Medical Image Registration via Superpixel Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional medical image diagnostic apparatuses face difficulties in rapidly and accurately identifying corresponding blood vessels across different imaging modalities, such as CT and ultrasound scans, due to the complexity of comparing numerous vessels in images.
Innovation Solution
A medical image diagnostic apparatus that performs superpixel segmentation on images, generates transformation matrices for corresponding superpixels, and automatically registers them using feature extraction and labeling units, enabling precise matching of blood vessels across different imaging modalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual labeling of blood vessels is performed in conventional medical image diagnostic apparatuses, then the simplicity of the method is maintained, but the time consumption and labor intensity increase significantly
Solution Approach 1:
The system performs automatic blood vessel registration by having the computer automatically identify corresponding blood vessels across different imaging modalities using image processing algorithms, eliminating the need for manual labeling while reducing time consumption and labor intensity
Solution Approach 2:
The manual mechanical process of labeling blood vessels is replaced with an automated image processing system that uses computer algorithms to identify and register corresponding blood vessels, substituting human manual work with automated computational methods
2Measurement precision
If manual comparison of numerous blood vessels across different imaging modalities is performed, then the accuracy of identification can be maintained, but the productivity decreases due to the large number of vessels
Solution Approach 1:
The system segments the complex task of blood vessel identification into automated image processing steps, dividing the numerous blood vessels into individually analyzable units that the computer can process systematically, maintaining accuracy while improving productivity
Solution Approach 2:
The computer acts as an intermediary between the different imaging modalities, automatically comparing and registering blood vessels across CT and ultrasound images, enabling accurate identification of corresponding vessels without requiring manual comparison of numerous vessels
3Productivity
If automatic blood vessel registration is performed using the patent method, then the productivity and speed of diagnosis are improved, but the device complexity increases due to the need for image processing apparatus
Solution Approach 1:
The image processing apparatus performs multiple functions including image acquisition, image processing, blood vessel identification, and registration in a single integrated system, improving productivity while managing device complexity through multi-functionality
Solution Approach 2:
The complex manual process of blood vessel registration is replaced with automated image processing algorithms and computer-based systems, increasing diagnostic speed while the complexity is managed through software-based solutions rather than mechanical systems
Data Source
AI summary
A medical image diagnostic apparatus according to an embodiment includes processing circuitry configured to determine a plurality of small blocks for each of a plurality of pieces of medical image data, generate a plurality of superpixels corresponding to the plurality of small blocks, assign a label to at least one of the plurality of pieces of medical image data, and perform registration between the plurality of pieces of medical image data using the plurality of superpixels and the label.