Transvaginal Ultrasound Endometrium Alignment for 3D Uterine Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing transvaginal ultrasound systems face challenges in aligning the endometrium with standard cross-sectional planes of the image volume, leading to increased time and resource consumption due to manual intervention and user dependence, especially when uterine abnormalities distort anatomical features.
Innovation Solution
Automated methods using image processing systems to align the endometrium with a cross-sectional plane by generating a uterine trace line based on a medial axis extraction and polynomial fitting, or performing 3D segmentation and eigenvector-based rotation to automatically orient the 3D image volume.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual alignment methods are used to align the endometrium with cross-sectional planes, then alignment can be achieved, but time consumption and resource usage increase significantly
Solution Approach 1:
The system performs automatic alignment of the endometrium with cross-sectional planes using image processing algorithms and machine learning models, eliminating the need for manual intervention by radiologists. The automated workflow independently completes tasks such as endometrium segmentation, plane selection, and image orientation, thereby reducing time consumption while maintaining alignment accuracy.
Solution Approach 2:
The patent replaces manual mechanical alignment operations with automated computational methods. Image processing systems and algorithms automatically perform the alignment task that previously required manual manipulation by radiologists, substituting human-operated mechanical processes with automated digital systems.
2Measurement precision
If manual alignment methods are used, then alignment can be achieved, but workflow efficiency decreases due to user dependence
Solution Approach 1:
The automated system independently performs endometrium alignment without requiring radiologist intervention for each step. The system self-manages the entire workflow from image acquisition through alignment and display, eliminating bottlenecks caused by manual operations and improving overall workflow efficiency while preserving alignment quality.
Solution Approach 2:
The system performs preliminary processing and pre-alignment operations automatically before presenting results to radiologists. By completing preparatory tasks such as initial segmentation and plane selection in advance, the system reduces the time radiologists need to spend on routine alignment tasks, thereby improving workflow efficiency.
3Loss of time
If automated image processing is implemented, then time and resource usage are reduced, but system complexity increases
Solution Approach 1:
The automated system divides the image processing workflow into distinct modular segments, including endometrium segmentation, plane selection, image orientation, and quality assessment. Each module performs a specific function independently, making the complex system more manageable and maintainable while enabling efficient automated processing that reduces time consumption.
Data Source
AI summary
The current disclosure provides systems and methods for improving a visualization of an image volume of a uterus and/or endometrium of a subject acquired using a transvaginal ultrasound system (TVUS). In one example, a method for the TVUS comprises extracting a medial axis of an endometrium of a received two-dimensional (2D) ultrasound image of a uterus of a subject; generating a uterine trace line based on the extracted medial axis; acquiring a three-dimensional (3D) image volume of the uterus based on the uterine trace line; and displaying the 3D image volume on a display device of the TVUS.