Tomographic Image Focal Plane Determination via Projection Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies for generating tomographic images from tomosynthesis imaging fail to accurately determine the focal plane corresponding to a structure of interest, such as tumors or calcifications, leading to difficulties in distinguishing structures on non-focal planes and inaccurate identification of the focal plane.
Innovation Solution
An image processing apparatus that acquires projection images from multiple angles, reconstructs tomographic images, detects structures of interest using machine learning models or pattern matching, and determines whether the detected tomographic image corresponds to the focal plane by analyzing the similarity between regions of projection images, specifically using correlation values to identify the tomographic image with the maximum similarity as the focal plane.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If tomographic images are generated from tomosynthesis imaging without focal plane determination, then the imaging process is simple and fast, but the ability to accurately identify and emphasize structures of interest is poor
Solution Approach 1:
The system performs preliminary actions by detecting structures of interest in advance and determining the focal plane before final image synthesis. The processor detects structures of interest from tomographic images, determines the focal plane based on projection image similarity, and then creates synthesized images with the focal plane emphasized, ensuring accurate identification before the main imaging task
Solution Approach 2:
The system introduces an intermediary step by using projection images as a mediator to determine the focal plane. Instead of directly analyzing complex three-dimensional tomographic images, the system uses the similarity of projection images (two-dimensional representations) as an intermediary criterion to identify the focal plane, simplifying the determination process while maintaining accuracy
2Reliability
If synthesized images are created without focal plane information, then the image generation is quick and simple, but the visibility and detection of structures of interest is reduced
Solution Approach 1:
The system applies local quality by creating synthesized images with different characteristics for different regions. The focal plane is identified through projection image similarity analysis, and then the synthesized image is created to emphasize structures at this specific focal plane, giving different weightings and visual characteristics to structures at different depths
Solution Approach 2:
The system uses feedback by analyzing the similarity of projection images to determine the focal plane, then using this determination to create synthesized images that emphasize the detected structures. The processor feedbacks the focal plane information back into the image synthesis process, ensuring that the final image highlights the correct structures of interest
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables more accurate determination of the focal plane, allowing for the creation of high-quality synthesized two-dimensional images and slab images that emphasize the structure of interest, thereby improving the visibility and detection of tumors, spicula, and calcifications.
Implementation Method 1
acquire projection images by imaging a subject with radiation at a plurality of angles
Data Source
AI summary
An image processing apparatus includes at least one processor that is configured to: acquire projection images obtained by imaging a subject with radiation at a plurality of angles; reconstruct a plurality of tomographic images from the acquired projection images; detect a structure of interest from the plurality of reconstructed tomographic images; derive a region of the projection image corresponding to the detected structure of interest; and determine, by using the derived region of the projection image, whether or not the tomographic image from which the structure of interest is detected is a tomographic image corresponding to a focal plane of the structure of interest.