Pathological Slide Biomarker Analysis With User Feedback Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning models for detecting or segmenting biological elements from pathological slide images often perform poorly, leading to inaccurate biomarker analysis and hindering the establishment of effective treatment plans.
Innovation Solution
A computing device and method that includes generating first biomarker expression information through analysis, allowing for user input to update analysis results, and outputting a report based on biomarker expression information to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If machine learning models are used for detecting or segmenting biological elements from pathological slide images, then automation is improved, but measurement precision deteriorates
Solution Approach 1:
The system implements a feedback mechanism where users can review analysis results and provide correction inputs. The machine learning model re-performs analysis incorporating user feedback, iteratively improving measurement precision while maintaining automation. This resolves the contradiction by allowing the system to learn from user corrections and enhance accuracy over time.
Solution Approach 2:
The system introduces an intermediary layer between automated analysis and final results, where user inputs act as a mediator to refine biomarker expression information. This intermediary process allows automated efficiency to be combined with human expertise, improving precision without completely sacrificing automation.
2Device complexity
If machine learning models with low performance are used, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The system changes the parameter of model performance by allowing users to select different machine learning models with varying complexity levels. Users can choose simpler models for routine analyses and more complex models when higher precision is required, flexibility in parameter selection resolves the contradiction between complexity and precision.
Solution Approach 2:
The system dynamically adjusts the analysis process based on user inputs and feedback. Rather than using a fixed complex model, the system adapts its complexity level and refinement process according to the specific case and user needs, optimizing the balance between device complexity and measurement precision.
3Measurement precision
If user input is required to update analysis results, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The system implements partial user involvement where users only need to review and provide inputs for specific regions or uncertain cases rather than the entire image. This partial action approach maintains measurement precision for critical areas while preserving overall productivity by avoiding complete manual review of all analysis results.
Solution Approach 2:
The system maintains continuous automated analysis while incorporating user feedback iteratively. Rather than stopping for complete manual review, the automated process continues and is refined based on user inputs, ensuring both precision improvement and productivity maintenance through uninterrupted analysis flow.
Data Source
AI summary
A computing device includes at least one memory, and at least one processor configured to generate, based on first analysis on a pathological slide image, first biomarker expression information, generate, based on a user input for updating at least some of results of the first analysis, second biomarker expression information about the pathological slide image, and control a display device to output a report including medical information about at least some regions included in the pathological slide image, based on at least one of the first biomarker expression information or the second biomarker expression information.