Paper Info
Title
A Two-Phase Learning Approach for the Segmentation of Dermatological Wounds
Abstract
Tissue segmentation in photographs of lower limb chronic ulcers is a non-intrusive approach that supports dermatological analyses. This paper presents 2PLA, a method that combines supervised and unsupervised learning strategies for enhancing the segmentation of dermatological wounds. Given an ulcer photo captured according to a fixed protocol, 2PLA first phase performs a pixelwise classification of points of interest, whereas pre-processing filters are employed for the smoothing of image noise. The cleaned image is further sent to the 2PLA divide-and-conquer second phase. It builds upon SLIC superpixel construction algorithm for dividing the lower limb into regions of interest with well-defined borders, and clusters the superpixels by taking advantage of the similarity-based DBSCAN algorithm. We set up the phases of our method by using a real annotated set of dermatological wounds, and empirical evaluations on representative samples up to 100,000 points showed a compact Multi-Layer Perceptron with Levenberg-Marquardt training algorithm (Cohen-Kappa = .971, Sensitivity = .98, and Specificity = .98) outperformed other classifiers as 2PLA first phase. Additionally, experimental trials on DBSCAN with five distance functions (L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> , L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> , L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">∞</sub> , Canberra, and BrayCurtis) indicated L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> function provided fewer groups in comparison to the competitors, and the number of clusters was an exponential decay to the similarity ratio. Accordingly, we used the elbow criterion for finding the L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -based DBSCAN threshold as 2PLA second phase parameterization. We evaluated the fine-tuned setting of our method over a labeled set of ulcer images, and wounded tissues were segmented within a .05 Mean Absolute Error ratio. These results illustrate the impact of learning parameters on 2PLA as well as the method efficacy for wound segmentation.
Year
DOI
Venue
2019
10.1109/CBMS.2019.00076
2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS)
Keywords
DocType
ISSN
Wound images, Superpixels, MLP, DBSCAN
Conference
2372-918X
ISBN
Citations 
PageRank 
978-1-7281-2287-8
2
0.39
References 
Authors
11
9
Name
Order
Citations
PageRank
Wellington S. Silva120.39
Daniel L. Jasbick220.39
Rodrigo E. Wilson320.39
Paulo M. Azevedo-Marques419519.04
Agma J. M. Traina51024153.61
Lucio F. D. Santos6256.76
Ana Elisa Serafim Jorge781.21
Daniel de Oliveira861759.87
Marcos V. N. Bedo920.39