Ultrasound Fetal Imaging via Articulated Model Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current 3D ultrasound imaging systems face challenges in generating high-quality compounded images of fetuses due to fetal movement, which limits the field of view and complicates image stitching, often resulting in low-quality or unusable compounded images, especially in later gestational ages.
Innovation Solution
An ultrasound imaging system that uses an articulated fetal model with joint-limb relationships to segment and adapt 3D image frames, determining the relative orientation and confidence value of each frame, and compares it to an image compounding threshold to ensure high-quality spatial compounding, allowing for improved visualization and flexibility in data acquisition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If standard image stitching or mosaicking is used to combine 3D ultrasound image frames, then the field of view is expanded to cover the full fetus, but image quality deteriorates when the fetus moves between acquisitions
Solution Approach 1:
The system performs preliminary segmentation of each 3D image frame using an articulated fetal model to identify the fetus position and orientation before compounding. This preliminary action allows the system to detect fetal movement between acquisitions and adapt the compounding process accordingly, preventing image quality deterioration while maintaining expanded field of view
Solution Approach 2:
The system dynamically adapts the articulated fetal model to each acquired 3D image frame by detecting variations in fetal structure and adjusting the model parameters. This dynamic adaptation enables the system to handle fetal movement between acquisitions, maintaining reliable image quality while achieving comprehensive field of view coverage
2Area of stationary object
If multiple 3D image frames are acquired at different look directions to achieve full fetus coverage, then the field of view increases, but the complexity of image processing and compounding increases
Solution Approach 1:
The system segments each 3D image frame into fetal and non-fetal regions using an articulated fetal model. This segmentation simplifies the compounding process by focusing processing only on relevant fetal structures, reducing overall image processing complexity while maintaining comprehensive field of view coverage through multiple look directions
Solution Approach 2:
The articulated fetal model serves multiple functions simultaneously: it segments image frames, identifies fetal orientation, detects movement between acquisitions, and guides the compounding process. This multi-functionality reduces processing complexity by consolidating multiple tasks into a single unified framework
3Reliability
If the articulated fetal model is adapted to each 3D image frame to handle fetal movement, then image quality is maintained, but the processing time and computational load increase
Solution Approach 1:
The system performs partial adaptation of the articulated fetal model by focusing computational resources on detecting and adapting to significant fetal movements rather than processing every detail of each frame. This selective approach maintains image quality while reducing overall processing time
Data Source
AI summary
The present invention provides an improved ultrasound imaging system arranged to evaluate a set of acquired 3D image data in order to provide a compounded 3D image of a fetus irrespective of its position and movement. This is achieved by providing an ultrasound imaging system comprising: an ultrasound probe having an ultrasound transducer array operable to acquire at different look directions a plurality of three dimensional (3D) ultrasound image frames of a volumetric region comprising a fetus; a compound image memory for storing the acquired plurality of the 3D ultrasound image frames and an articulated fetal model with a common fetal structure; an ultrasound image processor responsive to the plurality of 3D ultrasound image frames, said processor comprising a fetal segmentation unit arranged to segment each 3D image frame based on the articulated fetal model thereby providing a plurality of spatially related 3D images of the volumetric region; and an image quality analyzer coupled to the segmentation unit and arranged to determine, based on the articulated fetal model, an overall confidence value of the plurality of the 3D images, said image quality analyzer is further arranged to compare the overall confidence value with an image compounding threshold.