High-Dimensional Breast Image Grids for Clearer 2D Rendering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing breast imaging technologies face challenges in effectively processing and displaying high-dimensional breast tissue data, particularly in reducing 3D structures to a clear 2D format that maintains clinically relevant information while minimizing visual clutter.

Innovation Solution

A method involving the creation of a high-dimensional object grid from breast tissue data, followed by data reduction techniques to generate a low-dimensional synthesized image that emphasizes significant features and de-emphasizes less important ones, using a 3D object grid to enhance the rendering of clinically relevant information in a 2D format.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If high-dimensional (3D) breast tissue data is processed to maintain all clinically relevant information, then diagnostic accuracy is improved, but visual clutter and complexity increase

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidvisual clutter
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the breast tissue volume into discrete 3D objects (lesions, masses, calcifications) and represents them in an object grid, separating clinically relevant structures from background tissue to reduce visual clutter while maintaining diagnostic accuracy

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts only the most clinically relevant 3D objects from the full breast tissue volume and represents them in a simplified object grid, removing unnecessary background information while preserving diagnostically important features

Inventive Principle:
Principle #2Taking out (Extraction)

2Ease of operation

If 3D breast tissue structures are reduced to 2D format for display, then ease of viewing is improved, but loss of depth information occurs

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

Solution Approach 1:

The patent creates an intermediate 3D object grid representation that maintains spatial depth information, then selectively projects this structured 3D data onto 2D display planes, preserving depth relationships through the grid structure while enabling easy 2D viewing

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

Solution Approach 2:

The patent introduces an object grid as an intermediary data structure between the raw 3D breast tissue data and the 2D display, maintaining depth information in the grid while enabling flexible 2D projection for ease of viewing

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If multiple 3D objects are represented on a single 2D synthesized image, then comprehensive overview is improved, but object discrimination becomes difficult

Engineering Contradiction:
Improvecomprehensive overviewVSAvoidobject discrimination
Core Design Contradiction:
ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent applies different visual properties to different regions of the 2D synthesized image based on the 3D object grid data, enhancing the appearance of objects at different depths or with different clinical significance to improve discrimination while maintaining comprehensive overview

Inventive Principle:
Principle #3Local quality

Data Source

PatentUS20250225694A1System and method for synthesizing low-dimensional image data from high-dimensional image data using an object grid enhancement
Publication Date: 2025.07.10 HOLOGIC INC
  • US20250225694A1 patent drawing
  • US20250225694A1 patent drawing
  • US20250225694A1 patent drawing

AI summary

A method for processing breast tissue image data includes processing image data of a patient's breast tissue to generate a high-dimensional grid depicting one or more high-dimensional objects in the patient's breast tissue; determining a probability or confidence of each of the one or more high-dimensional objects depicted in the high-dimensional grid; and modifying one or more aspects of at least one of the one or more high-dimensional objects based at least in part on its respective determined probability or confidence to thereby generate a lower-dimensional format version of the one or more high-dimensional objects. The method may further include displaying the lower-dimensional format version of the one or more high-dimensional objects in a synthesized image of the patient's breast tissue.