AI-Guided Sparse Tomosynthesis Scans for Faster 3D X-Ray Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tomosynthesis methods suffer from limited resolution changes at the same location, lack of view angle location information, slow incremental position and angle coverage due to single X-ray source rotation, and absence of artificial intelligence (AI) in progressive scans.
Innovation Solution
A method and system utilizing multiple pulsed X-ray sources-in-motion with AI for real-time image reconstruction, performing sparse partial scans at distributed wide angles, and determining if sufficient information is gathered for diagnostics to stop or continue scanning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a single stationary x-ray source is used for tomosynthesis imaging, then the imaging system is simple and cost-effective, but the temporal resolution is insufficient to capture rapid cardiac motion and the scan time is too long
Solution Approach 1:
The patent divides the imaging system into multiple independent x-ray sources (first and second x-ray sources) that can operate simultaneously. Each source has its own detector assembly, allowing parallel data acquisition. This segmentation enables the system to capture multiple projection angles at different time points, achieving high temporal resolution while maintaining manageable system complexity through modular design
Solution Approach 2:
The patent transitions from a single stationary source to multiple sources positioned at different locations (first and second sources at different positions). This spatial dimensionality change allows simultaneous multi-angle imaging, effectively adding temporal resolution without requiring complex motion tracking of a single source
2Productivity
If multiple x-ray sources are used simultaneously, then temporal resolution and scan speed are improved, but the device complexity and alignment precision requirements increase
Solution Approach 1:
The patent incorporates positioning members and alignment features that are pre-installed and pre-configured during manufacturing. The first and second x-ray sources are mounted with predetermined positioning structures that ensure accurate spatial relationships before operation. This preliminary action eliminates the need for complex real-time alignment adjustments during scanning
Solution Approach 2:
The patent introduces positioning members as intermediary elements between the x-ray sources and the support structure. These positioning members act as mediators that translate high-precision positioning requirements into manageable mechanical features, reducing the direct alignment burden on the x-ray source mounting structure
3Loss of time
If a single x-ray source performs sequential scanning, then device complexity is low, but the total scan time increases and temporal resolution decreases
Solution Approach 1:
The patent employs periodic scanning where the first and second x-ray sources alternately project images at different angular positions. This periodic action allows the system to acquire data from multiple angles in rapid succession, reducing total scan time while maintaining manageable complexity through systematic alternation rather than simultaneous operation of all components
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
Enables faster and more efficient 3D imaging with reduced X-ray dose by utilizing multiple X-ray sources and AI to make intelligent decisions based on patient history, achieving wide-angle coverage and high-resolution scans.
Implementation Method 1
a first and second x-ray source-in-motion tomosynthesis imaging system... each comprising: a first and second x-ray source
Data Source
Figure 1
Figure 2
Figure 3
AI summary
System and method are disclosed for imaging acquisition from sparse partial scans of distributed wide angle. During real time image reconstruction, artificial intelligence (AI) determines if there is enough information to perform diagnostics based on initial scans. If there is enough information from the fractional scans, then data acquisition stops; if more information is needed, then system performs another round of wide-angle sparse scans in a new location progressively until a result is satisfactory. The system reduces X-ray dose on a patient and performs quicker X-ray scan at multiple pulsed source-in-motion tomosynthesis imaging system. The method and system also significantly reduce the amount of time required to display high quality three-dimensional tomosynthesis images.