Medical Imaging Device Positioning with Optical Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional medical scan positioning approaches rely heavily on human intervention, leading to inefficiencies and inaccuracies in positioning medical devices for imaging and treatment.

Innovation Solution

Systems and methods that utilize optical imaging to identify body part boundaries and feature points, enabling automated and accurate positioning of medical devices by determining image regions and guiding device placement with minimal user intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If automated optical imaging and recognition models are used, then positioning accuracy and efficiency are improved, but device complexity increases

Engineering Contradiction:
Improvepositioning accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system divides the positioning task into multiple independent modules: optical image acquisition module, body part boundary recognition model, feature point recognition model, and image region determination module. Each module handles a specific aspect of the positioning process, improving overall accuracy while allowing independent optimization and maintenance of each component.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces optical images as an intermediary medium between the medical device and the patient's body. The recognition models process these optical images to identify body part boundaries and feature points, serving as a bridge that translates visual information into precise positioning data without requiring direct physical contact or complex mechanical positioning mechanisms.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of time

If automated positioning systems are implemented, then user workload and time are reduced, but measurement and detection difficulty increases

Engineering Contradiction:
Improvepositioning timeVSAvoidimage processing complexity
Core Design Contradiction:
Loss of timeVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary actions by pre-training recognition models with large datasets of optical images and anatomical structures. The body part boundary recognition model and feature point recognition model are prepared in advance to quickly process new images during actual positioning, reducing real-time computation requirements and enabling rapid positioning without manual intervention.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The automated positioning system performs self-service by automatically acquiring optical images, processing them through recognition models, identifying body part boundaries and feature points, and determining the target image region without requiring user intervention. The system independently completes the entire positioning workflow, eliminating manual measurement and detection steps.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4330935B1Systems and methods for medical imaging
Publication Date: 2025.08.06 SHANGHAI UNITED IMAGING HEALTHCARE
  • EP4330935B1 patent drawingFigure 1~2
  • EP4330935B1 patent drawingFigure 3
  • EP4330935B1 patent drawingFigure 4

AI summary

A method and a system for medical imaging may be provided. A first optical image of a target subject that includes a target region to be scanned or treated by a medical device may be obtained. At least one body part boundary and at least one feature point of the target subject may be identified using at least one target recognition model from the first optical image. An image region corresponding to the target region of the target subject may be identified from the first optical image based on the at least one body part boundary and the at least one feature point. At least one first edge of the image region may be determined based on the at least one body part boundary, and at least one second edge of the image region may be determined based on the at least one feature point.