Automated Contour Validation Using Statistical Tolerances
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating the accuracy of delineated anatomies in computerized patient imaging are time-consuming, rely heavily on user expertise, and lack flexibility and customizability, leading to potential errors in medical procedures.
Innovation Solution
An automated quality control system that uses stored statistical data to validate the accuracy of delineated contours, with the ability to update and refine these standards based on individual performance, allowing for variances in targeted populations and image modalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual evaluation is used to assess delineated anatomy accuracy, then reliability of evaluation is improved, but time consumption increases
Solution Approach 1:
The patent introduces statistical data as an intermediary between manual evaluations and automated validation. The system collects manual evaluation results, processes them into statistical data defining acceptable tolerances, and uses this statistical data as a mediator to enable automated validation that maintains reliability while reducing time consumption.
Solution Approach 2:
The system performs preliminary manual evaluations to build the statistical data database before automated validation can begin. This preliminary action creates the foundation of acceptable tolerance ranges that enable subsequent automated evaluations to be both fast and reliable.
2Extent of automation
If atlas-based systems are used for validation, then automation is improved, but adaptability worsens
Solution Approach 1:
The system transitions from static atlas-based validation to dynamic statistical data-driven validation. The acceptable tolerances are not fixed in an atlas but are dynamically determined from collected evaluation data, allowing the system to adapt to new anatomical structures and populations while maintaining automation.
Solution Approach 2:
The patent changes the fundamental parameter from fixed atlas references to variable statistical tolerance ranges. By using parameter-based validation with adjustable acceptable tolerances derived from statistical data, the system achieves both automation and adaptability to diverse anatomical structures.
3Ease of operation
If landmark-based similarity coefficients are used, then measurement simplicity is improved, but measurement precision worsens
Solution Approach 1:
The patent replaces the mechanical landmark-based measurement system with a statistical field-based validation system. Instead of measuring distances between discrete landmarks, the system uses statistical data to define acceptable tolerance ranges for anatomical structure delineation, achieving both simplicity and precision.
Data Source
AI summary
A system and method for validating the accuracy of delineated contours in computerized imaging using statistical data for generating assessment criterion that define acceptable tolerances for delineated contours, with the statistical data being conditionally updated and/or refined between individual processes for validating delineated contours to thereby adjust the tolerances defined by the assessment criterion in the stored statistical data, such that the stored statistical data is more closely representative of a target population. The present invention may be used to facilitate, as one example, on-line adaptive radiation therapy.