3D Patient Anatomy Model Accuracy Mapping at Tissue Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing patient-specific modeling techniques introduce errors in anatomical models due to data processing, particularly at tissue interfaces and anatomical landmarks, leading to potential complications during surgeries and reduced effectiveness of surgical procedures.
Innovation Solution
Systems and methods for analyzing bone models by calculating signal intensity gradients and curvature to indicate accuracy, overlaying accuracy indicators on the model, and flagging potential inaccuracies for operator correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If data processing procedures (filtering, interpolation, sampling) are applied to imaging data to create a patient model, then the model can be generated for surgical planning, but errors and deviations are introduced that reduce the precision of the anatomical representation
Solution Approach 1:
The system calculates gradient values at each voxel of the segmented volume and compares these gradients against threshold values to determine accuracy. This feedback mechanism identifies regions where the segmented model deviates from the original imaging data, allowing operators to review and correct specific areas rather than regenerating the entire model.
Solution Approach 2:
The patent changes the parameter being measured from simple voxel classification to gradient-based accuracy assessment. By calculating the gradient of signal intensity values at each voxel boundary and comparing it to threshold values, the system provides a quantitative measure of segmentation accuracy that highlights regions requiring improvement.
2Adaptability or versatility
If image segmentation is performed to create a three-dimensional bone surface model from imaging data, then the model can be used for surgical planning, but inaccuracies occur at tissue interfaces and anatomical landmarks
Solution Approach 1:
The system applies local quality assessment by evaluating gradient values at each individual voxel rather than assessing the entire model uniformly. This allows different regions of the model to be evaluated based on their local characteristics, with high-gradient regions (tissue interfaces) receiving more stringent accuracy checks through threshold comparison.
Solution Approach 2:
The patent segments the volume data into multiple voxels and evaluates each voxel's gradient independently. This voxel-level segmentation of the accuracy assessment process allows identification of specific problematic regions at tissue interfaces and anatomical landmarks without requiring re-evaluation of the entire model.
3Shape
If the data is processed multiple times with smoothing and estimation techniques, then the model surface becomes smoother, but the chance of introducing errors and deviations from actual anatomy increases
Solution Approach 1:
The gradient calculation and threshold comparison provides feedback on the reliability of each region after smoothing operations. By comparing gradients before and after processing, or by using absolute gradient thresholds, the system identifies regions where smoothing may have excessive deviations, allowing operators to adjust processing parameters or review specific areas.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems, devices, and methods are described for providing patient anatomy models with indications of model accuracy included with the model. Accuracy is determined, for example, by analyzing gradients at tissue boundaries or by analyzing tissue surface curvature in a three-dimensional anatomy model. The determined accuracy is graphically provided to an operator along with the patient model. The overlaid accuracy indications facilitate the operator's understanding of the model, for example by showing areas of the model that may deviate from the modeled patient's actual anatomy.