Ultrasound Model Alignment via Touch Motion Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasound image processing systems face challenges in accurately aligning anatomical models with ultrasound images due to issues like poor image quality and limited field-of-view, leading to incorrect model placement and tedious manual corrections.
Innovation Solution
An ultrasound image processing apparatus with a touchscreen interface that allows users to intuitively adjust the positioning of anatomical models through recognized touch motions, enabling direct correction of model placement errors and improving automated segmentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If automatic model-based segmentation is used to eliminate user variability, then measurement consistency is improved, but model placement accuracy deteriorates due to poor image quality and limited field-of-view
Solution Approach 1:
The system performs preliminary automatic model placement before final segmentation, allowing the model to be positioned based on available image features. This preliminary action can be followed by manual adjustment if needed, resolving the contradiction by separating the automated consistency aspect from the accuracy aspect.
Solution Approach 2:
The system provides visual feedback by displaying the placed model on the ultrasound image, allowing users to verify placement accuracy and make corrections. This feedback loop enables the system to maintain automated segmentation benefits while allowing manual intervention when image quality is poor.
2Reliability
If manual model placement is used to ensure accurate alignment, then model placement accuracy is improved, but user time and effort increase significantly
Solution Approach 1:
The system applies partial automation by performing automatic model placement only when image quality and field-of-view are sufficient, while allowing manual intervention when conditions are poor. This selective approach reduces user effort in good conditions while ensuring accuracy when needed.
Solution Approach 2:
The system performs preliminary automatic placement to provide a starting point for manual adjustment, reducing the total time required for manual placement compared to starting from scratch. The automatic placement narrows down the search space for manual refinement.
3Extent of automation
If generic shape-constrained heart models are used for automated segmentation, then segmentation automation is improved, but adaptability to individual patient anatomy and pathologies deteriorates
Solution Approach 1:
The system uses dynamic model selection that adapts to the specific patient anatomy and pathology observed in the ultrasound image. The model parameters and shape constraints are adjusted dynamically based on image features, allowing the automated system to handle anatomical variability and pathological conditions.
Solution Approach 2:
The system changes model parameters such as shape constraints, size, and orientation based on the specific patient anatomy and pathology detected in the image. This parameter adaptation allows generic models to be tailored to individual cases while maintaining automation.
Data Source
AI summary
An ultrasound image processing apparatus (10) is disclosed comprising a processor arrangement (16) adapted to map a model (1) of an anatomical feature of interest onto an ultrasound image showing at least a section of said anatomical feature of interest and to segment said ultrasound image in accordance with the mapped model; and a touchscreen display (18, 19) adapted to display said ultrasound image including the mapped anatomical model. The processor arrangement is responsive to the touchscreen display and adapted to recognize a type of a user touch motion (3) provided through the touchscreen display (18, 19), each type of user touch motion being associated with a particular type of alteration of said mapping and alter said mapping in accordance with the recognized type of user touch motion. Also disclosed are an ultrasound imaging system, a computer-implemented method and a computer program product.