Computer-Aided Diagnosis of Skin Lesions Using Conventional Digital Photography: A Reliability and Feasibility Study

Abstract

BackgroundComputer-aided diagnosis (CADx) software that provides a second opinion has been widely used to assist physicians with various tasks. In dermatology, however, CADx has been mostly limited to melanoma or melanocytic skin cancer diagnosis. The frequency of non-melanocytic skin cancers and the accessibility of regular digital macrographs have raised interest in developing CADx for broader applications.ObjectivesTo investigate the feasibility of using CADx to diagnose both melanocytic and non-melanocytic skin lesions based on conventional digital photographic images.MethodsThis study was approved by an institutional review board, and the requirement to obtain informed consent was waived. In total, 769 conventional photographs of melanocytic and non-melanocytic skin lesions were retrospectively reviewed and used to develop a CADx system. Conventional and new color-related image features were developed to classify the lesions as benign or malignant using support vector machines (SVMs). The performance of CADx was compared with that of dermatologists.ResultsThe clinicians' overall sensitivity, specificity, and accuracy were 83.33%, 85.88%, and 85.31%, respectively. New color correlation and principal component analysis (PCA) features improved the classification ability of the baseline CADx (p = 0.001). The estimated area under the receiver operating characteristic (ROC) curve (Az) of the proposed CADx system was 0.949, with a sensitivity and specificity of 85.63% and 87.65%, respectively, and a maximum accuracy of 90.64%.ConclusionsWe have developed an effective CADx system to classify both melanocytic and non-melanocytic skin lesions using conventional digital macrographs. The system's performance was similar to that of dermatologists at our institute. Through improved feature extraction and SVM analysis, we found that conventional digital macrographs were feasible for providing useful information for CADx applications. The new color-related features significantly improved CADx applications for skin cancer.

Computer-assisted melanoma diagnosis

“…This has led various research groups to assess the possibility of using digital information technology for objective analysis of patterns to aid clinicians in this complicated differentiation. A widely used method has been digital dermoscopy analysis [9][10][11][12][13][14]. This method enables images to be numerically transformed and stored.…”

“…In dermatology, attempts at synergy between man and machine have mainly been made to improve melanoma diagnosis [3][4][5][6][7][8][9][10][11][12][13][14][15]. After many years of using instruments in this field, we think that if we want to optimize computer diagnosis it is important to understand on what types of lesions we wish to exploit these new technologies.…”

Addressing overdiagnosis and overtreatment in cancer: a prescription for change

“…69 Solutions include reassessment of precursor lesions (eg, dysplastic naevi) for their consequential cancer potential and the use of computer-aided diagnostic methods to set better thresholds for biopsy. 70 Efforts have been made to establish an expert panel to identify solutions (including changes in terminology) to reduce benign biopsy rates and overly aggressive procedures. 8,9 …”

First review on psoriasis severity risk stratification: An engineering perspective

“…Statistics such as mean, standard deviation, variance, entropy, skewness, color asymmetry, chromatic difference of color plane and kurtosis for each color component of several color spaces is proposed in [47][48][49][50]. The most popular and prominent four color spaces i.e., RGB, HSV, YCbCr and CIE Lnanbn can be considered.…”