Binary Tissue Classification on Wound Images With Neural Networks and Bayesian Classifiers

Abstract

A pressure ulcer is a clinical pathology of localized damage to the skin and underlying tissue caused by pressure, shear, or friction. Diagnosis, treatment, and care of pressure ulcers are costly for health services. Accurate wound evaluation is a critical task for optimizing the efficacy of treatment and care. Clinicians usually evaluate each pressure ulcer by visual inspection of the damaged tissues, which is an imprecise manner of assessing the wound state. Current computer vision approaches do not offer a global solution to this particular problem. In this paper, a hybrid approach based on neural networks and Bayesian classifiers is used in the design of a computational system for automatic tissue identification in wound images. A mean shift procedure and a region-growing strategy are implemented for effective region segmentation. Color and texture features are extracted from these segmented regions. A set of k multilayer perceptrons is trained with inputs consisting of color and texture patterns, and outputs consisting of categorical tissue classes which are determined by clinical experts. This training procedure is driven by a k-fold cross-validation method. Finally, a Bayesian committee machine is formed by training a Bayesian classifier to combine the classifications of the k neural networks. Specific heuristics based on the wound topology are designed to significantly improve the results of the classification. We obtain high efficiency rates from a binary cascade approach for tissue identification. Results are compared with other similar machine-learning approaches, including multiclass Bayesian committee machine classifiers and support vector machines. The different techniques analyzed in this paper show high global classification accuracy rates. Our binary cascade approach gives high global performance rates (average sensitivity =78.7% , specificity =94.7% , and accuracy =91.5% ) and shows the highest average sensitivity score ( =86.3%) when detecting necrotic tissue in the wound.

Computer assessment of the composition of a generic wound by image processing

“…However, wounds evolve over time, with specific types of tissue and pigmentation with eight identifiable colors which represent healing, necrosis and/or infection. [14] This theory is also supported by observations in a recent paper by Veredas et al [15] Finally, other authors have indicated that an unaccounted color may appear in a wound bed and affect classification. [17] The current study proposes that an eight-color model would more comprehensively represent wound composition, evolution and changes due to infection.…”

“…The authors previously presented initial results showing the presence of eight tissue types and pigmentation, with a one-to-one correspondence to distinct colors. [14] Subsequently, Veredas et al, [15] in their elaborate work on pressure ulcers based on four tissue-types (with the skin regarded as the fifth), have emphasized the necessity for precise evaluation. Recently, Mukherjee et al [16] presented results using a three-color model with textures.…”

Wound Healing Assessment Using Digital Photography: A Review

“…However, the classification error was greater than 50% for necrosis and the proposed approach required preliminary manual region of interest selection [14].…”

“…In clinical arena, assessment methods have mainly been based on Significant advances in the field of digital image processing make the standardized digital photography as the most popular tool which considers both aspects of the wound for assessment of healing. Several successful attempts to classify wound tissue have been made through segmentation algorithms applied to various sets of features extracted from different colour spaces, with the aim of objectively monitoring the colour changes during healing [8][9][10][11][12][13][14][15] and automatically determining the wound volume and area [16][17][18]. All these proposed methods for assessing wound healing provide information only at the surface level and cannot be applied to all types of wound [2,19].…”

A neural network learned information measures for heart motion abnormality detection

“…Adaptability and nonlinearity of ANNs has made them well-known, easy to implement, useful tools in pattern recognition [7,8], as well as in medical image processing [9][10][11].…”