Tilted Tomographic X-ray Slices for Lesion Localization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Digital Breast Tomosynthesis generates a large amount of image data, increasing reading time for radiologists due to the need to navigate through multiple slices to locate a lesion, which is time-consuming and inefficient.

Innovation Solution

A method to generate tilted tomographic X-ray images by calculating the coordinates of a point of interest within a 3D dataset, allowing for the reconstruction of a tomographic slice with reduced tissue overlap, enabling faster image reading and improved diagnosis by focusing on the lesion directly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple tomographic slices are generated to provide comprehensive 3D imaging, then imaging quality and diagnostic information are improved, but reading time and operational complexity increase significantly

Engineering Contradiction:
Improveimaging qualityVSAvoidreading time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the necessary slice information by calculating and displaying only the specific tomographic slice that contains the point of interest (lesion), rather than requiring the radiologist to review all generated slices. This extraction approach maintains diagnostic quality while significantly reducing reading time.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary actions by automatically calculating the coordinates of the point of interest in the 3D dataset and pre-determining which specific slice contains the lesion before the radiologist needs to review the images. This preliminary processing eliminates the need for manual slice-by-slice search.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If all tomographic slices are reviewed to locate a lesion, then diagnostic accuracy is maintained, but reading efficiency and productivity decrease

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidreading efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system incorporates feedback mechanisms where the radiologist can interact with the displayed slice information, and the system adjusts or provides additional context as needed. This feedback loop ensures diagnostic accuracy while maintaining high reading efficiency through automated slice selection.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary processing layer that automatically calculates lesion coordinates, determines the relevant slice, and presents it to the radiologist. This intermediary system acts as a bridge between the comprehensive 3D dataset and the radiologist's diagnostic task, maintaining accuracy while improving efficiency.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If navigation to a specific slice is performed manually, then the ability to locate a lesion is maintained, but time consumption increases

Engineering Contradiction:
Improvelesion location capabilityVSAvoidnavigation time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of navigating through slices with an automated computational system that calculates the precise slice containing the lesion based on its 3D coordinates. This substitution eliminates manual search while maintaining the ability to locate lesions accurately.

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

This approach reduces reading time and enhances diagnostic efficiency by providing a clearer view of the point of interest, allowing radiologists to quickly locate lesions within the 3D dataset without needing to review all slices.

Implementation Method 1

a 3D image data set is provided comprising a plurality of projection X-ray images generated by a tomosynthesis apparatus by moving an X-ray tube of the tomosynthesis apparatus along a path around a rotation axis relative to the examination object and wherein the examination object is irradiated with X-ray at different projection angles of the X-ray tube within a defined projection angle range

Methodology Applied
Scientific EffectX-ray: X-Ray

Implementation Method 2

from the set of projection images, eventually based on parallel x-ray images (slices) generated from the measured projection images with methods of image reconstruction theory, similar to algorithms known from CT images

Methodology Applied
Scientific EffectImage reconstruction: Tomography

Data Source

PatentEP3518182B1Tilted slices in dbt
Publication Date: 2022.05.18 SIEMENS HEALTHCARE GMBH
  • EP3518182B1 patent drawingFigure 1
  • EP3518182B1 patent drawingFigure 2
  • EP3518182B1 patent drawingFigure 3

AI summary

The invention relates to a method for generating a tilted tomographic X-ray map comprising: - providing a 3D image data set comprising a plurality of projection X-ray images generated by a tomosynthesis apparatus by moving an X-ray tube (2) of the tomosynthesis apparatus along a path around a rotation axis relative to the examination object and irradiating the examination object with X-ray at different projection angles within a defined projection angle range, - determining, based on the 3D image data set, synthetic mammograms corresponding to different angles within the defined projection angle range, - determining a point of interest (30) in one of the synthetic mammograms, - calculating coordinates of the point of interest in said one synthetic mammogram or the 3D dataset, - determining a tilted image plane through the examination object, the tilted image plane comprising the point of interest (30) and the rotation axis, - generating the tilted tomographic X-ray image (50) in the tilted image plane based on the provided 3D image data set, and - displaying the tilted tomographic X-ray image (50).