Automated DICOM Display Testing via Visual Marker Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual testing of software for displaying medical images in DICOM format is laborious, time-consuming, and prone to varying results, as it involves manually stepping through display capture footage to identify lag or skipped images.
Innovation Solution
A method and system for testing software that involves receiving a digital record with visual markers, providing instructions for displaying images in an expected sequence, running the software to detect the actual sequence, and comparing it to the expected sequence to quantify the software's effectiveness, using visual markers like progress bars or QR codes to identify image locations and durations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual testing is used to identify lag or skipped images, then testing can be performed with simple tools, but the testing process becomes laborious and time-consuming
Solution Approach 1:
The patent replaces manual mechanical inspection with an automated computer vision system that uses machine learning models to detect visual markers in video footage. The system automatically analyzes display capture footage to identify lag or skipped images without human intervention, thereby reducing testing duration while maintaining or improving accuracy.
Solution Approach 2:
The testing system performs self-validation by automatically comparing the detected sequence of visual markers against the expected sequence. The system independently identifies discrepancies such as lag or skipped frames without requiring manual verification, enabling autonomous testing that eliminates human labor while improving consistency and reducing time loss.
2Reliability
If manual testing is used to step through display capture footage, then testing setup remains simple, but the quality of results varies between testers
Solution Approach 1:
The patent replaces variable human judgment with a consistent automated computer vision system. The machine learning model processes all video footage using the same algorithms and criteria, eliminating inter-tester variability. While this increases system complexity, it dramatically improves testing consistency and reliability across different testing sessions and operators.
3Productivity
If automated detection of visual markers is implemented, then testing efficiency improves, but the complexity of the testing system increases
Solution Approach 1:
The patent implements automated computer vision with machine learning to detect visual markers in video footage. This substitution of manual processes with automated intelligent systems dramatically improves testing efficiency by processing footage rapidly and continuously. The increased system complexity is justified by the substantial gains in productivity and the ability to handle large volumes of testing data autonomously.
Solution Approach 2:
The patent introduces visual markers as intermediary elements that bridge the gap between the software output and the testing system. These markers serve as detectable signals that the automated system can reliably identify and track, enabling efficient automated testing without requiring complex direct analysis of the software interface. The markers act as a simplified intermediary that the machine learning model can easily detect and process.
4Measurement precision
If frame-by-frame manual analysis is performed, then detailed inspection is possible, but the testing process becomes extremely time-consuming
Solution Approach 1:
The patent replaces slow manual frame-by-frame analysis with high-speed automated computer vision processing. The machine learning model can analyze video footage at much higher speeds than human operators, maintaining detailed detection accuracy through algorithmic analysis of visual markers while increasing testing productivity by orders of magnitude.
Solution Approach 2:
The patent uses visual markers as copies or proxies for the actual image content being tested. Instead of manually analyzing every pixel of each medical image, the system detects these simplified marker copies that encode the essential information about image sequence and timing. This copying approach maintains measurement precision while dramatically improving testing speed.
Data Source
AI summary
Method for testing software configured to display a plurality of digital images includes receiving a digital record, the digital record comprising a plurality of digital images having an order, each of the digital images having a visual marker to indicate a respective location within the order; providing instructions to display the digital images, the instructions including an expected sequence; running the software to display the digital images in accordance with the expected sequence; detecting an actual sequence by detecting each visual marker of a respective digital image to identify when each digital image is displayed; and comparing the actual sequence and the expected sequence to quantify the effectiveness of the software at displaying the digital record.