Specimen Image Prioritization for Morphological Abnormality Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing drug discovery methods require significant human effort to analyze large numbers of specimen images for morphological abnormalities, as current automated systems are inefficient and impose a heavy processing load on users.
Innovation Solution
A drug discovery support device that prioritizes the analysis of specimen images based on degree-of-selection-priority information, using a processor to select target images, determine morphological abnormalities, and update selection priorities based on determination results, reducing the processing load.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If automated detection technology is used to detect morphological abnormalities in specimen images, then the burden on users is reduced, but the processing load remains considerable due to the large number of images (several thousand) that must be analyzed
Solution Approach 1:
The patent divides the large set of specimen images into multiple groups based on degree-of-selection-priority information. Instead of processing all images uniformly, the system segments them into high-priority and low-priority groups, allowing automated detection to focus first on the most likely candidates for morphological abnormalities. This segmentation resolves the contradiction by reducing user burden on high-priority images while maintaining processing efficiency through systematic handling of remaining images.
Solution Approach 2:
The patent applies different processing approaches to different subsets of images based on their selection priority. High-priority images receive more sophisticated automated analysis with lower user burden, while lower-priority images are handled with simpler processing. This local differentiation of processing quality resolves the contradiction by optimizing the balance between automation and efficiency for each image subset according to its characteristics.
2Reliability
If all specimen images are analyzed in detail, then comprehensive detection of morphological abnormalities is achieved, but the processing time and computational load increase significantly
Solution Approach 1:
The patent performs preliminary sorting of specimen images into groups based on degree-of-selection-priority information before detailed analysis. This preliminary action identifies and separates high-priority images that are most likely to contain morphological abnormalities. By pre-processing the image set in this way, the system ensures comprehensive detection of abnormalities in high-priority images while avoiding unnecessary detailed processing of low-priority images, thus resolving the contradiction between detection completeness and processing time.
Solution Approach 2:
The patent applies partial action by focusing detailed automated detection resources on a subset of high-priority images rather than uniformly processing all images. The degree-of-selection-priority information enables the system to concentrate computational efforts where they are most needed, achieving reliable detection of morphological abnormalities in the most critical images while reducing overall processing time by limiting intensive analysis to necessary portions of the dataset.
3Productivity
If the analysis focuses only on high-priority specimen images, then processing efficiency is improved, but the risk of missing abnormalities in lower-priority images increases
Solution Approach 1:
The patent establishes a continuous multi-stage processing workflow where high-priority images are analyzed first, followed by systematic handling of lower-priority images. The degree-of-selection-priority information guides this continuous process, ensuring that after high-priority images are processed, the system seamlessly transitions to analyzing lower-priority images. This continuity maintains detection accuracy across all image priorities while preserving processing efficiency through the structured sequential approach.
Solution Approach 2:
The patent incorporates feedback mechanisms where the results from analyzing high-priority images inform the subsequent processing of lower-priority images. The degree-of-selection-priority information is updated and refined based on detection results, allowing the system to adjust its analysis strategy. This feedback loop ensures that processing efficiency gains from focusing on high-priority images do not compromise overall detection accuracy, as the system continuously adapts based on accumulated information.
Data Source
AI summary
A drug discovery support device includes a processor. The processor is configured to obtain multiple specimen images of a tissue specimen of multiple organs of subjects subjected to an evaluation test of a candidate substance; select, in accordance with degree-of-selection-priority information in which a degree of selection priority is set for each of the multiple organs, a target specimen image of a tissue specimen of a single organ from among the multiple specimen images; make a determination as to whether a morphological abnormality has occurred in the tissue specimen in the target specimen image; and update the degree-of-selection-priority information, based on a determination result as to whether the morphological abnormality has occurred.