Synthesized 2D Mammography Image Generation via Tomosynthesis Data Merging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The transition to tomosynthesis imaging technology is hindered by the lack of integration with existing mammography expertise, as tomosynthesis systems do not leverage the interpretation skills developed for mammogram images, and they offer lower spatial resolution and less effective visualization of micro-calcifications compared to traditional mammograms.
Innovation Solution
A method to generate a synthesized 2D image by merging relevant data from 2D and 3D image sources, including mammograms, tomosynthesis projection images, and reconstructed slices, which allows radiologists to view multiple regions of interest in a single image, with optional filtering and source image display features to enhance visualization of specific features like calcifications and masses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If dedicated tomosynthesis systems are used, then better visualization of structures is achieved, but acceptance by medical professionals is reduced due to lack of integration with existing mammography expertise
Solution Approach 1:
The patent merges tomosynthesis projection images with mammogram images to create a composite image that integrates the strengths of both imaging modalities. This allows medical professionals to leverage their existing mammography interpretation expertise while benefiting from the enhanced structural visualization provided by tomosynthesis, thereby resolving the contradiction between improved visualization and adaptability to existing workflows.
2Measurement precision
If traditional mammography is used, then higher spatial resolution and better visualization of micro-calcifications are achieved, but tissue overlap and structure noise problems persist
Solution Approach 1:
The patent segments the breast tissue into multiple thin slices through tomosynthesis reconstruction, allowing individual slices to be visualized separately. This segmentation eliminates the tissue overlap problem inherent in traditional 2D mammography while preserving the high spatial resolution needed for detecting micro-calcifications, as each slice can be independently analyzed without interference from overlying structures.
3Object-affected harmful factors
If tomosynthesis imaging is used, then tissue overlap problems are reduced, but spatial resolution and micro-calcification visualization are degraded
Solution Approach 1:
The patent combines tomosynthesis projection images with conventional mammogram images in a merged display. The mammogram images contribute high spatial resolution and superior micro-calcification visualization, while the tomosynthesis component reduces tissue overlap by providing angular information. This merging strategy allows simultaneous achievement of both reduced tissue overlap and maintained high spatial resolution.
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 enables radiologists to efficiently screen and diagnose breast cancer by combining the strengths of both 2D and 3D imaging modalities, improving visualization and interpretation efficiency while minimizing the risk of false positives through cluster spread indicators.
Implementation Method 1
breast tomosynthesis systems construct a 3D image volume from a series of 2D projection images, each projection image obtained at a different angular displacement of the x-ray source relative to the image detector as the x-ray source is scanned over the detector
Data Source
AI summary
The invention includes a method including the steps of obtaining a plurality of images, each of the images in the plurality having at least one corresponding region, generating a merged image, the merged image also having the corresponding region. The step of generating includes selecting an image source from the plurality of images to source image data for the corresponding region in the merged image by comparing attributes of the corresponding regions of the plurality of images to identify the image source having preferred attributes.