Patient-Specific CT Organ Dose Estimation via Auto-Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current CT radiation dose monitoring metrics, such as CTDI and DLP, are not accurate for estimating radiation doses to actual patients, as they are measured using a uniform acrylic cylinder and do not account for individual patient anatomy.
Innovation Solution
A system and method for automatically estimating patient-specific CT radiation doses using an auto-segmentation module to delineate organ boundaries, a dose-distribution-calculation module to generate spatially-dependent dose distribution maps by solving the Boltzmann Transport Equation, and a dose-tabulation module to compute individual organ doses based on these maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current dose monitoring metrics (CTDI, DLP) are used, then dose measurement is simple and standardized, but the measurement precision of actual patient organ dose is poor
Solution Approach 1:
The patent creates a virtual copy of the patient's anatomy by segmenting the CT volume into organ regions. This digital phantom is then used for dose calculation instead of physical phantoms, allowing patient-specific dose estimation while maintaining computational efficiency.
Solution Approach 2:
The patent divides the CT volume into multiple organ regions through automatic segmentation. This segmentation allows for separate dose calculation for each organ, improving measurement precision while enabling automated processing that manages system complexity.
2Measurement precision
If patient-specific organ dose estimation is implemented, then dose assessment accuracy is improved, but computational complexity and processing time increase
Solution Approach 1:
The patent performs automatic segmentation and organ identification before dose calculation. By preparing the anatomical model in advance with pre-segmented organ regions, the subsequent dose calculation can proceed efficiently without manual intervention during the actual dosimetry process.
Solution Approach 2:
The system uses the patient's own CT scan data to automatically generate the anatomical model and perform segmentation. The algorithm independently identifies organ boundaries and creates the dose calculation model without requiring external reference data or manual anatomical knowledge from operators.
3Ease of operation
If automatic segmentation is used to delineate organ boundaries, then ease of operation is improved, but segmentation accuracy may be compromised compared to manual methods
Solution Approach 1:
The patent incorporates feedback mechanisms in the automatic segmentation process, where the algorithm iteratively refines organ boundary detection based on image intensity patterns and anatomical constraints. This feedback loop improves segmentation accuracy while maintaining automated operation.
Solution Approach 2:
The segmentation algorithm adjusts parameters such as intensity thresholds and region boundaries dynamically based on the specific CT scan characteristics. This adaptability allows the automated system to achieve high precision across different patients and scanning conditions without manual recalibration.
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
Provides accurate and patient-specific radiation dose estimates, allowing for better assessment of radiation exposure to organs during CT scans, improving dose monitoring and patient safety.
Implementation Method 1
generate a spatially-dependent dose distribution map by solving a Boltzmann Transport Equation (BTE) using finite-element methods
Data Source
AI summary
In accordance with at least some embodiments of the present disclosure, a process for calculating patient-specific organ dose is presented. The process may include constructing a computed tomography (CT) volume based on CT images generated by a CT scanner. The process may include segmenting the CT volume into a plurality of organ regions, generating a material density map for the CT volume based on Hounsfield Unit (HU) values, and generating a dose distribution map for the CT volume based on the material density map by simulating particles emitting from the CT scanner and flowing through the CT volume. The process may further generate a dose value delivered to a specific organ region of the plurality of organ regions based on the dose distribution map.