Area Determination of Diabetic Foot Ulcer Images Using a Cascaded Two-Stage SVM-Based Classification

• Published in: IEEE transactions on biomedical engineering Vol. 64; no. 9; pp. 2098 - 2109
• Main Authors: Wang, Lei, Pedersen, Peder C., Agu, Emmanuel, Strong, Diane M., Tulu, Bengisu
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2017; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cascaded classifier; Classification; Classifiers; Color; Colorimetry - methods; Diabetes mellitus; Diabetic Foot - diagnostic imaging; Diabetic Foot - pathology; diabetic ulcer; Feature extraction; Feet; Foot; Foot diseases; Humans; Image analysis; Image capture; Image classification; Image Interpretation, Computer-Assisted - methods; Image processing; Image segmentation; Leg ulcers; Mobile Applications; Pattern Recognition, Automated - methods; Photography - methods; Reproducibility of Results; Sensitivity and Specificity; Severity of Illness Index; Smartphone; Smartphones; Support Vector Machine; Support vector machines; support vector machines (SVM); Training; Wavelet analysis; Wound healing; wound image assessment; Wounds
• ISSN: 0018-9294; 1558-2531; 1558-2531
• DOI: 10.1109/TBME.2016.2632522

The standard chronic wound assessment method based on visual examination is potentially inaccurate and also represents a significant clinical workload. Hence, computer-based systems providing quantitative wound assessment may be valuable for accurately monitoring wound healing status, with the wound area the best suited for automated analysis. Here, we present a novel approach, using support vector machines (SVM) to determine the wound boundaries on foot ulcer images captured with an image capture box, which provides controlled lighting and range. After superpixel segmentation, a cascaded two-stage classifier operates as follows: in the first stage, a set of k binary SVM classifiers are trained and applied to different subsets of the entire training images dataset, and incorrectly classified instances are collected. In the second stage, another binary SVM classifier is trained on the incorrectly classified set. We extracted various color and texture descriptors from superpixels that are used as input for each stage in the classifier training. Specifically, color and bag-of-word representations of local dense scale invariant feature transformation features are descriptors for ruling out irrelevant regions, and color and wavelet-based features are descriptors for distinguishing healthy tissue from wound regions. Finally, the detected wound boundary is refined by applying the conditional random field method. We have implemented the wound classification on a Nexus 5 smartphone platform, except for training which was done offline. Results are compared with other classifiers and show that our approach provides high global performance rates (average sensitivity = 73.3%, specificity = 94.6%) and is sufficiently efficient for a smartphone-based image analysis.