CT Image Depth Emphasis via Weight Map Adjustment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for reconstructing medical images, such as cephalometric and panoramic images from CT data, struggle to effectively emphasize depth resolution information without causing confusion or increasing processing time, limiting their utility in medical diagnosis.

Innovation Solution

A medical image processing device and method that divides CT images into sections, generates weight maps based on pixel values to emphasize depth information, and adjusts depth information in two-dimensional reconstruction images using user input, allowing for improved depth resolution and contrast.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If depth resolution information is increased in a two-dimensional image by conventional methods, then depth information becomes more prominent, but the image becomes more like a CT image causing sense of difference and confusion

Engineering Contradiction:
Improvedepth resolutionVSAvoidimage clarity
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent applies local quality by differentiating the processing of foreground and background regions. Depth enhancement is selectively applied to foreground objects while background regions maintain their original appearance characteristics. This is achieved through depth map generation and selective adjustment of image parameters based on depth information, allowing depth resolution to be improved in specific regions without affecting the overall image naturalness and causing confusion.

Inventive Principle:
Principle #3Local quality

2Measurement precision

If conventional methods are used to emphasize depth information by identifying depth information in CT data, then depth resolution is improved, but processing time increases

Engineering Contradiction:
Improvedepth resolutionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent employs preliminary action by pre-generating depth maps from the original image using automated depth estimation algorithms before the main image processing. These pre-computed depth maps are then reused for various depth enhancement operations, avoiding the need to re-process the entire CT data multiple times. This significantly reduces processing time while maintaining improved depth resolution in the final output images.

Inventive Principle:
Principle #10Preliminary action

3Ease of manufacture

If two-dimensional images are formed by overlapping slice images in a view direction, then cephalometric or panoramic images are created, but depth information representation is limited

Engineering Contradiction:
Improveimage formationVSAvoiddepth information representation
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent applies dimensionality change by integrating depth maps that provide an additional depth dimension to the traditional two-dimensional overlapping slice image method. While the base images are still formed by overlapping slices in a view direction for ease of manufacture, the depth maps add a third dimension of depth information that enhances depth representation without complicating the fundamental image formation process. This allows depth-resolved cephalometric and panoramic images to be created efficiently.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP3360481B1Medical image reconstruction device and method emphasising depth information
Publication Date: 2022.11.30 VATECH EWOO HLDG
  • EP3360481B1 patent drawingFigure 1~2
  • EP3360481B1 patent drawingFigure 3
  • EP3360481B1 patent drawingFigure 4

AI summary

A medical image processing device is disclosed. The disclosed medical image processing device may comprise: an input interface for receiving input in the form of a depth adjustment command from a user; an image processing and control unit for superimposing part or all of CT image data in a view direction so as to generate a two-dimensional reconstructed image, and for changing the contrast of at least part of the two-dimensional reconstructed image with respect to the depth adjustment command; and a display unit for displaying the two-dimensional reconstructed image.