Fuzzy spectral clustering for automated delineation of chronic wound region using digital images

Chronic wound is an abnormal disease condition of localized injury to the skin and its underlying tissues having physiological impaired healing response. Assessment and management of such wound is a significant burden on the healthcare system. Currently, precise wound bed estimation depends on the clinical judgment and remains a difficult task. The paper introduces a novel method for ulcer boundary demarcation and estimation, using optical images captured by a hand-held digital camera. The proposed approach involves gray based fuzzy similarity measure using spatial knowledge of an image. The fuzzy measure is used to construct similarity matrix. The best color channel was chosen by calculating the mean contrast for 26 different color channels of 14 color spaces. It was found that Db color channel has highest mean contrast which provide best segmentation result in comparison with other color channels. The fuzzy spectral clustering (FSC) method was applied on Db color channel for effective delineation of wound region. The segmented wound regions were effectively post-processed using various morphological operations. The performance of proposed segmentation technique was validated by ground-truth images labeled by two experienced dermatologists and a surgeon. The FSC approach was tested on 70 images. FSC effectively segmented targeted ulcer boundary yielding 91.5% segmentation accuracy, 86.7%, Dice index and 79.0%. Jaccard score. The sensitivity and specificity was found to be 87.3% and 95.7% respectively. The performance evaluation shows the robustness of the proposed method of wound area segmentation and its potential to be used for designing patient comfort centric wound care system.

[1]  Chandan Chakraborty,et al.  Selection of Optimal Denoising Filter Using Quality Assessment for Potentially Lethal Optical Wound Images , 2015 .

[2]  A. Hoppe,et al.  Analysis of Skin Wound Images Using Digital Color Image Processing: A Preliminary Communication , 2004, The international journal of lower extremity wounds.

[3]  Sansanee Auephanwiriyakul,et al.  Automatic segmentation and degree identification in burn color images , 2012, The 4th 2011 Biomedical Engineering International Conference.

[4]  N. D. Nanayakkara,et al.  Mobile based wound measurement , 2013, 2013 IEEE Point-of-Care Healthcare Technologies (PHT).

[5]  Peter Plassmann,et al.  Improved active contour models with application to measurement of leg ulcers , 2003, J. Electronic Imaging.

[6]  Marc Ebner.  A parallel algorithm for color constancy , 2004, J. Parallel Distributed Comput..

[7]  Shubhangi Vinayak Agale,et al.  Chronic Leg Ulcers: Epidemiology, Aetiopathogenesis, and Management , 2013 .

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

[9]  Aurobinda Routray,et al.  Diagnostic and Prognostic Utility of Non-Invasive Multimodal Imaging in Chronic Wound Monitoring: a Systematic Review , 2017, Journal of Medical Systems.

[10]  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.

[11]  Chandan Chakraborty,et al.  Telemedicine Supported Chronic Wound Tissue Prediction Using Classification Approaches , 2016, Journal of Medical Systems.

[12]  Gerd Glaeske,et al.  Epidemiology of chronic wounds in Germany: Analysis of statutory health insurance data , 2016, Wound repair and regeneration : official publication of the Wound Healing Society [and] the European Tissue Repair Society.

[13]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[14]  Rahul Shetty,et al.  A novel and accurate technique of photographic wound measurement , 2012, Indian Journal of Plastic Surgery.

[15]  Adilson Gonzaga,et al.  Segmentation and analysis of leg ulcers color images , 2001, Proceedings International Workshop on Medical Imaging and Augmented Reality.

[16]  Gargi Mukherjee,et al.  Segmentation of Chronic Wound Areas by Clustering Techniques Using Selected Color Space , 2013 .

[17]  Line Bisgaard Jørgensen,et al.  Methods to assess area and volume of wounds – a systematic review , 2016, International wound journal.

[18]  P. Franks,et al.  The burden of chronic wounds in the UK. , 2008, Nursing times.

[19]  Sylvie Treuillet,et al.  Relevé 3D couleur d'escarres par un appareil photo numérique , 2005 .

[20]  Nicholas A Richmond,et al.  Evidence‐based management of common chronic lower extremity ulcers , 2013, Dermatologic therapy.

[21]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[22]  Metin Nafi Gürcan,et al.  Segmentation and automated measurement of chronic wound images: probability map approach , 2014, Medical Imaging.

[23]  Rafael Marcos Luque Baena,et al.  Wound image evaluation with machine learning , 2015, Neurocomputing.

[24]  Honglak Lee,et al.  A unified framework for automatic wound segmentation and analysis with deep convolutional neural networks , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[25]  Metin Nafi Gürcan,et al.  Computerized segmentation and measurement of chronic wound images , 2015, Comput. Biol. Medicine.

[26]  Licheng Jiao,et al.  Spectral clustering with fuzzy similarity measure , 2011, Digit. Signal Process..

[27]  Feipei Lai,et al.  Surgical wound segmentation based on adaptive threshold edge detection and genetic algorithm , 2017, International Conference on Graphic and Image Processing.

[28]  Paul Anthony Iaizzo,et al.  Wound status evaluation using color image processing , 1997, IEEE Transactions on Medical Imaging.

[29]  Bo Song,et al.  Automated wound identification system based on image segmentation and Artificial Neural Networks , 2012, 2012 IEEE International Conference on Bioinformatics and Biomedicine.

[30]  J. Bezdek,et al.  Recent convergence results for the fuzzy c-means clustering algorithms , 1988 .

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

[32]  L. Tang,et al.  Improved Retinex Image Enhancement Algorithm , 2011 .

[33]  R. W. Daniel,et al.  An assessment of the accuracy and usability of a novel optical wound measurement system , 2009, Diabetic medicine : a journal of the British Diabetic Association.

[34]  P. Bell,et al.  Wound Measurement in Diabetic Foot Ulceration , 2011 .

[35]  Christos P. Loizou,et al.  Evaluation of wound healing process based on texture analysis , 2012, 2012 IEEE 12th International Conference on Bioinformatics & Bioengineering (BIBE).

[36]  R J Hinchliffe,et al.  Evidence-based management of PAD & the diabetic foot. , 2013, European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery.

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

[38]  S. Gupta,et al.  Wound Healing Research: A Perspective From India , 2005, The international journal of lower extremity wounds.

[39]  Chandan Chakraborty,et al.  Spectral Clustering for Unsupervised Segmentation of Lower Extremity Wound Beds Using Optical Images , 2016, Journal of Medical Systems.

[40]  G. Gethin,et al.  Wound measurement comparing the use of acetate tracings and Visitrak digital planimetry. , 2006, Journal of clinical nursing.

[41]  Héctor Mesa,et al.  Efficient detection of wound-bed and peripheral skin with statistical colour models , 2014, Medical & Biological Engineering & Computing.