Efficient detection of wound-bed and peripheral skin with statistical colour models

• Published in: Medical & biological engineering & computing Vol. 53; no. 4; pp. 345 - 359
• Main Authors: Veredas, Francisco J., Mesa, Héctor, Morente, Laura
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2015; Springer Nature B.V
• Subjects: Aged; Aged, 80 and over; Bioengineering; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Color; Colour; Computer Applications; Computer graphics; Decisions; Female; Histograms; Human Physiology; Humans; Image Interpretation, Computer-Assisted - methods; Imaging; Machine learning; Male; Mathematical models; Medical diagnosis; Models, Statistical; Original Article; Pathology; Photography - methods; Pixels; Pressure Ulcer - diagnosis; Pressure Ulcer - pathology; Pressure ulcers; Radiology; Segmentation; Skin - pathology; Studies; Training; Ulcers; User-Computer Interface; Visualization; Spain; Image segmentation; Computer vision; Wound diagnosis; Pressure ulcer; Machine learning
• ISSN: 0140-0118; 1741-0444
• DOI: 10.1007/s11517-014-1240-0

A pressure ulcer is a clinical pathology of localised damage to the skin and underlying tissue caused by pressure, shear or friction. Reliable diagnosis supported by precise wound evaluation is crucial in order to success on treatment decisions. This paper presents a computer-vision approach to wound-area detection based on statistical colour models. Starting with a training set consisting of 113 real wound images, colour histogram models are created for four different tissue types. Back-projections of colour pixels on those histogram models are used, from a Bayesian perspective, to get an estimate of the posterior probability of a pixel to belong to any of those tissue classes. Performance measures obtained from contingency tables based on a gold standard of segmented images supplied by experts have been used for model selection. The resulting fitted model has been validated on a training set consisting of 322 wound images manually segmented and labelled by expert clinicians. The final fitted segmentation model shows robustness and gives high mean performance rates [(AUC: .9426 (SD .0563); accuracy: .8777 (SD .0799); F -score: 0.7389 (SD .1550); Cohen’s kappa: .6585 (SD .1787)] when segmenting significant wound areas that include healing tissues.