AI Breast Lesion Matching Across X-Ray and Ultrasound Imaging

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Clinicians face challenges in accurately correlating lesions identified in x-ray imaging with those in ultrasound imaging due to differences in patient position, imaging modality appearance, and the increasing size of detectable lesions, making it difficult to navigate and confirm lesion matches during diagnostic ultrasound procedures.

Innovation Solution

A computing system utilizing artificial intelligence and machine learning algorithms analyzes x-ray and ultrasound images to determine the likelihood that a potential lesion in ultrasound corresponds to a previously identified lesion in x-ray imaging, providing a confidence score and navigation assistance through electromagnetic or optical tracking inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If x-ray imaging is performed with patient upright and breast under compression to detect lesions, then lesion detection capability is improved, but difficulty in correlating lesion position with ultrasound imaging increases

Engineering Contradiction:
Improvelesion detection capabilityVSAvoiddifficulty in correlating lesion position
Core Design Contradiction:
Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The system performs preliminary co-registration of the x-ray image with the ultrasound image before the ultrasound procedure. This pre-alignment establishes a reference framework that allows the ultrasound system to navigate to the correct lesion location even though the breast will be in a different position and compression state during ultrasound imaging. The co-registration creates a mapping relationship that compensates for the anticipated positional changes.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual mechanical navigation and visual correlation methods with an automated computer-based image co-registration and navigation system. The system uses software algorithms to mathematically align the x-ray and ultrasound images and provides automated guidance to the ultrasound probe position, eliminating the need for manual trial-and-error navigation by the technologist.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If different imaging modalities (x-ray and ultrasound) are used to image breast tissue, then comprehensive diagnostic information is obtained, but difficulty in correlating images due to different appearance and contrast levels increases

Engineering Contradiction:
Improvecomprehensive diagnostic informationVSAvoiddifficulty in correlating images
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system introduces a computer-based image co-registration system as an intermediary that bridges the two different imaging modalities. This intermediary performs mathematical transformations to align the x-ray and ultrasound images into a common coordinate system, allowing clinicians to correlate lesions across modalities despite their different appearances, contrast levels, and imaging geometries.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If ultrasound imaging is performed without compression to maintain patient comfort, then patient comfort is improved, but ability to locate small lesions previously identified in x-ray imaging decreases

Engineering Contradiction:
Improvepatient comfortVSAvoidability to locate small lesions
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary co-registration of the x-ray image (taken with compression) with the ultrasound image (taken without compression) before the ultrasound procedure. This pre-alignment establishes a reference framework that allows the ultrasound system to navigate to the correct lesion location even though the breast will be in a different position and compression state during ultrasound imaging.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual mechanical navigation and visual correlation methods with an automated computer-based image co-registration and navigation system. The system uses software algorithms to mathematically align the x-ray and ultrasound images and provides automated guidance to the ultrasound probe position, eliminating the need for manual trial-and-error navigation by the technologist.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enhances the ability to accurately locate and confirm lesions identified in x-ray imaging within ultrasound images, improving diagnostic precision and reducing the imaging analysis workload.

Implementation Method 1

Ultrasound uses sound waves, typically produced by piezoelectric transducers, to image tissue in a patient

Methodology Applied
Scientific EffectPiezoelectric effect: Piezoelectric Effect

Implementation Method 2

An ultrasound probe focuses the sound waves by producing an arc-shaped sound wave that travels into the body and is partially reflected from the layers between different tissues in the patient. The reflected sound wave is detected by the transducers

Methodology Applied
Scientific EffectAcoustic reflection: Reflection

Data Source

PatentEP4125601B1Systems and methods for correlating regions of interest in multiple imaging modalities
Publication Date: 2025.08.06 HOLOGIC INC
  • EP4125601B1 patent drawingFigure 1
  • EP4125601B1 patent drawingFigure 2
  • EP4125601B1 patent drawingFigure 3

AI summary

Methods and systems for identifying a region of interest in breast tissue utilize artificial intelligence to confirm that a target lesion identified during imaging the breast tissue using a first imaging modality (e.g. x-ray imaging) has been identified using a second imaging modality (e.g. ultrasound imaging). A computing system operating a lesion matching engine utilizes a machine learning classifier algorithm trained on cases of x-ray images and corresponding ultrasound images in which lesions were identified for further analysis. The lesion matching engine analyzes a target lesion identified with x-ray imaging and a potential lesion identified with ultrasound imaging to determine a likelihood that the target lesion is the same as the potential lesion. A confidence level indicator for the lesion match is presented on a display of a computing device to aid a healthcare provider in locating a lesion in breast tissue.