Contrast-Enhanced CT Image Visualization for Pulmonary Embolism Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current image rendering techniques, such as maximum intensity projection (MIP), minimum intensity projection (mIP), and vessel enhancing projection, are not effective in detecting pulmonary embolisms in contrast-enhanced CT images due to the subtle hypo-density of embolisms being occluded by surrounding vascular structures, leading to potential oversight during visual inspection.

Innovation Solution

A combination of a vessel filter and a hypo-density filter is applied to contrast-enhanced image data to generate composite image data, where vesselness and hypo-density values are weighted and combined, allowing for enhanced visualization of pulmonary embolisms through separate or combined renderings, facilitating efficient navigation to the embolism locations in 2D slices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Illumination intensity

If maximum intensity projection (MIP) is used to visualize vascular structures, then vascular structures are highlighted, but pulmonary embolisms are occluded by surrounding vessels and cannot be detected

Engineering Contradiction:
Improvevascular structure visibilityVSAvoidpulmonary embolism detection
Core Design Contradiction:
Illumination intensityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent segments the image processing into two distinct components: a vessel filter that extracts vascular structures and a hypo-density filter that identifies low-density regions. These segmented filters are then combined through multiplication to produce a composite image where pulmonary embolisms are highlighted without being occluded by surrounding vessels, resolving the contradiction between vascular visibility and embolism detection.

Inventive Principle:
Principle #1Segmentation

2Reliability

If visual inspection of all images is performed to detect pulmonary embolisms, then detection thoroughness is improved, but inspection time and workload increase significantly

Engineering Contradiction:
Improvedetection thoroughnessVSAvoidinspection time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary processing by generating a composite image that pre-highlights suspected pulmonary embolism locations using the combined vessel and hypo-density filters. This preliminary visualization allows radiologists to quickly identify areas of interest before performing detailed inspection, significantly reducing the time required to detect embolisms while maintaining detection thoroughness.

Inventive Principle:
Principle #10Preliminary action

3Device complexity

If conventional rendering techniques are used, then image processing is simple, but pulmonary embolisms are not effectively highlighted due to subtle hypo-density

Engineering Contradiction:
Improveprocessing simplicityVSAvoidembolism visibility
Core Design Contradiction:
Device complexityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent creates a composite image by combining the outputs of the vessel filter and hypo-density filter through multiplication. This composite approach integrates two different filtering perspectives into a single enhanced visualization that effectively highlights pulmonary embolisms, overcoming the limitations of simple conventional rendering techniques while maintaining reasonable processing complexity.

Inventive Principle:
Principle #40Composite materials

Data Source

PatentEP3146505B1Visualization of tissue of interest in contrast-enhanced image data
Publication Date: 2019.08.07 KONINKLIJKE PHILIPS NV
  • EP3146505B1 patent drawingFigure 1~2
  • EP3146505B1 patent drawingFigure 3
  • EP3146505B1 patent drawingFigure 4

AI summary

A method includes obtaining contrast-enhanced image data having a plurality of voxels, each voxel having an intensity value. The method further includes determining a vesselness value for each voxel. The method further includes determining a hypo-density value for each voxel. The method further includes weighting each of the intensity values by a corresponding vesselness value. The method further includes weighting each of the hypo- density values by the corresponding vesselness value. The method further includes combining the weighted intensity values and the weighted hypo-density values, thereby generating composite image data. The method further includes visually displaying the composite image data.