Camera-Based X-Ray Imaging for AI Patient Motion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing X-ray imaging devices struggle to detect patient motion accurately without fiducial elements, leading to potential abnormal images and increased radiation exposure due to retakes.
Innovation Solution
An X-ray imaging device equipped with a camera and AI technology to analyze object images, using a trained deep neural network model to detect motion by comparing key points between reference and subsequent frames, and outputting notification signals.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fiducial elements are attached to detect patient motion, then motion detection capability is improved, but patient comfort and procedure complexity worsen
Solution Approach 1:
The patent extracts the motion detection function from fiducial elements and implements it through AI-based analysis of standard imaging data and sensor data. The system removes the need for additional fiducial markers by utilizing existing camera images and sensor measurements to detect patient motion through machine learning algorithms that analyze anatomical landmark positions and sensor signal changes.
Solution Approach 2:
The patent introduces AI algorithms as an intermediary between raw sensor data/camera images and motion detection results. The machine learning model acts as a mediator that processes standard imaging data and sensor inputs to infer patient motion states, eliminating the need for direct fiducial element attachment while maintaining detection accuracy.
2Measurement precision
If fiducial elements are used for motion detection, then motion detection accuracy is improved, but patient radiation exposure worsens due to retakes
Solution Approach 1:
The patent performs preliminary motion detection using AI analysis of pre-imaging camera images and sensor data before the actual X-ray exposure. By detecting patient motion in advance through non-radiative means (camera and sensors), the system can alert operators to adjust patient positioning before radiation exposure occurs, preventing the need for retakes and reducing cumulative radiation exposure.
Solution Approach 2:
The patent converts potentially harmful radiation exposure into a benefit by using AI analysis of non-radiative data (camera images, sensor readings) to detect motion. The system transforms the limitation of not having fiducial elements into an opportunity to use alternative, non-radiative sensing methods that protect patients from unnecessary radiation while maintaining motion detection capability.
3Measurement precision
If AI technology is introduced for patient recognition, then recognition precision is improved, but device complexity worsens
Solution Approach 1:
The patent implements self-service through automated AI-based patient recognition and motion detection systems. The machine learning models automatically analyze camera images and sensor data to identify patients, detect motion, and generate alerts without requiring manual intervention or complex operator judgment, thereby improving precision while managing system complexity through automation.
Data Source
AI summary
An X-ray imaging device for detecting a motion of an object includes an X-ray irradiator configured to generate X-rays and to irradiate the X-rays to the object, an X-ray detector configured to detect the X-rays irradiated by the X-ray irradiator and transmitted through the object, a camera configured to obtain an object image by photographing the object positioned in front of the X-ray detector, a display, one or more processors including processing circuitry, and a memory storing instructions. The instructions, when executed by the one or more processors individually or collectively, cause the X-ray imaging device to detect the motion of the object from the object image by analyzing the object using an artificial intelligence (AI) model, and output, on the display, a notification signal notifying a user of a result of the detecting of the motion of the object.