.

7. The information processing apparatus according to claim 1, wherein the processor is further configured to:

extract a target region from the image by using the learned model corresponding to the specified group.

8. An information processing method comprising:

extracting information indicating a physique of a target subject from an image acquired by imaging the target subject;

specifying a group into which the target subject is classified by using the extracted information indicating the physique of the target subject; and

generating a learned model for each of a plurality of groups using, as an input, image data indicating medical images acquired by imaging a plurality of subjects for each of the groups and using, as an output, information indicating a region extracted from each of the medical images through machine learning using, as learning data, the image data indicating the medical images and the information indicating the regions, wherein the learned model for each of the groups respectively corresponds to a different physique.

9. A non-transitory computer readable medium storing a program causing a computer to execute a process comprising:

extracting information indicating a physique of a target subject from an image acquired by imaging the target subject;

specifying a group into which the target subject is classified by using the extracted information indicating the physique of the target subject; and

generating a learned model for each of a plurality of groups using, as an input, image data indicating medical images acquired by imaging a plurality of subjects for each of the groups and using, as an output, information indicating a region extracted from each of the medical images through machine learning using, as learning data, the image data indicating the medical images and the information indicating the regions, wherein the learned model for each of the groups respectively corresponds to a different physique.