Wound tissue segmentation by computerised image analysis of clinical pressure injury photographs: a pilot study. (2nd August 2022)

• Record Type: Journal Article
• Authors: Li, Dan; Mathews, Carol; Zamarripa, Cecilia; Zhang, Fei; Xiao, Qian
• Is Part Of: Journal of wound care. Volume 31:Number 8(2022)
• Page Start: 710
• Page End: 719
• Publication Date: 2022-08-02
• Subjects: image analysis -- nursing assessment -- pressure injury -- pressure ulcer -- wound -- wound bed -- wound care -- wound dressing -- wound healing -- wound tissue; Wounds and injuries -- Treatment -- Periodicals; Wound healing -- Periodicals; 617.1
• DOI: 10.12968/jowc.2022.31.8.710
• Languages: English
• ISSNs: 0969-0700

Abstract

Abstract : Objective: Wound tissues can provide ample information about the wound development and healing process. However, the manual identification and measurement of wound tissue types is time-consuming and challenging due to the complexities of pressure injuries (PI). This study aims to develop an image analysis algorithm to automatically identify and differentiate wound tissue types from PI wound beds. Method: This was a cross-sectional algorithm development study. PI photographs were obtained from a western Pennsylvania hospital. We used our previously developed wound bed segmentation tool to identify PI wound beds. We then used the k-means clustering method to classify the subzones on the wound beds. Finally, the support vector machine classifier was used to identify the classified subzones to certain types of wound tissue. Results: An image analysis algorithm was developed, using 64 selected PI photographs, to automatically identify different wound tissues for PIs. Conclusion: Validation of the wound tissue identification of the PIs by image analysis algorithm demonstrated that our image analysis algorithm is a reliable and objective approach to monitoring wound healing progress through clinical PI photographs, and offers new insight into PI evaluation and documentation.