Thresholding methods for lesion segmentation of basal cell carcinoma in dermoscopy images.

PURPOSE: Algorithms employed for pigmented lesion segmentation perform poorly on dermoscopy images of basal cell carcinoma (BCC), the most common skin cancer. The main objective was to develop better methods for BCC segmentation. METHODS: Fifteen thresholding methods were implemented for BCC lesion segmentation. We propose two error metrics that better measure the type II error: Relative XOR Error and Lesion Capture Ratio. RESULTS: On training/test sets of 305 and 34 BCC images, respectively, five new techniques outperform two state-of-the-art methods used in segmentation of melanomas, based on the new error metrics. CONCLUSION: The proposed algorithms, which include solutions for image vignetting correction and border expansion to achieve dermatologist-like borders, provide more inclusive and feature-preserving border detection, favoring better BCC classification accuracy, in future work.

Skin tumor area extraction using an improved dynamic programming approach.

BACKGROUND/PURPOSE: Border (B) description of melanoma and other pigmented skin lesions is one of the most important tasks for the clinical diagnosis of dermoscopy images using the ABCD rule. For an accurate description of the border, there must be an effective skin tumor area extraction (STAE) method. However, this task is complicated due to uneven illumination, artifacts present in the lesions and smooth areas or fuzzy borders of the desired regions. METHODS: In this paper, a novel STAE algorithm based on improved dynamic programming (IDP) is presented. The STAE technique consists of the following four steps: color space transform, pre-processing, rough tumor area detection and refinement of the segmented area. The procedure is performed in the CIE L(*) a(*) b(*) color space, which is approximately uniform and is therefore related to dermatologist's perception. After pre-processing the skin lesions to reduce artifacts, the DP algorithm is improved by introducing a local cost function, which is based on color and texture weights. RESULTS: The STAE method is tested on a total of 100 dermoscopic images. In order to compare the performance of STAE with other state-of-the-art algorithms, various statistical measures based on dermatologist-drawn borders are utilized as a ground truth. The proposed method outperforms the others with a sensitivity of 96.64%, a specificity of 98.14% and an error probability of 5.23%. CONCLUSION: The results demonstrate that this STAE method by IDP is an effective solution when compared with other state-of-the-art segmentation techniques. The proposed method can accurately extract tumor borders in dermoscopy images.

Weighted performance index for objective evaluation of border detection methods in dermoscopy images.

PURPOSE: This paper presents a novel approach for objective evaluation of border detection in dermoscopy images of melanoma. BACKGROUND: In melanoma studies, border detection is a fundamental step toward the development of a computer-aided diagnosis system. Therefore, its accuracy is essential for accurate implementation of the subsequent parts of the diagnostic system. METHOD: An objective evaluation procedure of border detection methods is presented. The evaluation procedure uses the weighted performance index, which is composed of weighted metrics of sensitivity, specificity, accuracy, precision, border error and similarity. This index can also be used to optimize the parameters of a border detection method. RESULT AND CONCLUSION: Experiments are performed on 55 high-resolution dermoscopy images. Using the union of four sets of dermatologist-drawn borders as the ground truth, weighted metrics of sensitivity, specificity, accuracy, precision, border error and similarity are evaluated. Then, the weighted performance index is constructed and used to optimize the parameters of the hybrid border detection method. The outcome of the optimization process, verified through statistical analysis, yields a higher degree of agreement between automatic borders and the ground truth, compared with using standard metrics only. Finally, the weighted performance index is used to evaluate five recently reported border detection methods.

Analysis of input-output clustering for determining centers of RBFN.

The key point in design of radial basis function networks is to specify the number and the locations of the centers. Several heuristic hybrid learning methods, which apply a clustering algorithm for locating the centers and subsequently a linear leastsquares method for the linear weights, have been previously suggested. These hybrid methods can be put into two groups, which will be called as input clustering (IC) and input-output clustering (IOC), depending on whether the output vector is also involved in the clustering process. The idea of concatenating the output vector to the input vector in the clustering process has independently been proposed by several papers in the literature although none of them presented a theoretical analysis on such procedures, but rather demonstrated their effectiveness in several applications. The main contribution of this paper is to present an approach for investigating the relationship between clustering process on input-output training samples and the mean squared output error in the context of a radial basis function netowork (RBFN). We may summarize our investigations in that matter as follows: 1) A weighted mean squared input-output quantization error, which is to be minimized by IOC, yields an upper bound to the mean squared output error. 2) This upper bound and consequently the output error can be made arbitrarily small (zero in the limit case) by decreasing the quantization error which can be accomplished through increasing the number of hidden units.