Medical Image Processing Apparatus for Spectral Observation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In medical endoscopes and microscopes, the selection of images displayed to the user is often dependent on the operator's decision, leading to inefficiencies in endoscopic observations as the operator may not be aware of the most appropriate image, affecting the efficiency of the observation process.

Innovation Solution

An information processing apparatus and method that analyzes captured images from medical observation apparatuses, identifies the most appropriate image based on the observation situation, and recommends it to the user, enhancing the efficiency of medical observations by providing a suitable image for the current situation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If multiple spectral images are captured in different wavelength ranges, then the information about blood vessels at different depths is improved, but the operator cannot efficiently select the appropriate image for display

Engineering Contradiction:
Improveinformation about blood vesselsVSAvoidimage selection operation
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system automatically analyzes captured spectral images and provides feedback by determining and displaying the most appropriate wavelength range image without operator intervention. The image determination unit analyzes characteristics of spectral images and automatically selects the optimal image for display, eliminating the need for manual selection while preserving all captured spectral information.

Inventive Principle:
Principle #23Feedback

2Ease of operation

If the operator manually selects images for display, then the display shows what the operator chooses, but the efficiency of the observation process deteriorates due to lack of awareness of appropriate images

Engineering Contradiction:
Improveimage display controlVSAvoidobservation efficiency
Core Design Contradiction:
Ease of operationVSProductivity

Solution Approach 1:

The system performs self-service by automatically determining the most appropriate image for display through automated analysis of spectral image characteristics. The image determination unit independently evaluates captured images and selects the optimal display image without requiring operator knowledge or manual selection, thereby maintaining operational simplicity while significantly improving observation efficiency.

Inventive Principle:
Principle #25Self-service

3Device complexity

If spectral images are captured and displayed based on operator decision, then the system maintains simplicity, but the effectiveness of medical observation deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoidobservation effectiveness
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The system performs preliminary action by automatically analyzing and determining the most appropriate spectral image before display. The image determination unit pre-processes spectral images, evaluates their characteristics, and prepares the optimal image for display, ensuring observation effectiveness without adding visible complexity to the system operation.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3471591B1Information processing apparatus, information processing method, program, and medical observation system
Publication Date: 2024.05.29 SONY GROUP CORP
  • EP3471591B1 patent drawingFigure 1
  • EP3471591B1 patent drawingFigure 2A~2B
  • EP3471591B1 patent drawingFigure 2C

AI summary

Provided is an medical information processing apparatus including processing circuitry that, based on surgical situation information concerning surgical characteristics at a time of observing an interior of a living body, selects at least one of a plurality of biological images each having a different wavelength range or at least one of secondary images generated from the plurality of biological images each having a different wavelength range, as a recommended image.