Deformable Image Registration Using DICOM-Based Mask for CT to CBCT Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Deformable image registration between Computed Tomography (CT) and Cone Beam Computed Tomography (CBCT) images is challenging due to partial field of view and misinterpretation of image boundaries, leading to inaccurate registration results that impact treatment planning and monitoring.
Innovation Solution
A registration-enhancement system that generates an image mask based on Digital Imaging and Communications in Medicine (DICOM) information from CBCT images to distinguish between meaningful and meaningless data, improving the deformable image registration process by ignoring pixels outside the illuminated region and accurately mapping CT to CBCT images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automatic registration processing is performed using images with partial field of view or false boundaries, then processing speed is maintained, but registration accuracy deteriorates due to misleading cues
Solution Approach 1:
The system performs preliminary detection of image boundaries and illuminated regions before executing the registration algorithm. By pre-identifying valid data regions and marking invalid pixels, the system prepares the registration process in advance, ensuring that misleading cues from partial field of view or false boundaries do not compromise registration accuracy while maintaining processing efficiency
Solution Approach 2:
The patent introduces an intermediary component that generates a mask or validity map to distinguish between meaningful and meaningless pixels in the CBCT image. This intermediary structure mediates between the input images and the registration algorithm, filtering out misleading information from regions outside the illuminated area or with false boundaries, thereby improving registration accuracy without significantly increasing processing time
2Quantity of substance
If the entire image including boundary regions is used for registration, then more data is available for processing, but registration accuracy deteriorates due to misinterpretation of false boundaries
Solution Approach 1:
The system extracts and isolates the valid illuminated region from the entire CBCT image by detecting boundary characteristics and generating a mask. This extraction process separates meaningful data within the illuminated area from meaningless data at the boundaries or outside the field of view, allowing the registration algorithm to use only the extracted valid regions, thereby preventing misinterpretation of false boundaries while maintaining sufficient data volume for accurate registration
Data Source
AI summary
In accordance with at least some embodiments of the present disclosure, a process to improve computed tomography (CT) to cone beam computed tomography (CBCT) registration is disclosed. The process may include receiving a CT image generated by CT-scanning of an object, and receiving a CBCT image generated by CBCT-scanning of the object. The process may include generating an image mask based on Digital Imaging and Communications in Medicine (DICOM) information extracted from the CBCT image. For a specific pixel in the CBCT image, the image mask contains a corresponding data-field indicating whether the specific pixel contains image data generated based on the CBCT-scanning of the object. The process may further include generating a registered image by utilizing the image mask to perform a DIR between the CT image and the CBCT image.