Information Processing Apparatus for Medical Image Interpretation Support

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current technologies for image diagnosis in medical settings lack efficient support for interpreting related regions of interest after an initial interpretation, leading to potential oversight of associated lesions or structures.

Innovation Solution

An information processing apparatus and method that acquires a character string describing a first region of interest, specifies related but undescribed second regions of interest, and notifies users to review images likely to include these second regions, thereby facilitating comprehensive interpretation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a radiologist manually interprets all regions of interest in medical images, then interpretation accuracy is improved, but interpretation time and workload increase

Engineering Contradiction:

Improveinterpretation accuracyVSAvoidinterpretation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary identification of related regions of interest using correlation data before the radiologist completes interpretation. By pre-specifying regions that are likely related to already-interpreted areas, the system prepares a checklist of regions to review, reducing the cognitive load and time required for comprehensive interpretation while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If the radiologist checks all possible related regions, then completeness of interpretation is improved, but the complexity of the interpretation process increases

Engineering Contradiction:

Improvecompleteness of interpretationVSAvoidinterpretation process complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system provides feedback to the radiologist by notifying them of specified related regions that require review. This feedback mechanism guides the radiologist's attention to specific areas without requiring them to manually evaluate all possible regions, thereby ensuring completeness while simplifying the overall process through targeted notifications.

Inventive Principle:

Principle #23Feedback

3Productivity

If correlation data is used to specify related regions, then the efficiency of identifying relevant areas is improved, but the precision of region specification may be reduced

Engineering Contradiction:

Improveefficiency of identifying regionsVSAvoidprecision of region specification

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system applies partial action by notifying the radiologist of specific related regions based on correlation data rather than requiring complete manual review of all possible areas. The correlation data provides a probabilistic guide that covers the most likely related regions, achieving sufficient precision for clinical purposes while dramatically improving efficiency.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20250029725A1Information processing apparatus, information processing method, and information processing program

Publication Date: 2025.01.23 FUJIFILM CORP

AI summary

An information processing apparatus including a processor, wherein the processor is configured to: acquire a character string including a description regarding a first region of interest; specify a second region of interest that is not described in the character string and that is related to the first region of interest; and notify a user to check a necessity of displaying an image in which the second region of interest is likely to be included.