Medical Information Processing Apparatus Model Selection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Medical image diagnosis using machine-trained models faces a trade-off between processing time and accuracy, where reducing processing time degrades accuracy, and in urgent medical situations, there is a need for both speed and high accuracy.

Innovation Solution

A medical information processing apparatus that selects a combination of trained models based on patient and environment information to prioritize either speed or accuracy, allowing for dynamic adjustment of processing parameters and user interface controls to optimize processing for specific needs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a machine-trained model processes higher-definition medical images, then diagnostic accuracy is improved, but processing time increases significantly

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system dynamically adjusts processing parameters such as image resolution and model complexity based on the diagnostic task requirements. For urgent cases, it processes images at lower resolution with simpler models to achieve fast results, while for non-urgent cases, it uses higher resolution and complex models for maximum accuracy.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes processing parameters including image downscaling factors, model architecture selections, and processing depth based on the urgency level and diagnostic needs. This allows the same system to adapt between speed-optimized and accuracy-optimized processing modes.

Inventive Principle:

Principle #35Parameter changes

2Speed

If processing time is reduced for urgent medical cases, then diagnostic speed is improved, but accuracy deteriorates

Engineering Contradiction:

Improvediagnostic speedVSAvoiddiagnostic accuracy

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The diagnostic process is segmented into multiple stages: an initial fast processing stage that provides preliminary results quickly, and an optional secondary detailed processing stage that can be applied if higher accuracy is needed. This segmentation allows the system to deliver urgent results rapidly while offering the possibility of enhanced accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

For urgent cases, the system performs partial processing - analyzing only the most critical features or a subset of the full image data - to achieve fast diagnostic results. When time permits, complete processing is performed for maximum accuracy.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20230326564A1Medical information processing apparatus, medical information processing method and non-transitory computer-readable medium

Publication Date: 2023.10.12 CANON KK

AI summary

According to one embodiment, a medical information processing apparatus includes processing circuitry. The processing circuitry acquires patient information relating to a target patient, environment information relating to an environment for execution, and target data relating to the target patient. processing circuitry determines, from a plurality of trained models differing from each other in processing speed and accuracy, a combination of trained models that satisfies a condition according to the patient information and the environment information.