3D Ultrasound Inverted Rendering With Masked Noise Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Inverted rendering of 3D ultrasound data often obscures hypoechoic regions of interest due to noise and artifacts, reducing its utility in medical imaging.

Innovation Solution

Preprocess 3D ultrasound data by segmenting it into sets using a mask to distinguish between signal from regions of interest and noise, applying filtering techniques to enhance the difference between signal and noise values, and generate an inverted render from the subset of data points associated with the region of interest.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If inverted rendering is applied to 3D ultrasound data, then hypoechoic regions become more visible, but noise and artifacts dominate the image and obscure regions of interest

Engineering Contradiction:
Improvevisibility of hypoechoic regionsVSAvoidnoise and artifacts
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent segments the 3D ultrasound dataset into multiple subsets based on signal intensity characteristics. By dividing the data into different intensity ranges, the system can selectively process and render only those subsets containing hypoechoic regions of interest, while excluding noise-dominated regions from the inverted render, thus resolving the contradiction between visibility and noise interference

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different rendering qualities and processing strategies to different regions of the 3D dataset. Regions identified as containing hypoechoic features of interest receive enhanced processing and are rendered with higher quality, while noise-dominated regions are either excluded or rendered with lower priority, allowing local optimization of image quality without compromising overall performance

Inventive Principle:
Principle #3Local quality

2Measurement precision

If preprocessing and segmentation are applied to 3D ultrasound data, then quality of inverted render improves, but processing time and computational complexity increase

Engineering Contradiction:
Improvequality of inverted renderVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary segmentation and identification of hypoechoic regions of interest before generating the inverted render. By pre-processing the data to identify and tag regions containing features of interest, the system avoids the need for complex post-processing and iterative adjustments, thereby improving render quality while controlling processing time through efficient upfront classification

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent applies preprocessing and segmentation operations selectively to only those portions of the 3D dataset that are likely to contain hypoechoic regions of interest, rather than uniformly processing the entire dataset. This partial application of processing reduces overall computational burden and processing time while maintaining high quality in the regions that matter most

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3928294B1Methods and systems for segmentation and rendering of inverted ultrasound data
Publication Date: 2025.12.03 KONINKLIJKE PHILIPS NV
  • EP3928294B1 patent drawingFigure 1
  • EP3928294B1 patent drawingFigure 2
  • EP3928294B1 patent drawingFigure 3

AI summary

Systems and methods for preprocessing three dimensional (3D) data prior to generating inverted renders are disclosed herein. The preprocessing may include segmenting the 3D data to remove portions of the data associated with noise such that those portions do not appear in the generated render. The segmentation may include applying a mask to the 3D data. The mask may be generated by sorting data points in the 3D data set into a first set or a second set. In some examples, the 3D data may be filtered prior to generating the mask. In some examples, the mask may be adjusted based on feature recognition. The preprocessing may allow the visualization of hypoechoic regions of interest in a volume.