Figure 1.
Flowchart of the CADx system.
Table 1.
Demographic data for each histological diagnosis and the performance of dermatologists and CADx.
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.