Dynamic Slabbing for Tomosynthesis Image Review
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The diagnostic review of tomosynthesis mammography images is inefficient due to the need to review multiple 2D slices, which increases the time required for analysis and comparison with previous images, highlighting the need for improved navigation and visualization tools to enhance accuracy, speed, and quality of assessment.
Innovation Solution
Interactive visualization systems that include a signal processor circuit and GUI for generating slabbed views from selected slices, employing Computer Aided Detection (CAD) to identify abnormalities and automatically group slices, allowing users to refine views and browse images efficiently, and providing an electronic review wizard for automated viewing protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If tomosynthesis images are reviewed by browsing a series of 2D slices, then complete 3D representation can be obtained, but the review time increases significantly
Solution Approach 1:
The patent segments the 3D breast tissue into multiple 2D slices (stack) that can be independently viewed and analyzed. This segmentation allows the system to present complex 3D data in manageable 2D portions while maintaining the ability to reconstruct the complete 3D representation through navigation between slices.
Solution Approach 2:
The patent transforms 3D tomosynthesis data into 2D slice views for analysis, then provides navigation tools that allow physicians to move through the slice stack in a systematic manner. This dimensional transformation enables easier viewing and comparison while maintaining 3D spatial relationships through the slice stack navigation interface.
2Measurement precision
If multiple 2D slices are reviewed for each breast, then complete diagnostic information is obtained, but the speed of review process decreases
Solution Approach 1:
The patent performs preliminary actions by automatically navigating to and displaying specific slices based on predefined protocols or detected abnormalities. The system can pre-identify important slices for review based on CAD marks or other detection algorithms, allowing physicians to focus on the most relevant slices rather than reviewing the entire stack sequentially.
Solution Approach 2:
The patent incorporates feedback mechanisms where CAD systems or detection algorithms analyze the slice stack and provide recommendations for slices that require attention. This feedback loop enables the system to adapt the review process to the specific characteristics of each patient's imaging data, highlighting areas of interest and reducing the time needed for comprehensive review.
3Device complexity
If automatic geometric position synchronization is limited to stacks with known geometric relation, then processing is simplified, but the applicability to all patient scans is reduced
Solution Approach 1:
The patent implements self-service functionality where the system automatically detects and establishes geometric relationships between stacks without requiring manual input or pre-programmed configurations. The system self-adapts to different scanning conditions and patient positions, automatically determining the appropriate synchronization parameters based on the actual image data and anatomical landmarks detected in the scans.
Data Source
AI summary
Systems and methods for generating images of respective patients from multi-dimensional medical image data sets include a processor circuit in communication with a display having a graphic user interface (GUI), the processor circuit configured to define at least one grouping of a subset of slices selected from slices in a medical data stack, then generate and display at least one slabbed view based on the at least one grouping of slices.