Tomosynthesis ROI Extraction for Diagnostic Workflow Efficiency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current medical imaging technologies face challenges in efficiently diagnosing diseases from substantial 3D medical image data without sacrificing detail, as physicians struggle to identify regions of interest within numerous 2D and 3D images.

Innovation Solution

A system and method that enhances image processing by converting 3D medical image data into 2D format, using a three-dimensional ROI detector and extractor to create a region-of-interest-enhanced 2D image, which blends binary masks with original images to improve visibility of objects like masses, thereby aiding diagnosticians.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If 3D medical image data is reviewed in full detail, then diagnostic accuracy is improved, but time consumption and workflow efficiency deteriorate

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts regions of interest (ROIs) from the full 3D medical image data using automated detection algorithms. By isolating and highlighting only the suspicious or diagnostically relevant regions, the system allows physicians to focus on critical areas without reviewing the entire volumetric dataset, thus maintaining diagnostic accuracy while significantly reducing time consumption.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the 3D medical image data into multiple 2D projection images at different angles and depths. This segmentation allows physicians to review simplified 2D representations rather than navigating complex 3D volumes, improving workflow efficiency while preserving the ability to diagnose accurately through multi-angle visualization.

Inventive Principle:
Principle #1Segmentation

2Productivity

If 3D medical image data is converted to 2D format, then workflow efficiency is improved, but image detail and visualization quality deteriorate

Engineering Contradiction:
Improveworkflow efficiencyVSAvoidimage detail
Core Design Contradiction:
ProductivityVSLoss of information

Solution Approach 1:

The patent converts 3D medical image data into multiple 2D projection images viewed from different angles and depths. This dimensionality transformation maintains diagnostic information by providing multi-planar views, while improving workflow efficiency by presenting data in the familiar 2D format that radiologists are trained to interpret, thus avoiding information loss while enhancing productivity.

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

3Reliability

If multiple 2D and 3D images are reviewed, then comprehensive diagnosis is improved, but ease of operation deteriorates

Engineering Contradiction:
Improvecomprehensive diagnosisVSAvoidease of operation
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent merges multiple 2D projection images and 3D volumetric data into a unified display interface that presents all relevant information simultaneously. By combining these different image types and perspectives in a single integrated view with automated ROI highlighting, the system maintains comprehensive diagnostic capability while significantly improving ease of operation through streamlined visualization.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP2922472B1System and method for improving workflow efficiencies in reading tomosynthesis medical image data
Publication Date: 2023.01.04 ICAD INC
  • EP2922472B1 patent drawingFigure 1
  • EP2922472B1 patent drawingFigure 2
  • EP2922472B1 patent drawingFigure 3

AI summary

A system and a method are disclosed that forms a novel, synthetic, two-dimensional image of an anatomical region such as a breast. Two-dimensional regions of interest (ROIs) such as masses are extracted from three-dimensional medical image data, such as digital tomosynthesis reconstructed volumes. Using image processing technologies, the ROIs are then blended with two-dimensional image information of the anatomical region to form the synthetic, two-dimensional image. This arrangement and resulting image desirably improves the workflow of a physician reading medical image data, as the synthetic, two-dimensional image provides detail previously only seen by interrogating the three-dimensional medical image data.