Automatic segmentation and degree identification in burn color images

Abstract

When burn injury occurs, the most important step is to provide treatment to the injury immediately by identifying degree of the burn which can only be diagnosed by specialists. However, specialists for burn trauma are still inadequate for some local hospitals. Hence, the invention of an automatic system that is able to help evaluating the burn would be extremely beneficial to those hospitals. The aim of this work is to develop an automatic system with the ability of providing the first assessment to burn injury from burn color images. The method used in this work can be divided into 2 parts, i.e., burn image segmentation and degree of burn identification. Burn image segmentation employs the Cr-transformation, Luvtransformation and fuzzy c-means clustering technique to separate the burn wound area from healthy skin and then mathematical morphology is applied to reduce segmentation errors. The segmentation algorithm performance is evaluated by the positive predictive value (PPV) and the sensitivity (S). Burn degree identification uses h-transformation and texture analysis to extract feature vectors and the support vector machine (SVM) is applied to identify the degree of burn. The classification results are compared with that of Bayes and K-nearest neighbor classifiers. The experimental results show that our proposed segmentation algorithm yields good results for the burn color images. The PPV and S are about 0.92 and 0.84, respectively. Degree of burn identification experiments show that SVM yields the best results of 89.29 % correct classification on the validation sets of the 4-fold cross validation. SVM also yields 75.33 % correct classification on the blind test experiment.

Chronic wound assessment and infection detection method

“…From our literature review, recent works for wound segmentation include: Song and Sacan [14] apply neural networks, k-means clustering, edge detection, thresholding and region growing to do wound segmentation for foot ulcers images (78 training, 14 testing). It achieves 71.4% accuracy (MLP kernel) and 85.7% accuracy (RBF kernel); Wantanajittikul et al [15] apply FCM & morphology, texture analysis and SVM to do image segmentation and characterization for 5 images (burn cases). It achieves 72.0–98.0% accuracy; Hani et al [16] apply ICA and k-means to do granulation detection and segmentation for 30 wound region images.…”

A Comparative Study of Segmentation Algorithms in the Classification of Human Skin Burn Depth

“…Table I shows the hybrid segmentation algorithms used in the comparison. The algorithm with ID 6 was proposed by the previous related work [31].…”

“…Wantanajittikul et al [31] proposed a new segmentation algorithm to separate the skin region from the background and then in turn, separate the wound region from the healthy skin. The algorithm started with converting the entire RGB image to the Cr-space.…”

Extracting Novel Features for Skin Burn Image Classification

“…The average minimum and maximum values of the normalized L*, a* and b* channels for DPTB, FTB and SPTB are calculated using the formulas as shown in (4) and (5) respectively. (4) 5where, totalImages = number of images in each burn depth The minimum and maximum standard deviation of the normalized L*, a* and b* channels for DPTB, FTB and SPTB are calculated using the formulas as shown in (6) and (8) with the (7) and (9) showing the formula used in (6) and (8) respectively. (6) where, (8) where, (9) where, totalImages = number of images in each burn depth…”

“…Most of them used the colour feature as the main characteristic to differentiate between different burn depths. There were some related work focusing on extracting both colour and texture features [6], [7], [9]- [11]. Their extracted colour features were mostly statistical moment of common colour features such as variance of hue, mean of h-space, mean of lightness and so on.…”