Endoscope Image Diagnosis Model Comparison System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing learning models used for medical image diagnosis do not account for changes in their outputs after relearning, making it difficult to assess the influence of these changes on diagnosis support information.
Innovation Solution
A program and information processing method that acquires and inputs endoscope images into multiple learning models, outputs diagnosis support information from each model, and associates this information with the models themselves, allowing for the comparison of outputs before and after relearning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a learning model is relearned to improve diagnosis accuracy, then the diagnosis support information becomes more accurate, but the influence of changes in the learning model on diagnosis support information cannot be assessed
Solution Approach 1:
The system performs preliminary actions by storing multiple versions of learning models (before and after relearning) and their corresponding diagnosis support information in advance. This allows for subsequent comparison and assessment of the influence of model changes without losing historical data.
Solution Approach 2:
The system creates copies of learning models at different stages (original and relearned versions) and stores them along with their output information. This copying approach enables preservation of historical models for comparison while allowing the system to assess the influence of changes.
2Loss of information
If multiple learning models are used to compare outputs, then the influence of model changes can be assessed, but the system complexity increases
Solution Approach 1:
The system merges multiple learning models and their corresponding diagnosis support information into a single integrated system. By combining model storage, information storage, and comparison functionality into one unified system, the complexity is managed rather than multiplied.
Solution Approach 2:
The system is designed with multi-functionality to handle multiple learning models, store various types of information (model data, diagnosis support information, influence assessment data), and perform multiple operations (comparison, assessment, display) within a single framework, reducing overall system complexity.
Data Source
AI summary
A program causes a computer to execute processing including: acquiring an endoscope image captured by an endoscope; inputting the acquired endoscope image into a plurality of learning models learned so as to output diagnosis support information regarding a lesion included in the endoscope image; acquiring a plurality of pieces of diagnosis support information output from each of the learning models; and outputting a plurality of pieces of the acquired diagnosis support information and information regarding each of the learning models in association with each other. Alternatively, the program causes the computer to execute the processing of inputting the acquired endoscope image into one learning model, executing a plurality of determination logics to acquire a plurality of pieces of output diagnosis support information, and outputting a plurality of pieces of the acquired diagnosis support information and information regarding each of the learning models in association with each other is executed.