Radiographic Motion Correction via Depth Camera Surface Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Slot scanning techniques in radiography face challenges due to patient movement during scans, leading to image distortions and motion artifacts, which are difficult to correct using traditional methods.
Innovation Solution
The integration of depth cameras with radiographic systems to record patient surface movements simultaneously with radiographic scans, allowing for post-hoc correction of image distortions using surface measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If slot scanning techniques are used to produce high contrast orthogonal radiographs with low radiation exposure, then image quality and radiation safety are improved, but patient movement during the scan causes image distortion
Solution Approach 1:
A depth camera system is introduced as an intermediary device to capture patient surface movements during the radiographic scan. The depth camera records temporal-spatial data of patient position changes, which then serves as a mediator to guide the correction of image distortions in the radiographic images through post-processing registration algorithms.
Solution Approach 2:
The system implements feedback by using the depth camera to continuously monitor patient movement during scanning, and then applying this movement information to correct the radiographic images. The correction process uses the recorded surface movement data to adjust and realign the radiographic images, closing the loop between detection and correction.
2Adaptability or versatility
If stereo radiography is used to allow analysis of skeletal structure in load bearing posture with 3D analysis capability, then diagnostic capability is improved, but large dedicated infrastructure is required and patient motion between scans introduces errors
Solution Approach 1:
The depth camera system serves multiple functions: it captures patient surface geometry, tracks patient movement during scanning, and provides correction data for image registration. This multi-functional approach eliminates the need for separate motion capture systems or specialized infrastructure, allowing a single device to support both diagnostic imaging and motion correction.
Solution Approach 2:
Instead of requiring complex specialized infrastructure for stereo radiography, the system uses depth cameras to create a digital copy or representation of patient surface geometry and movement. This digital twin approach allows motion tracking and correction without needing physical specialized equipment, simplifying the overall system architecture.
3Adaptability or versatility
If asynchronous imaging is used in stereo radiography to enable imaging from multiple angles, then 3D reconstruction capability is improved, but patient motion between scans introduces distortion
Solution Approach 1:
The depth camera continuously records patient surface movement throughout the entire scanning process before the images are fully acquired and processed. This preliminary recording of motion data allows the system to have the correction information ready before final image reconstruction, enabling accurate alignment even though the imaging is asynchronous.
Solution Approach 2:
The system transitions from static image capture to dynamic motion tracking by using the depth camera to continuously monitor patient movement during the scanning process. This dynamic approach allows the system to adapt to patient motion in real-time and apply corresponding corrections to each image frame, maintaining measurement precision despite asynchronous acquisition from multiple angles.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A method comprising: receiving a radiographic image dataset representing a sequential radiographic scan of a region of a human subject; receiving three-dimensional (3D) image data representing an optical scan of a surface of said region, wherein said 3D image data is performed simultaneously with said sequential radiographic scan; estimating a time-dependent motion of said subject during said acquisition, relative to a specified position, based, at least in part, on said 3D image data; and using said estimating to determine corrections for said radiographic image dataset, based, at least in part, on a known transformation between corresponding coordinate systems of said radiographic image dataset and said 3D image data.