Fluorescence Image ROI Extraction for Surgical Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current fluorescence navigation surgery systems are inadequate in capturing, displaying, and storing fluorescence images of the entire surgical field, making it difficult to confirm the absence of unremoved cancer cells, as they primarily focus on the area of interest and do not effectively capture or store images of the entire surgical field.

Innovation Solution

An image processing apparatus and system that captures fluorescence images of the entire surgical field with high definition, allows users to select and cut out regions of interest, and displays these regions with a lower definition for surgical operations, while storing the high-definition images for verification purposes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If fluorescence images of the entire surgical field are captured with high definition, then measurement precision and reliability are improved, but device complexity and data storage requirements increase

Engineering Contradiction:
Improveimage definitionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the surgical field into multiple regions of interest (ROIs) and captures images of each region separately. This allows high-definition capture of specific areas without the need to capture and process the entire surgical field at maximum resolution, thereby reducing device complexity and data storage requirements while maintaining measurement precision for critical areas.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different image capture qualities to different regions of the surgical field. High-definition capture is applied only to regions containing cancer cells or areas requiring detailed verification, while standard definition is used for other areas. This local quality approach maintains measurement precision where needed while reducing overall system complexity.

Inventive Principle:
Principle #3Local quality

2Reliability

If the entire surgical field is captured with high pixel resolution, then reliability for verifying cancer cell removal is improved, but loss of time for image processing and storage increases

Engineering Contradiction:
Improveverification reliabilityVSAvoidimage processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts only the essential regions containing cancer cells or requiring verification from the entire surgical field. By taking out and capturing only these critical ROIs at high resolution, the system achieves reliable verification without the time-consuming process of capturing, processing, and storing high-resolution images of the entire surgical field.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent applies partial action by capturing high-definition images only of specific regions rather than the entire surgical field. This selective approach provides sufficient verification reliability for cancer cell removal while significantly reducing image processing and storage time compared to capturing the whole field at maximum resolution.

Inventive Principle:
Principle #16Partial or excessive action

3Ease of operation

If fluorescence observation image and visible light observation image are superimposed with same field of view, then ease of operation is improved, but device complexity increases due to shared zoom lens configuration

Engineering Contradiction:
Improveimage superimposition easeVSAvoidlens sharing configuration
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent creates a copied or mapped representation of the visible light image coordinates in the fluorescence image space. By establishing coordinate correspondence between the two images through software processing rather than hardware sharing, the system achieves easy image superimposition without the mechanical complexity of shared zoom lens configurations.

Inventive Principle:
Principle #26Copying

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables the capture, display, and storage of fluorescence images effectively, allowing for thorough verification of cancer cell removal and providing evidence for medical malpractice prevention by capturing the entire surgical field with high pixel resolution and displaying relevant areas with clear detail.

Implementation Method 1

an image of fluorescence emitted from an observation target area of a living body, the image of fluorescence being obtained by applying excitation light to the observation target area to which a fluorescent reagent is added in advance

Methodology Applied
Scientific EffectFluorescence: Fluorescence

Data Source

PatentUS11452453B2Image processing apparatus, image processing method, information processing program, fluorescence observation system, and fluorescence navigation surgery system
Publication Date: 2022.09.27 SONY GROUP CORP
  • US11452453B2 patent drawing
  • US11452453B2 patent drawing
  • US11452453B2 patent drawing

AI summary

An information processing apparatus includes a storage unit, a cutting-out unit, and a display controller. The storage unit is configured to store an image of fluorescence emitted from an observation target area of a living body in a recording medium as a fluorescence image of the observation target area, the image of fluorescence being captured with a first definition, the image of fluorescence being obtained by applying excitation light to the observation target area to which a fluorescent reagent is added in advance.The cutting-out unit is configured to cause a user to select at least a partial area of the fluorescence image and to cut out the selected area as a fluorescence image of a ROI area. The display controller is configured to cause a display unit to display the fluorescence image of a ROI area with a second definition that is lower than the first definition.