IP Library › Granted Patent US 12,493,961
Granted Patent B2
US 12,493,961 · App. 18/025,746 · Granted Dec 9, 2025

Estimation device, estimation method, program, and generation method

Inventors: Kou Katayama (Hokkaido, JP); Kensaku Mori (Aichi, JP); Masahiro Oda (Aichi, JP); Dongping Pan (Aichi, JP)
Assignee: MEDICAL CORPORATION KATAYAMA ORTHOPEDIC RHEUMATOLOGY CLINIC
G06T7/0014G06T2207/10116G06T2207/20081G06T2207/30008
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,493,961
App. No.
18/025,746
Granted
Dec 9, 2025
Kind
B2
Abstract

A purpose of the present invention is to make it possible, when diagnosing bone marrow edema, to estimate whether bone marrow edema is present in a body part of a subject without using MRI testing using a high-cost MRI device. The present invention is an estimation device that includes a learner that is trained using X-ray images in which the body part is photographed, and learning data including information about whether the body part photographed in the X-ray image has bone marrow edema, the X-ray image in which the body part of the subject is photographed being inputted into the learner, and an estimation result being outputted that relates to the presence of bone marrow edema in the body part photographed in the inputted X-ray image.

Claims (14)

1 . An estimation device comprising:

a learner that has been trained using training data including X-ray images of body part and information about whether or not bone marrow edema is present in body part captured in each of the X-ray images, wherein

the estimation device inputs an X-ray image of body part of a subject into the learner, and causes the learner to output an estimation result related to a presence or absence of bone marrow edema in body part captured in the inputted X-ray image.

2 . The estimation device according to claim 1 , wherein the body part is a joint of hand.

3 . The estimation device according to claim 1 , wherein the bone marrow edema is bone marrow edema associated with rheumatoid arthritis.

4 . The estimation device according to claim 1 , further comprising a visualization unit that analyzes an internal state of the learner and outputs an image visualizing a region of suspected abnormality in the inputted X-ray image.

5 . A method for estimating a presence or absence of bone marrow edema in body part captured in an X-ray image, the method comprising:

an estimating step of inputting an X-ray image of body part of a subject into a learner that has been trained using training data including X-ray images of body part and information about whether or not bone marrow edema is present in body part captured in each of the X-ray images, and causing the learner to output an estimation result related to a presence or absence of bone marrow edema in body part captured in the inputted X-ray image.

6 . The method according to claim 5 , further comprising a visualizing step of analyzing an internal state of the learner and outputting an image visualizing a region of suspected abnormality in the inputted X-ray image.

7 . A non-transitory computer-readable storage medium storing a program causing a computer to function as:

a learner that has been trained using training data including X-ray images of body part and information about whether or not bone marrow edema is present in body part captured in each of the X-ray images, wherein

the trained learner accepts an X-ray image of body part of a subject as input, and outputs an estimation result related to a presence or absence of bone marrow edema in body part captured in the inputted X-ray image.

8 . A generation method for generating a trained learner that can estimate a presence or absence of bone marrow edema in body part captured in an X-ray image, the generation method comprising:

a training step of training the learner using training data including X-ray images of body part and information about whether or not bone marrow edema is present in body part captured in each of the X-ray images.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 10, 2023
From: KATAYAMA, KOU; MORI, KENSAKU; ODA, MASAHIRO; PAN, DONGPING
To: MEDICAL CORPORATION KATAYAMA ORTHOPEDIC RHEUMATOLOGY CLINIC
Reel/Frame 062946/0612 →
Priority Claims (1)
JP 2020-154719 · Sep 15, 2020 · national
Continuity (1)
Related Publication 20230419493A1 · Dec 28, 2023
References Cited (19)
US 8290564B2 · Lang · 2012 [cited by examiner]
US 11471096B2 · Griffith · 2022 [cited by examiner]
US 20040242987A1 · Liew · 2004 [cited by examiner]
US 20130195325A1 · Lang · 2013 [cited by examiner]
US 20160048961A1 · Mohr et al. · 2016 [cited by applicant]
US 20170360473A1 · Hanson et al. · 2017 [cited by applicant]
US 20180360858A1 · Tabuteau · 2018 [cited by examiner]
US 20190021677A1 · Grbic · 2019 [cited by examiner]
US 20200129114A1 · Griffith · 2020 [cited by examiner]
JP 201641245 · 2016 [cited by applicant]
Hirvasniemi J, Niinimäki J, Thevenot J, Saarakkala S. Bone Density and Texture from Minimally Post-Processed Knee Radiographs in Subjects with Knee Osteoarthritis. Ann Biomed Eng. May 2019;47(5):1181-1190. doi: 10.1007… [cited by examiner]
International Search Report issued Dec. 14, 2021 in International Application No. PCT/JP2021/033957. [cited by applicant]
Colebatch et al., “EULAR recommendations for the use of imaging of the joints in the clinical management of rheumatoid arthritis”, Ann Rheum Dis, 2013, vol. 72, pp. 804-814. [cited by applicant]
Fukae et al., “Convolutional neural network for classification of two-dimensional array images generated from clinical information may support diagnosis of rheumatoid arthritis”, Scientific Reports, 2020, vol. 10, pp. 1… [cited by applicant]
Office Action issued Aug. 17, 2021 in corresponding Japanese Patent Application No. 2020-154719, with English machine translation. [cited by applicant]
Katayama et al. “11.X-ray radiograph characteristic of extensive bone marrow edema in hand joint”, 2019, vol. 94(1), pp. 61, with English translation. [cited by applicant]
Extended European Search Report issued Sep. 12, 2024 in corresponding European Patent Application No. 21869399.2. [cited by applicant]
Kento Morita et al., “Computer-Aided Diagnosis System for Rheumatoid Arthritis Using Machine Learning”, 2017 International Conference on Machine Learning and Cybernetics (ICMLC), IEEE, vol. 2, Jul. 2017, pp. 357-360, XP… [cited by applicant]
Katayama et al. “11.X-ray radiograph characteristic of extensive bone marrow edema in hand joint”, 2019, vol. 91, No. 1, pp. 61, with English translation. [cited by applicant]