Medical Image Processing Apparatus Voxel Reliability Map

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The accuracy of three-dimensional surface models generated from two-dimensional endoscopic images is compromised by low illumination intensity at distances from the observation window, particularly in body cavities with folds or protrusions, leading to obscured areas behind these features, which hinders effective diagnosis.

Innovation Solution

A medical image processing apparatus and method that includes a surface model generation section to create three-dimensional models from two-dimensional images and an area reliability calculation section to assess the reliability of data in each area, generating a voxel reliability map to improve detection and judgment of lesions like polyps by providing reliability information for each voxel in the model.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If a three-dimensional surface model is generated from a two-dimensional endoscopic image, then the ease of diagnosis is improved, but the reliability of data in areas behind folds or protrusions deteriorates due to low illumination intensity

Engineering Contradiction:
Improveease of diagnosisVSAvoidreliability of data
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent divides the three-dimensional surface model into multiple areas (first area with high reliability and second area with low reliability) based on illumination intensity and data quality. This segmentation allows the system to present different levels of confidence for different regions, enabling doctors to focus on reliable areas while being aware of potential inaccuracies in obscured areas behind folds or protrusions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by assigning different reliability characteristics to different areas of the three-dimensional surface model. Areas with sufficient illumination and clear data are marked as high reliability, while areas with low illumination or obscured views are marked as low reliability. This local differentiation allows the system to maintain overall diagnostic usefulness while highlighting specific regions that require caution.

Inventive Principle:
Principle #3Local quality

2Ease of operation

If the observation window is positioned to view the lumen shape, then the ease of observation is improved, but areas behind folds or protrusions become obscured due to light blockage

Engineering Contradiction:
Improveease of observationVSAvoidloss of information
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent creates a three-dimensional copy or reconstruction of the lumen shape from two-dimensional endoscopic images. This three-dimensional model serves as a virtual copy that can be viewed from multiple angles, allowing doctors to observe areas that would be obscured in the original two-dimensional view. The reliability map accompanying the model indicates which portions of the copy are based on reliable data and which are interpolated, thereby managing the loss of information while providing comprehensive visualization.

Inventive Principle:
Principle #26Copying

Data Source

PatentUS8184146B2Medical image processing apparatus and medical image processing method
Publication Date: 2012.05.22 OLYMPUS CORPORATION(JP)
  • US8184146B2 patent drawing
  • US8184146B2 patent drawing
  • US8184146B2 patent drawing

AI summary

An image processing apparatus includes: a surface model generation section for performing processing for generating a three-dimensional surface model from a two-dimensional medical image; and an area reliability calculation section for dividing the surface model into multiple areas and calculating the reliability of data in each of the multiple areas.