M. Binder et al., Computer-aided epiluminescence microscopy of pigmented skin lesions: the value of clinical data for the classification process, MELANOMA RE, 10(6), 2000, pp. 556-561
Early melanoma is often difficult to differentiate from benign pigmented sk
in lesions (PSLs). Digital epiluminescence microscopy (DELM) and automated
image analysis could represent possible aids for inexperienced clinicians.
We designed an automated computerized image analysis system that has the po
tential for use as an additional tool for the differentiation of melanoma f
rom dysplastic naevi and common naevi. The PC-based pilot system was attach
ed to a common DELM system as the image source. Digital images of PSLs were
automatically segmented and a panel of 107 morphological parameters were m
easured. Additionally, seven clinical parameters were evaluated and used as
an additional source of information. Neural networks were then trained to
distinguish melanoma from benign PSLs. One class of networks was trained so
lely based on the morphometric features, whereas the second class of networ
ks was trained on the combination of morphometric and clinical features. Th
e automatic segmentation algorithm was correct in 96% of cases. Using three
-way receiver operating characteristic (ROC) analysis, for networks trained
solely on morphometric features the volume under surface (VUS) was 0.617 (
SD 0.036). The performance was significantly better for networks trained on
the combination of both morphometric and clinical features (VUS = 0.682, S
D 0.035). In a dichotomous model, distinguishing benign lesion (common naev
i + dysplastic naevi) from melanoma, the area under the curve (AUC) from tw
o-way ROC analysis was 0.942 (SD 0.018) for networks trained solely on morp
hometric features and 0.968 (SD 0.012) for those trained on the combination
of clinical and morphometric data (P = NS). Automated feature extraction f
rom PSLs and the training of neural networks as classifiers has thus shown
satisfactory performance in a large scale experiment. The addition of clini
cal data significantly increases the diagnostic performance for distinguish
ing three classes of lesions (i.e. common naevi, dysplastic naevi and melan
oma). Such integrated systems hold promise as a decision aid for the diagno
sis of PSLs. (C) 2000 Lippincott Williams & Wilkins.