PATIENT FACING SYSTEMS Spectral Clustering for Unsupervised Segmentation of Lower Extremity Wound Beds Using Optical Images Dhiraj Manohar Dhane 1 & Vishal Krishna 2 & Arun Achar 3 & Chittaranjan Bar 3 & Kunal Sanyal 4 & Chandan Chakraborty 1 Received: 12 April 2016 /Accepted: 14 July 2016 # Springer Science+Business Media New York 2016 Abstract Chronic lower extremity wound is a complicated disease condition of localized injury to skin and its tissues which have plagued many elders worldwide. The ulcer assess- ment and management is expensive and is burden on health establishment. Currently accurate wound evaluation remains a tedious task as it rely on visual inspection. This paper propose a new method for wound-area detection, using images digitally captured by a hand-held, optical camera. The strategy proposed involves spectral approach for clustering, based on the affinity matrix. The spectral clustering (SC) involves construction of similarity matrix of Laplacian based on Ng-Jorden-Weiss algo- rithm. Starting with a quadratic method, wound photographs were pre-processed for color homogenization. The first-order statistics filter was then applied to extract spurious regions. The filter was selected based on the performance, evaluated on four quality metrics. Then, the spectral method was used on the filtered images for effective segmentation. The segmented re- gions were post-processed using morphological operators. The performance of spectral segmentation was confirmed by ground-truth pictures labeled by dermatologists. The SC results were additionally compared with the results of k-means and Fuzzy C-Means (FCM) clustering algorithms. The SC ap- proach on a set of 105 images, effectively delineated targeted wound beds yielding a segmentation accuracy of 86.73 %, pos- itive predictive values of 91.80 %, and a sensitivity of 89.54 %. This approach shows the robustness of tool for ulcer perimeter measurement and healing progression. The article elucidates its potential to be incorporated in patient facing medical systems targeting a rapid clinical assistance. Keywords Lower extremity wound . Chronic ulcer . Optical imaging . Image processing . Spectral clustering . Segmentation Introduction Lower extremity wound (LEW) have become a serious health care problem globally. Mostly, elders with diabetes and obesity suffer from these ulcers. It may cause them severe pain, social isolation, altered mentation, incontinence and decreased produc- tivity. Since re-growth of skin is deferred or dormant, a patient takes costly and prolonged treatment. These wounds are also susceptible to secondary infections. It is reported that the popu- lation prevalence rate for chronic wounds in the United States is This article is part of the Topical Collection on Patient Facing Systems * Chandan Chakraborty chandanc@smst.iitkgp.ernet.in Dhiraj Manohar Dhane dmdhane@smst.iitkgp.ernet.in Vishal Krishna viscrisn@gmail.com Arun Achar achararun@rediffmail.com Chittaranjan Bar drcrbar@gmail.com Kunal Sanyal dmdhane_karad@yahoo.com 1 School of Medical Science and Technology, Indian Institute of Technology, Kharagpur, West Bengal, India 2 Computer Science and Engineering, Manipal Institute of Technology, Manipal, Karnataka, India 3 Department of Dermatology, Midnapore Medical College, Midnapore, West Bengal, India 4 Department of Surgery, Midnapore Medical College, Midnapore, West Bengal, India J Med Syst (2016) 40:207 DOI 10.1007/s10916-016-0554-x