Dynamic Reference Template Exchange for Cross-Modality Image Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing algorithms in pathology are slow and lack robustness in matching images from different imaging modalities or with different treatments, such as those with and without a cover slip, which complicates the identification of regions of interest in tissue samples.
Innovation Solution
An image processing apparatus that exchanges a reference template for a template computed from a matching frame once a match is detected, allowing for more efficient matching of subsequent frames with similar image characteristics, reducing computational complexity and improving robustness and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a reference template from a first imaging modality is used to match frames from a second imaging modality, then the matching can be performed, but the computational complexity is high and the matching speed is slow
Solution Approach 1:
The system performs a preliminary matching phase using the reference template from the first imaging modality to identify candidate matches in the second modality. Once a match is found, the system pre-computes a new reference template from the matched frame, which is then used for subsequent matching operations. This preliminary action reduces the computational burden for ongoing matching tasks.
Solution Approach 2:
The reference template is not static but dynamically updated during the matching process. The system transitions from using a template from the first imaging modality to using templates derived from the second imaging modality frames themselves. This dynamic adaptation allows the matching process to become progressively faster and more efficient.
2Adaptability or versatility
If image matching is performed between frames with different imaging modalities or treatments, then the matching can be achieved, but the robustness is poor
Solution Approach 1:
The system uses matched frames from the second imaging modality as intermediary templates. These intermediary templates serve as a bridge between the first and second imaging modalities, allowing subsequent matching operations to be performed within the second modality where the images are more similar and robustness is improved.
Solution Approach 2:
The system changes the reference template parameter dynamically. Instead of always using the original reference template from the first modality, it updates the template parameter to use frames from the second modality, which have similar characteristics to the frames being matched, thereby improving robustness.
3Ease of operation
If manual ROI dissection is performed, then the ROI can be identified, but the accuracy is low
Solution Approach 1:
The system replaces manual mechanical dissection with an automated image processing system. The automated system uses template matching algorithms to identify and locate ROIs in the second imaging modality frames, providing higher precision and accuracy compared to manual dissection while maintaining ease of operation through automated workflows.
Data Source
Figure 1
Figure 2
AI summary
An apparatus (MDS) and related method for image processing. The apparatus includes a multi-modal matcher (M). The matcher (M) operates to match a first reference (RF1) image against a stream (LF) of image frames (F1, F2). Once a match is found, the current reference image (RF1) is exchanged for a matching frame from the stream. The matcher (M) then attempts matching against subsequent frames in the stream by now using said matched frame as a new reference image. Once a further frame (Fm) is found that matches said new reference image, said further frame (Fm) is output as a best match.