4D-CT Artifact Detection via Segmentation Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating 4D-tomographic image data, particularly in 4DCT, are inefficient and prone to missing image artifacts, leading to costly and time-consuming re-scans due to undetected motion artifacts, which compromise treatment planning and patient comfort.
Innovation Solution
An automated algorithm for detecting and locating image artifacts in 4D-tomographic data using a segmentation algorithm and scoring function, capable of identifying artifacts in real-time during scanning, ensuring comprehensive assessment without manual oversight.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual review of 4DCT images is conducted by therapists or physicians, then expert evaluation can be performed, but the process is time-consuming and may miss artifacts due to selective review of only a fraction of image data
Solution Approach 1:
The system enables automated self-evaluation of 4DCT images through the artifact detection algorithm, eliminating the need for manual review by therapists or physicians. The algorithm independently analyzes the complete image dataset, detects artifacts, and provides recommendations, allowing the system to serve itself rather than relying on human experts to perform time-consuming selective reviews.
Solution Approach 2:
The artifact detection algorithm performs preliminary analysis of the complete 4DCT image dataset immediately after acquisition, before treatment planning begins. This preliminary action identifies artifacts early, preventing wasted time on subsequent treatment planning with compromised data and avoiding the need for repeat scans.
2Productivity
If selective review of a subset of crucial slices and time points is performed, then evaluation time is reduced, but artifacts may remain undetected and surface later during treatment planning
Solution Approach 1:
The artifact detection algorithm segments the 4DCT image dataset into multiple evaluation regions and time points, systematically analyzing each segment. This segmentation approach enables comprehensive review of the complete dataset rather than selective sampling, ensuring no artifacts are missed while maintaining computational efficiency through structured processing of divided image portions.
3Measurement precision
If artifacts are detected late during treatment planning phase, then the issue is identified, but repeat scan is necessary leading to increased costs, time, and patient discomfort
Solution Approach 1:
The system performs preliminary artifact detection immediately after 4DCT image acquisition, before treatment planning commences. This timing ensures that any artifacts are identified in advance, allowing clinicians to decide whether to proceed with treatment planning or perform a repeat scan, thereby avoiding wasted resources on planning with compromised data and preventing the need for costly and time-consuming repeat procedures.
Data Source
Figure 1
Figure 2~3
AI summary
Method for evaluating the exploitability of 4D-tomographic image data (4D), comprising the steps of: - Receiving (100) 4D-tomographic image data (4D), wherein said 4D-tomographic image data (4D) comprises a plurality of 3D-tomographic image data (3D) of an examination object, wherein the plurality of 3D-tomographic image data (3D) corresponds to a plurality of time points, - Applying (300) a segmentation algorithm to the plurality of 3D-tomographic image data (3D), wherein the segmentation algorithm is configured to segmentate at least one organ in the 3D-tomographic image data (3D) to which the algorithm is applied, - Applying (400) a scoring function to the segmented organs of the 3D-tomographic image data (3D), wherein the scoring function is configured to determine a scoring value for the segmented organ to which it is applied, wherein the scoring value comprises and/or corresponds to a metric quantifying an extent to which a vicinity of voxels at a surface of the segmented organ in the 3D-tomographic image data (3D) contains an image artifact, - Comparing (500) the scoring values with a threshold value, - Providing (600) a user notification, when at least one scoring value exceeds the threshold value.