Ultrasound Scan Data Processing for Pelvic Floor Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ultrasound scan data processing methods require manual and iterative identification of relevant slices, which is time-consuming and inefficient for medical professionals assessing pelvic floor disorders.
Innovation Solution
A system that allows medical professionals to select the first and second end boundaries of the region of interest from different views, with the option to have one boundary identified automatically, generating a set of evenly spaced images between these boundaries for improved assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual identification of relevant slices is performed, then assessment accuracy is maintained, but time consumption increases significantly
Solution Approach 1:
The system performs automatic identification of relevant slices using computer vision algorithms and deep learning models. The processing apparatus autonomously analyzes the three-dimensional scan data, detects anatomical structures, and generates two-dimensional views without requiring manual intervention, thereby resolving the contradiction between maintaining assessment quality and reducing time consumption
Solution Approach 2:
The patent replaces the manual mechanical process of slice identification with an automated computational system. The processing apparatus uses image processing algorithms, neural networks, and automated detection methods to substitute the manual visual inspection and manual slicing operations, achieving both time efficiency and maintained diagnostic accuracy
2Productivity
If iterative process is used to locate region of interest, then identification accuracy is improved, but productivity decreases
Solution Approach 1:
The system performs preliminary automatic detection and identification of the region of interest before detailed assessment. The processing apparatus pre-processes the three-dimensional scan data, automatically locates anatomical structures, and generates initial two-dimensional views, eliminating the need for iterative manual searching and significantly improving productivity while maintaining identification accuracy through advanced detection algorithms
Solution Approach 2:
The system implements feedback mechanisms where the automated detection results are continuously refined based on detected features and assessment criteria. The processing apparatus uses feedback from initial detection to adjust and optimize the identification of relevant slices, ensuring high accuracy while maintaining efficient automated operation without requiring manual iterative adjustments
Data Source
AI summary
An apparatus for processing ultrasound scan data comprises a processor configured to obtain three-dimensional ultrasound scan data for a volume including a region of interest in a subject, the processor is further configured to: provide the three-dimensional ultrasound scan data for display to the user by providing for display to the user a first two-dimensional view of the region of interest in a predetermined direction such that the first two-dimensional view intersects the first boundary; and upon receiving, via the user interface, a user input indicating a location of the first boundary in the first two-dimensional view of the region of interest, generate a second two-dimensional view of the region of interest corresponding to the slice at the first boundary on basis of the indicated location, and providing for display to the user the second two-dimensional view of the region of interest.