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

Abstract 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.

[1]  Hong Yan,et al.  Dermatological disease diagnosis using color-skin images , 2012, 2012 International Conference on Machine Learning and Cybernetics.

[2]  Alex Waibel,et al.  Gaze Tracking Based on Face‐Color , 1995 .

[3]  Larry S. Davis,et al.  Efficient mean-shift tracking via a new similarity measure , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[4]  Hazem Wannous,et al.  Robust tissue classification for reproducible wound assessment in telemedicine environments , 2010, J. Electronic Imaging.

[5]  Kristin J. Dana,et al.  Skin Texture Modeling , 2005, International Journal of Computer Vision.

[6]  D. Kosmopoulos,et al.  Automated Pressure Ulcer Lesion Diagnosis for Telemedicine Systems , 2007, IEEE Engineering in Medicine and Biology Magazine.

[7]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[8]  Meng Liu,et al.  Efficient Mean‐shift Clustering Using Gaussian KD‐Tree , 2010, Comput. Graph. Forum.

[9]  Chandan Chakraborty,et al.  Automated Tissue Classification Framework for Reproducible Chronic Wound Assessment , 2014, BioMed research international.

[10]  Nancy A. Stotts,et al.  Wound Care: A Collaborative Practice Manual for Physical Therapists and Nurses , 1999 .

[11]  Laura E Edsberg.  Pressure ulcer tissue histology: an appraisal of current knowledge. , 2007, Ostomy/wound management.

[12]  Héctor Mesa,et al.  Binary Tissue Classification on Wound Images With Neural Networks and Bayesian Classifiers , 2010, IEEE Transactions on Medical Imaging.

[13]  C. Oomens,et al.  The Relative Contributions of Compression and Hypoxia to Development of Muscle Tissue Damage: An In Vitro Study , 2007, Annals of Biomedical Engineering.

[14]  Miguel Á. Carreira-Perpiñán.  Acceleration Strategies for Gaussian Mean-Shift Image Segmentation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[15]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[16]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[17]  J. T. Hao,et al.  Adaptive segmentation of cerebrovascular tree in time-of-flight magnetic resonance angiography , 2007, Medical & Biological Engineering & Computing.

[18]  Koji Kito,et al.  Pressure ulcers in America: prevalence, incidence, and implications for the future. An executive summary of the National Pressure Ulcer Advisory Panel monograph. , 2001, Advances in skin & wound care.

[19]  Tim D. Jones,et al.  An active contour model for measuring the area of leg ulcers , 2000, IEEE Transactions on Medical Imaging.

[20]  Nicolas Rannou,et al.  Image analysis of chronic wounds for determining the surface area , 2010, Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society.

[21]  Arie Ben-David,et al.  A lot of randomness is hiding in accuracy , 2007, Eng. Appl. Artif. Intell..

[22]  Sameh A. Salem,et al.  Segmentation of retinal blood vessels using a novel clustering algorithm (RACAL) with a partial supervision strategy , 2007, 2006 14th European Signal Processing Conference.

[23]  Dimitris A. Karras,et al.  Computer-aided tumor detection in endoscopic video using color wavelet features , 2003, IEEE Transactions on Information Technology in Biomedicine.

[24]  Xavier Blaizot,et al.  Wound debridement: Comparative reliability of three methods for measuring fibrin percentage in chronic wounds , 2010, Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society.

[25]  James M. Rehg,et al.  Statistical Color Models with Application to Skin Detection , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[26]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Marinos Elia,et al.  Disease-related Malnutrition: An Evidence-based Approach to Treatment , 2003 .

[29]  John R. Kender,et al.  Finding skin in color images , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[30]  Larry S. Davis,et al.  Mean-shift analysis using quasiNewton methods , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[31]  Liana Stanescu,et al.  A comparative study of some methods for color medical images segmentation , 2011, EURASIP J. Adv. Signal Process..

[32]  Hubert Emptoz,et al.  A Modified Mean Shift Algorithm For Efficient Document Image Restoration , 2008 .

[33]  Alexander H. Waibel,et al.  Skin-Color Modeling and Adaptation , 1998, ACCV.

[34]  Lena Gunningberg,et al.  EPUAP classification system for pressure ulcers: European reliability study. , 2007, Journal of advanced nursing.

[35]  Paul J. Kennedy,et al.  Non-parametric and integrated framework for segmenting and counting neuroblastic cells within neuroblastoma tumor images , 2013, Medical & Biological Engineering & Computing.

[36]  G. Pujolle,et al.  Efficient Mean Shift Clustering Using Exponential Integral Kernels , 2008 .

[37]  V. Papic,et al.  Accelerating mean shift image segmentation with IFGT on massively parallel GPU , 2013, 2013 36th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO).

[38]  Pedro M. Vieira,et al.  Segmentation of small bowel tumor tissue in capsule endoscopy images by using the MAP algorithm , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[39]  Michael J. Swain,et al.  Indexing via color histograms , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[40]  Alex Pentland,et al.  Parametrized structure from motion for 3D adaptive feedback tracking of faces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[41]  Anca Loredana Ion.  Towards improving medical image diagnosis , 2011, 2011 19thTelecommunications Forum (TELFOR) Proceedings of Papers.

[42]  Satendra Singh,et al.  Evaluation of wound healing process based on texture analysis , 2015 .

[43]  G. Onder,et al.  Pressure ulcer and mortality in frail elderly people living in community. , 2007, Archives of gerontology and geriatrics.

[44]  T. Nakatsuka,et al.  Analysis of ischemia‐reperfusion injury in a microcirculatory model of pressure ulcers , 2005, Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society.

[45]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[46]  Gary Bradski,et al.  Computer Vision Face Tracking For Use in a Perceptual User Interface , 1998 .

[47]  Rangaraj M. Rangayyan,et al.  Segmentation of dermatological ulcers using clustering of color components , 2013, 2013 26th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

[48]  Hazem Wannous,et al.  Enhanced Assessment of the Wound-Healing Process by Accurate Multiview Tissue Classification , 2011, IEEE Transactions on Medical Imaging.