Computational approach for chronic wound tissue characterization. (2019)

• Record Type: Journal Article
• Authors: Chakraborty, Chinmay
• Is Part Of: Informatics in medicine unlocked. Volume 17(2019)
• Publication Date: 2019
• Subjects: Chronic wounds -- Image segmentation -- Tissue classification -- Feature extraction -- Performance analysis; Medical informatics -- Periodicals; 610.285
• DOI: 10.1016/j.imu.2019.100162
• Languages: English
• ISSNs: 2352-9148

Abstract

Abstract: This paper describes an automated diagnostic system for continuous chronic wound status monitoring. Accurate and periodic wound assessment is important for optimal wound care. Automated wound diagnosis is beneficial for the aging population, to obtain a treatment-related decision for clinicians. Wound healing analysis can be done using image pre-processing, segmentation, and classification, with visual evaluation by a learned clinician. In this paper, we proposed fuzzy c-means clustering for wound image segmentation, in conjunction with the standard computational learning schemes: Linear Discriminant Analysis (LDA), Decision Tree (DT), Naïve Bayesian (NB) and Random Forest (RF). These techniques are useful for classifying the percent of wounded tissue in a segmented region. The color features observed in the imagery were expected to be helpful to enhance resolution. The histogram sampling method was found useful to provide a wider separation between wounded portions in the color space. The overall accuracy of our paradigm was measured with respect to images judged by an expert clinician, who manually traced the wound portions, i.e., for groundtruth images versus segmented wound images. The outcome of the proposed technique provided a 93.75% overall accuracy; whereas, using the Random Forest scheme with Decision Tree, Linear Discriminant Analysis, and Naïve Bayesian, we obtained 84.29%, 85.67%, and 78.66% accuracy, using manual segmentation as groundtruth. The proposed scheme achieved an overall performance comparable to the best results reported in the literature. Highlights: Chronic wound tissue prediction under telemedicine framework is proposed. Identification of tissue and correct prediction of wound status is formulated. Linear Discriminant Analysis, Decision Tree, Naïve Bayesian and Random Forest are used to classify effectively in segmented region. Intensity based features were extracted for training the proposed methodology. Robust Telemedicine based wound tissue analyzer with 93.75% accuracy is provided.