Lesion Volume of Interest Determination Using Transformation Matrix
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing systems face inaccuracies when determining a three-dimensional volume of interest (VOI) corresponding to a lesion in an image, as they often analyze incomplete lesions, leading to inaccurate information and segmentation.
Innovation Solution
A system and method that obtain a three-dimensional image from multiple two-dimensional images, determine a preliminary VOI, and perform transformation operations using a transformation matrix to ensure the VOI completely encloses the lesion, providing accurate information such as voxel values and volume.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a preliminary VOI is determined based on initial shape estimation, then the processing speed is improved, but the measurement precision of the lesion is worsened because the VOI may not completely enclose the lesion
Solution Approach 1:
The system uses feedback from the difference calculation between the transformed preliminary shape and the target shape to iteratively adjust the transformation matrix. By calculating the difference and using it to refine the transformation, the system ensures the VOI completely encloses the lesion while maintaining processing efficiency through automated iterative refinement rather than manual adjustment.
Solution Approach 2:
The system performs preliminary action by initially estimating the VOI and transformation matrix before final verification. This preliminary estimation allows fast initial processing, followed by a verification step that checks whether the transformed preliminary shape completely encloses the target shape, ensuring measurement precision without sacrificing overall processing speed.
2Measurement precision
If manual adjustment of VOI is performed to ensure complete lesion enclosure, then the measurement precision is improved, but the ease of operation is worsened due to increased complexity and time required
Solution Approach 1:
The system performs self-service by automatically calculating the transformation matrix and adjusting the VOI to completely enclose the lesion without requiring manual intervention. The automated process includes determining the preliminary VOI, calculating transformation matrices, transforming the shape, and verifying complete enclosure, all performed by the system itself to maintain both precision and operational simplicity.
Solution Approach 2:
The system replaces manual mechanical adjustment with automated computational methods. Instead of requiring operators to manually adjust the VOI boundaries, the system uses algorithms to calculate transformation matrices and automatically transform the preliminary shape, substituting mechanical/manual operations with automated image processing techniques that maintain precision while improving ease of operation.
3Manufacturing precision
If the VOI is transformed using a calculated transformation matrix, then the manufacturing precision of the VOI boundary is improved, but the use of energy is worsened due to additional computational requirements
Solution Approach 1:
The system applies partial action by performing the transformation only to the extent necessary to achieve complete lesion enclosure. Rather than over-transforming or performing exhaustive searches for the perfect transformation matrix, the system calculates the minimum necessary transformation to ensure the VOI completely encloses the target shape, reducing unnecessary computational energy consumption while maintaining boundary precision.
Data Source
AI summary
A system includes a storage device storing a set of instructions and a processor in communication with the storage device. When executing the set of instructions, the processor is configured to cause the system to obtain a 3D image including a plurality of 2D images, the 3D image relating to a lesion of an object and determine a preliminary VOI in the 3D image. The processor is also configured to cause the system to determine a preliminary shape based on an intersection of the preliminary VOI and a 2D target image of the plurality of 2D images and determine a transformation matrix corresponding to an operation to transform the preliminary shape to a target shape relating to the 3D ROI. The processor is further also configured to cause the system to determine a transformed VOI based on the preliminary VOI and the transformation matrix.