Adaptive Energy Curve Fitting for CT Monochromatic Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiology diagnostic workflows in multi-energy CT imaging are inefficient due to the need for radiologists to manually review multiple image datasets or adjust energy settings, which increases dataset generation and negatively impacts diagnostic routing.
Innovation Solution
An image processing system that determines an optimal energy value for forming monochromatic images by fitting an energy curve to image data, using energy value control points assigned to specific locations, allowing for automatic adaptation of energy settings based on anatomy or tissue type, thereby reducing manual intervention and improving diagnostic efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If radiologists manually review multiple image datasets or adjust energy settings, then diagnostic capabilities are maintained, but workflow efficiency deteriorates and time consumption increases
Solution Approach 1:
The system performs self-service by automatically determining optimal energy values based on tissue type identification and energy curve fitting, eliminating the need for radiologists to manually adjust energy settings. The energy value determiner autonomously processes image data, identifies tissue characteristics, and selects appropriate energy values without human intervention.
Solution Approach 2:
The system dynamically changes the energy parameter based on identified tissue types and anatomical locations. By fitting an energy curve to control points corresponding to different tissue types, the system automatically adjusts energy values to optimize image quality for each specific anatomical region, transforming a static manual adjustment process into a dynamic adaptive system.
2Reliability
If multiple image datasets with different energy settings are generated, then comprehensive diagnostic information is provided, but dataset quantity increases and processing complexity worsens
Solution Approach 1:
The system applies local quality by determining optimal energy values specifically for each anatomical location and tissue type rather than using a single energy setting for the entire dataset. This allows comprehensive diagnostic information to be obtained through localized optimization, where each anatomical region receives the appropriate energy setting tailored to its specific tissue characteristics.
Solution Approach 2:
The system segments the imaging task by separately identifying and processing different tissue types and anatomical locations. By dividing the complex task of optimal energy selection into discrete tissue-type-based categories, the system manages complexity through structured organization of diagnostic information by anatomical region and tissue composition.
3Productivity
If fixed energy settings are used for monochromatic images, then processing speed is maintained, but image quality adaptability deteriorates across different anatomical sections
Solution Approach 1:
The system performs preliminary action by pre-calculating and storing energy curves that map anatomical locations and tissue types to optimal energy values. This pre-computed energy curve allows for rapid determination of appropriate energy settings during actual imaging, maintaining processing speed while achieving adaptability through the pre-established relationship between anatomical features and optimal energy parameters.
Data Source
AI summary
An image processing system (IPS), comprising: an input interface (IN) for receiving a request to visualize image data captured of an anatomy of interest by an imaging apparatus (IA). An energy value determiner (EVD) is configured to determine based on at least one of the image data, the different image data or contextual data, an energy value for forming, from the image data, a monochromatic image. The determining by the energy value determiner (EVD) is based on an energy curve fitted to the image data. the image data forms part of a series of sectional images acquired of the anatomy of interest, or such sectional images derivable from the image data. The sectional images relate to different locations (z) of the anatomy. The energy curve is fitted to energy value control points assigned to at least a sub-set of the different locations (z). Each energy value control point represents a respective known energy value for a respective one of the sub-set of different locations. The system allows efficiently and automatically computing an energy value for any location (z).