CBCT Motion Artifact Reduction Using Segmentation and In-Painting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Radiation therapy systems suffer from motion artifacts due to involuntary and voluntary movements of patient anatomy during cone-beam computed tomography (CBCT) image acquisition, leading to degraded reconstruction quality and inaccurate detection of target volumes.
Innovation Solution
Implement autosegmentation of high-contrast structures to generate 3D representations, followed by forward projection to create 2D mask projections, and an in-painting process to replace high-contrast moving structure pixels with low-contrast pixels, thereby generating corrected 2D projections that reduce motion artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional CBCT reconstruction is performed without motion correction, then the reconstruction process is simple and fast, but motion artifacts degrade the reconstruction quality and target volume detection accuracy
Solution Approach 1:
The patent applies preliminary action by performing autosegmentation of high-contrast structures and generating 3D representations before the reconstruction process. Mask projections are created in advance to identify and correct motion artifacts during reconstruction, thereby improving reconstruction quality without significantly increasing overall processing complexity
Solution Approach 2:
The patent introduces mask projections as an intermediary element that mediates between the raw projection data and the final reconstructed volume. These masks serve as a bridge to selectively correct regions affected by motion artifacts while preserving unaffected regions, thus improving reconstruction quality with controlled complexity increase
2Measurement precision
If high-contrast structures are preserved in the reconstructed volume, then anatomical features are clearly visible, but motion artifacts from these structures create inconsistencies and reduce image quality
Solution Approach 1:
The patent applies segmentation by dividing the reconstructed volume into different regions based on contrast levels. High-contrast structures are identified and segmented separately using autosegmentation, allowing selective processing where motion artifacts are corrected while preserving the anatomical definition provided by these structures
Solution Approach 2:
The patent applies local quality by applying different processing strategies to different regions of the image. Regions containing high-contrast moving structures receive motion artifact correction through mask-based inpainting, while other regions maintain their original high-contrast characteristics for clear anatomical visualization
Data Source
AI summary
A reconstructed volume of a region of patient anatomy is processed to reduce motion artifacts in the reconstructed volume. Autosegmentation of high-contrast structures present in an initial reconstructed volume is performed to generate a 3D representation of the high-contrast structures. 2D mask projections are generated by performing forward projection on the 3D representation, where each 2D mask projection includes location information indicating pixels that correspond to the high-contrast structures during the forward projection process. The acquired 2D projections are modified via in-painting to generate corrected 2D projections, where the acquired 2D projections are modified using information from the 2D mask projections. For example, pixels in the acquired 2D projections that are associated with high-contrast moving structures are replaced with low-contrast pixels. These corrected 2D projections are used to produce an improved reconstructed volume with fewer and/or less visually prominent motion artifacts.