Computer-aided diagnosis of skin lesions using conventional digital photography: a reliability and feasibility study

Abstract

Background: Computer-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.

Objectives: To investigate the feasibility of using CADx to diagnose both melanocytic and non-melanocytic skin lesions based on conventional digital photographic images.

Methods: This 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.

Results: The 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%.

Conclusions: We 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.

Figure 1. Flowchart of the CADx system.

Figure 2. Comparison of the diagnostic performance of CADx systems and dermatologists.

The ROC curves for differentiating between benign and malignant lesions using the baseline (red line) and proposed (blue line) CADx systems. The clinical sensitivity and specificity of the performance of the dermatologists (circles) at our institute are shown, and the area of the circle indicates the number of biopsies performed by each doctor. Note that the clinical sensitivity and specificity were calculated presuming that the clinician always made a “wrong” diagnosis for “indeterminate” lesions.

Figure 3. Az with different numbers of features for the baseline and proposed CADx systems.

After adding new color-related features, the proposed CADx had a better Az performance than the baseline CADx system did.

Figure 4. The accuracy of dermatologists and CADx for different pathological diagnoses.

Figure 5. Two lesions with incorrect clinical diagnoses but correct CADx categorization.

Two lesions with incorrect clinical diagnoses but correct CAD system categorization. (A) Basal cell carcinoma. A skin nodule with variegated color. The clinical impression was a benign epidermal cyst. (B) Intradermal nevus. An asymmetric pigmented nodule with an irregular border. The clinical impression was malignant melanoma.