Prostate Boundary Segmentation Algorithm for Ultrasound Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for segmenting the prostate boundary in medical imaging are time-consuming and prone to user variability, which can lead to inaccuracies in diagnosis and treatment of prostate cancer, especially in brachytherapy procedures.
Innovation Solution
A fully automated algorithm that initializes the prostate center, uses edge detection and length thresholding to remove false edges, employs prior knowledge to identify the boundary, scans along radial lines, and applies polynomial fitting to obtain a closed contour, minimizing user interaction and variability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual segmentation methods are used to identify prostate boundary, then user can adjust and verify the segmentation results, but the process is time-consuming and prone to user variability
Solution Approach 1:
The system performs automatic boundary detection and segmentation without requiring user intervention. The algorithm independently identifies edges, determines boundaries, and generates segmentation results, eliminating the need for manual adjustment and verification while maintaining high accuracy through multiple filtering and validation steps
Solution Approach 2:
The system performs preliminary edge detection and boundary identification before final segmentation is needed. By pre-processing the image to identify candidate boundaries and filter false edges in advance, the system prepares the segmentation result ready for use without requiring time-consuming manual intervention
2Measurement precision
If manual segmentation methods are used to identify prostate boundary, then user can verify the segmentation quality, but user variability leads to inaccuracies in diagnosis and treatment
Solution Approach 1:
The system performs self-validation through multiple internal checks including edge length thresholding, domain knowledge verification, and polynomial fitting consistency checks. This automated verification process eliminates user variability while maintaining high accuracy through objective, repeatable criteria
Solution Approach 2:
The system incorporates feedback loops where segmentation results are continuously validated against domain knowledge and image features. The algorithm adjusts its boundary detection based on feedback from edge analysis, length thresholding, and polynomial fitting, ensuring consistent and reliable results across different cases
3Productivity
If fully automated algorithm is used for prostate segmentation, then segmentation time is reduced and user variability is minimized, but the algorithm must handle false edges and complex boundary detection automatically
Solution Approach 1:
The algorithm divides the segmentation process into distinct stages: edge detection, length thresholding, domain knowledge verification, radial line scanning, and polynomial fitting. Each stage handles a specific aspect of boundary detection, making the complex overall process more manageable and effective while maintaining high speed through specialized processing at each step
Solution Approach 2:
The algorithm applies different processing strategies to different regions of the image. Edge detection parameters, thresholding values, and polynomial fitting approaches are adapted locally based on image characteristics and boundary features, allowing the system to handle diverse cases efficiently with high accuracy
4Extent of automation
If edge detection is used to identify prostate boundary, then the process is automated, but false edges are detected which reduce accuracy
Solution Approach 1:
The algorithm extracts and removes false edges through length thresholding that filters out edges below a minimum length criterion. By separating true boundary edges from false edges based on their length characteristics, the system maintains high automation while improving boundary detection accuracy
Solution Approach 2:
The algorithm changes parameters dynamically to distinguish true edges from false edges. By adjusting edge detection thresholds, length criteria, and polynomial fitting parameters based on image characteristics, the system maintains high automation level while achieving accurate boundary detection through adaptive parameter optimization
Data Source
AI summary
Segmenting the prostate boundary is essential in determining the dose plan needed for a successful bracytherapy procedure—an effective and commonly used treatment for prostate cancer. However, manual segmentation is time consuming and can introduce inter and intra-operator variability. This present invention describes an algorithm for segmenting the prostate from two dimensional ultrasound (2D US) images, which can be full-automatic, with some assumptions of image acquisition. Segmentation begins with the user assuming the center of the prostate to be at the center of the image for the fully-automatic version. The image is then filtered to identify prostate edge candidates. The next step removes most of the false edges and keeps as many true edges as possible. Then, domain knowledge is used to remove any prostate boundary candidates that are probably false edge pixels. The image is then scanned along radial lines and only the first-detected boundary candidates are kept the final step includes the removal of some remaining false edge pixels by fitting a polynomial to the image points and removing the point with the maximum distance from the fit. The resulting candidate edges form an initial model that is then deformed using the Discrete Dynamic Contour (DDC) model to obtain a closed contour of the prostate boundary.