Respiratory Motion Analysis for Accurate Patient Body Positioning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing medical image capturing systems, such as MRI, face challenges in accurately identifying the body position of a subject due to insufficient accuracy in image processing, particularly when relying on camera-based identification methods.

Innovation Solution

A medical image capturing support apparatus and method that utilize time-series captured images to detect body movement regions corresponding to respiratory movements, employing optical flow calculation and respiratory signal analysis to identify the body position with high accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If camera-based image processing is used to identify body position, then the system is simple and easy to operate, but the identification accuracy is insufficient

Engineering Contradiction:
Improvebody position identification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the body position identification process into multiple independent analysis components: respiratory movement detection, periodicity analysis, magnitude analysis, and orientation determination. Each component processes specific features separately and combines results to achieve high accuracy without requiring a single complex system

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary analysis layer that processes camera images through multiple stages: detecting respiratory movements, analyzing periodicity patterns, and comparing magnitude variations. This intermediary processing chain transforms simple camera data into accurate body position identification without direct complex hardware intervention

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If simple image processing is applied to captured images, then the processing speed is fast and the system is easy to operate, but sufficient accuracy in identification cannot be obtained

Engineering Contradiction:
Improvebody position identification accuracyVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-defining analysis frameworks for respiratory movement patterns, periodicity characteristics, and magnitude thresholds. These pre-established criteria enable rapid processing of captured images without requiring complex real-time computations, thus maintaining speed while improving accuracy

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent exploits the periodic nature of respiratory movements to streamline processing. By detecting and analyzing periodic patterns in body position changes, the system can identify body orientation efficiently without examining every pixel in every frame, significantly reducing processing time while maintaining high accuracy

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP4702916A1Medical image capturing support apparatus, operation method of medical image capturing support apparatus, program, and medical image capturing apparatus
Publication Date: 2026.03.04 FUJIFILM CORP
  • EP4702916A1 patent drawingFigure 1
  • EP4702916A1 patent drawingFigure 2~3
  • EP4702916A1 patent drawingFigure 4

AI summary

Provided are a medical image capturing support apparatus, an operation method of a medical image capturing support apparatus, a program, and a medical image capturing apparatus that realize identification of a body position of a subject (103) with high accuracy. A medical image capturing support apparatus acquires a plurality of time-series captured images generated by capturing a subject (103), detects, from the plurality of time-series captured images, a body movement region of the subject (103) in the captured image in which a movement of the subject (103) having periodicity and magnitude corresponding to a respiratory movement of the subject (103) occurs, and identifies a body position of the subject (103) based on the body movement region.