Lesion Contour Error Detection in 3D Ultrasound
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Accurate extraction and correction of lesion contours in three-dimensional images formed by multiple two-dimensional frames are hindered by noise, poor resolution, and low contrast, making it difficult to detect and correct errors in the contours.
Innovation Solution
An apparatus and method that extract contours from two-dimensional image frames, generate estimation information based on preceding and subsequent frames, calculate energy values, and determine errors by comparing these values to predefined thresholds or distributions, with the ability to correct contours by modifying reference contours to produce candidate contours based on pixel information and similarities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If contour extraction is performed on two-dimensional image frames with noise and low contrast, then contour extraction can be performed, but extraction precision deteriorates
Solution Approach 1:
The patent combines multiple two-dimensional image frames into a three-dimensional image structure, allowing contour extraction to leverage information from multiple frames simultaneously. This merging approach enables the system to overcome the limitations of single-frame extraction by aggregating complementary information across frames, thereby improving extraction precision despite noise and low contrast conditions.
Solution Approach 2:
The patent implements an error detection and correction mechanism that uses feedback from energy value calculations and estimation information. The system continuously monitors the quality of extracted contours and adjusts the extraction process based on detected errors, allowing for iterative refinement and improved precision in contour extraction from noisy images.
2Measurement precision
If error detection is performed on extracted contours, then accuracy can be improved, but device complexity increases
Solution Approach 1:
The system performs self-diagnosis by automatically calculating energy values and generating estimation information to detect errors in extracted contours. The error detection mechanism serves itself by using the extracted contour information to verify its own accuracy, eliminating the need for external verification systems and reducing overall device complexity while maintaining high precision.
Solution Approach 2:
The patent transforms the error detection problem into a parameter optimization problem by defining energy values as quantitative measures of contour quality. By changing the detection approach from qualitative visual inspection to quantitative parameter measurement, the system simplifies the error detection mechanism while improving contour accuracy through objective criterion-based evaluation.
3Measurement precision
If correction of contour errors is performed, then contour precision improves, but processing time increases
Solution Approach 1:
The patent performs preliminary actions by pre-calculating energy values and generating estimation information from neighboring frames before the actual correction process. This preparation allows the correction algorithm to work with pre-processed data, reducing the computational burden during correction and thereby minimizing the time loss while achieving high precision contour correction.
Solution Approach 2:
The system applies partial correction by focusing error correction efforts only on regions where errors are detected, rather than processing the entire contour uniformly. This selective correction approach reduces processing time by avoiding unnecessary computations in error-free regions while maintaining high precision where needed, effectively balancing speed and accuracy.
Data Source
AI summary
An apparatus for detecting an error in a contour of a lesion includes an extracting unit configured to extract a contour of a lesion in each of a plurality of two-dimensional image frames that form a three-dimensional image, and an error determining unit configured to determine a presence or an absence of an error in a contour of a lesion in a target image frame of the two-dimensional image frames based on estimation information about the lesion in the target image frame and/or an energy value that corresponds to the contour of the lesion in the target image frame.