The CASH (color, architecture, symmetry, and homogeneity) algorithm for dermoscopy
ABSTRACT The color, architecture, symmetry, and homogeneity (CASH) algorithm for dermoscopy includes a feature not used in prior algorithms, namely, architecture. Architectural order/disorder is derived from current concepts regarding the biology of benign versus malignant melanocytic neoplasms.
We sought to evaluate the accuracy of the CASH algorithm.
A total CASH score (TCS) was calculated for dermoscopic images of 325 melanocytic neoplasms. Sensitivity, specificity, diagnostic accuracy, and receiver operating characteristic curve analyses were performed by comparing the TCS with the histopathologic diagnoses for all lesions.
The mean TCS was 12.28 for melanoma, 7.62 for dysplastic nevi, and 5.24 for nondysplastic nevi. These differences were statistically significant (P < .001). A TCS of 8 or more yielded a sensitivity of 98% and specificity of 68% for the diagnosis of melanoma.
This is a single-evaluator pilot study. Additional studies are needed to verify the CASH algorithm.
The CASH algorithm can distinguish melanoma from melanocytic nevi with sensitivity and specificity comparable with other algorithms. Further study is warranted to determine its intraobserver and interobserver correlations.
[Show abstract] [Hide abstract]
ABSTRACT: Dermoscopy is a noninvasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. Color information is indispensable for the clinical diagnosis malignant melanoma, the most deadly form of skin cancer. For this reason, most of the currently accepted dermoscopic scoring systems either directly or indirectly incorporate color as a diagnostic criterion. For example, both the asymmetry, border, colors, and dermoscopic (ABCD) rule of dermoscopy and the more recent color, architecture, symmetry, and homogeneity (CASH) algorithm include the number of clinically significant colors in their calculation of malignancy scores. In this paper, we present a machine learning approach to the automated quantification of clinically significant colors in dermoscopy images. Given a true-color dermoscopy image with $N$ colors, we first reduce the number of colors in this image to a small number $K$, i.e., $K ll N$, using the $K$-means clustering algorithm incorporating a spatial term. The optimal $K$ value for the image is estimated separately using five commonly used cluster validity criteria. We then train a symbolic regression algorithm using the estimates given by these criteria, which are calculated on a set of 617 images. Finally, the mathematical equation given by the regression algorithm is used for two-class (benign versus malignant) classification. The proposed approach yields a sensitivity of 62% and a specificity of 76% on an independent test set of 297 images.IEEE Systems Journal 09/2014; 8(3):980-984. DOI:10.1109/JSYST.2014.2313671 · 1.75 Impact Factor
Actas Dermo-Sifiliográficas 08/2014; 106(1). DOI:10.1016/j.adengl.2014.11.007
[Show abstract] [Hide abstract]
ABSTRACT: Dermoscopy (dermatoscopy or epiluminescence microscopy) is a non-invasive diagnostic technique for the in vivo observation of pigmented skin lesions used in dermatology. There is currently a great interest in the prospects of automatic image analysis methods for dermoscopy, both to provide quantitative information about a lesion, which can be of relevance for the dermatologist, and as a stand-alone early warning tool. The standard approach in automatic dermoscopic image analysis has usually three stages: (i) segmentation, (ii) feature extraction and selection and (iii) lesion classification. This study evaluates the potential of an alternative approach based on the Menzies method – presence of one or more of six colour classes, indicating that the lesion should be considered a potential melanoma. This method does not require stages (i) and (ii) – lesion segmentation and feature extraction. The identification of colour classes in dermoscopic images is a subjective task, which poses great challenges for an automatic implementation. The purpose of this work is to evaluate the potential discrimination between the six Menzies colour classes in dermoscopic red, blue and green (RGB) images. The Jeffries–Matusita and transformed divergence separability distances were used to evaluate the colour class separability for an experimental evaluation with 28 dermoscopic images. Considering the skin as an additional class, an image intensity calibration was applied to the data-set, which improved the rate of separable colour class pairs. A nonlinear cluster transformation allowed almost the total separation of each colour class in the feature space. Several neural networks in competition were used as classifiers, which lead to loss of arbitrariness and perfect knowledge of each cluster surface. The discrimination between the various Menzies colour classes in dermoscopic RGB images achieved 93% of sensibility, 62% of specificity and 74% of accuracy (averaged measures). These results indicate that it might be possible to evaluate a lesion based on the presence of Menzies colours in dermoscopic images, mimicking the human diagnosis.12/2013; 1(4):211-224. DOI:10.1080/21681163.2013.803683