Tomosynthesis Mammography View Synchronization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The diagnostic review of tomosynthesis images in mammography is inefficient due to the need to compare multiple 2D slices, which increases the time required for analysis, and existing systems lack effective navigation tools for accurate and rapid comparison between reference images and tomosynthesis stacks.
Innovation Solution
A visualization system that synchronizes the view of tomosynthesis stacks based on anatomical and geometric properties, allowing for the display of corresponding regions in both tomosynthesis and 2D mammogram data sets, enabling electronic navigation and synchronization between stacks connected to patient anatomy and data set geometric position.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a whole stack of 2D images is reviewed for each breast in tomosynthesis, then the diagnostic accuracy is improved, but the review time is multiplied by the number of images in the stack
Solution Approach 1:
The tomosynthesis stack is segmented into multiple 2D image slices that can be independently navigated and viewed. The system divides the 3D data into manageable 2D segments while maintaining the ability to quickly jump between them, allowing radiologists to focus on specific regions of interest rather than sequentially reviewing every slice.
Solution Approach 2:
The system transitions from viewing only 2D slices to a 3D volumetric view that allows navigation through the stack in three dimensions. This enables radiologists to visualize the breast tissue in 3D space, identify abnormalities more efficiently, and selectively examine only the relevant slices that contain potential findings.
2Reliability
If multiple 2D mammogram images are displayed for comparison, then the diagnostic assessment quality is improved, but the complexity of the viewing system increases
Solution Approach 1:
The system merges multiple 2D mammogram images and tomosynthesis slices into a unified 3D volumetric representation. This integration allows simultaneous viewing of multiple images in a coordinated manner, with automatic alignment and registration that simplifies the comparison process while maintaining high diagnostic quality.
Solution Approach 2:
The viewing system is designed to handle multiple image types (2D mammograms, tomosynthesis slices, 3D volumes) and comparison modes (temporal comparison, bilateral comparison) within a single unified interface. This multi-functional capability eliminates the need for separate viewing systems for different comparison tasks.
3Reliability
If automatic geometric position synchronization is limited to stacks with known geometric relation, then the system reliability is improved, but the adaptability to different scanning conditions is reduced
Solution Approach 1:
The system performs automatic geometric registration and synchronization without requiring pre-defined geometric relationships or manual intervention. It autonomously identifies corresponding anatomical landmarks and calculates transformation parameters between different stacks, enabling adaptability to various scanning conditions while maintaining reliability through automated quality control.
Solution Approach 2:
The system dynamically adjusts geometric parameters (rotation, translation, scaling) based on the actual scanning conditions and patient anatomy. It modifies registration parameters automatically to accommodate different scan protocols, patient positions, and anatomical variations, thereby maintaining both reliability and adaptability.
Data Source
AI summary
Systems and methods that visualize medical data having image rendering circuits configured to substantially concurrently display a first image view of breast tissue using a stack of primary tomosynthesis image data and a second image view of breast tissue using a reference image data set, the second image view rendered from at least one of a 2D X-ray mammogram reference image data set or a reference stack of tomosynthesis image data. The first view is visualized based on: (a) anatomical and/or geometric position properties of the reference image data set of the patient; (b) properties of a current view of the reference image data set of the patient; or (c) anatomical and/or geometric position properties of the reference image data set and properties of a current view of the reference image data set.