Automated Chronic Wound Segmentation Using Probability Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for measuring and documenting chronic wound size and healing progress are time-intensive and require significant clinician involvement, limiting their effectiveness in clinical settings and accuracy.
Innovation Solution
The development of systems and methods for automated segmentation and measurement of chronic wound images using a probability map to classify pixels as belonging to granulation, slough, or eschar tissues, allowing for automated boundary determination and size measurement without user input, and enabling monitoring of wound healing over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated segmentation is implemented, then productivity and clinician workload reduction are improved, but measurement precision and reliability may worsen due to algorithmic errors
Solution Approach 1:
The patent introduces an intermediary calibration object (ruler or reference card) placed in the wound image that serves as a mediator between the automated segmentation algorithm and the actual wound boundaries. This calibration object provides known reference dimensions that enable the system to accurately scale and locate wound features, thereby maintaining measurement precision while enabling automated processing.
Solution Approach 2:
The system transforms the wound image from raw pixel data to a calibrated coordinate system by detecting the calibration object and computing transformation parameters (scale factor, position offsets). This parameter change enables the automated segmentation to operate on normalized coordinates, improving both accuracy and computational efficiency simultaneously.
2Ease of operation
If automated segmentation without user input is used, then ease of operation is improved, but measurement precision deteriorates due to lack of clinician verification
Solution Approach 1:
The system performs self-calibration by automatically detecting the calibration object within the wound image and computing its own transformation parameters without requiring clinician intervention. The algorithm identifies the calibration object's features (edges, markings), calculates scale and position, and applies these corrections autonomously, thereby maintaining high precision while maximizing ease of operation.
3Device complexity
If simple segmentation algorithms are used, then device complexity is reduced, but measurement precision worsens due to inability to handle complex wound boundaries
Solution Approach 1:
The patent divides the wound image processing into distinct segments: calibration object detection, transformation parameter calculation, and wound boundary segmentation. By separating the calibration step from the segmentation step, the system can use simple algorithms for each individual task while achieving high overall precision through the coordinated sequence of operations.
Data Source
AI summary
Disclosed are systems and methods for automated monitoring of the size, area or boundary of chronic wound images. The disclosure includes use of a probability map that measures the likelihood of wound pixels belonging to granulation, slough or eschar, which can then be segmented using any standard segmentation techniques. Measurement of the wound size, area or boundary occurs automatically and without user input related to outlining, filling in, or making measurement lines over the image on a display.