Wound Image Segmentation via Active Contouring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wound assessment methods are subjective and inaccurate, relying on manual measurements and clinician interpretation of wound color and texture, which can be influenced by lighting conditions and individual perception, leading to inconsistent and coarse estimates of wound healing progress.
Innovation Solution
A semi-automated system for real-time wound image segmentation and photogrammetry using a mobile platform, which includes a touchscreen interface for user-assisted perimeter identification and active contouring to accurately define wound boundaries, leveraging image processing algorithms for precise wound area and volume measurements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual measurements and clinician interpretation are used for wound assessment, then the process is simple and requires minimal equipment, but the measurement precision and objectivity deteriorate due to subjectivity and lighting conditions
Solution Approach 1:
The patent replaces manual mechanical measurement methods with an automated image processing system using active contouring algorithms. The system uses computer vision technology to automatically detect and measure wound boundaries, substituting clinician interpretation with algorithm-based objective measurement, thereby improving precision while maintaining ease of use through mobile device integration
Solution Approach 2:
The patent creates a digital copy of the wound through imaging and uses active contouring to generate a precise perimeter model. This digital representation allows for accurate measurement and tracking without physical contact, enabling repeated assessments without disturbing the wound environment
2Reliability
If automated image processing is used for wound assessment, then measurement precision and objectivity improve, but the device complexity and processing requirements increase
Solution Approach 1:
The system performs self-assessment through automated active contouring algorithms that automatically detect wound boundaries without requiring manual intervention. The algorithm independently processes images to generate precise measurements, enabling the system to serve itself in terms of measurement and monitoring tasks
Solution Approach 2:
The patent transitions from two-dimensional visual assessment to three-dimensional volumetric measurement by integrating active contouring across multiple image planes. This dimensional enhancement allows for more comprehensive wound characterization including depth and volume, improving reliability through multi-dimensional data
3Loss of information
If frequent wound monitoring is performed to track healing progress, then the quality of care improves, but the time required for assessment increases
Solution Approach 1:
The system enables continuous monitoring by allowing rapid successive imaging and automated processing of wound assessments. The active contouring algorithm can quickly process new images to generate updated measurements, maintaining continuous tracking of healing progress without significant time interruption to patient care
Solution Approach 2:
The patent replaces time-consuming manual measurement processes with automated image processing that rapidly generates precise measurements. This substitution dramatically reduces the time required for each assessment while maintaining or improving the accuracy of healing progress tracking
Data Source
AI summary
In one example embodiment, a wound imaging system includes a user interface, a computer processor, and an active contouring module. The user interface is configured to display an image of a wound acquired by the wound imaging system and selectively receive inputs from a user defining an initial perimeter of the wound. An active contouring module is configured to operate on the computer processor to receive the inputs defining the initial perimeter of the wound, identify features of the image on opposing sides of the initial perimeter of the wound, and identify an actual perimeter of the wound based on the initial perimeter of the wound and the identified features. The user interface is further configured to display, on the image of the wound, the actual perimeter of the wound as identified by the active contouring module and selectively receive inputs from the user to modify the actual perimeter of the wound.