In vivo epiluminescence microscopy (ELM) is a non-invasive technique which improves the clinical diagnosis of naevi and malignant melanoma by providing diagnostic criteria that cannot be appreciated by the naked eye. The present study investigated whether ELM criteria pattern analysis can be employed in an objective, observer-trained, computer-aided diagnostic system, and whether artificial neural networks (ANN) can be applied to the diagnosis of pigmented skin lesions (PSL). The ELM criteria patterns of 200 PSL oil immersion images (60 common naevi, 60 dysplastic naevi, and 80 malignant melanomas) were analysed using a standardized questionnaire. One hundred randomly assigned PSL were used as a training set for an ANN, the remaining 100 PSL serving as the test set. The ANN was trained by backward propagation according to the histological diagnosis, and its performance was compared with that of human investigators. Out of the test set the human investigators correctly diagnosed 88% of PSL and the ANN 86%. In a dichotomized model comparing common, compound, and dysplastic naevi vs. malignant melanoma, i.e. benign vs. malignant PSL, the sensitivity and specificity of human diagnosis was 95 and 90%, respectively, whereas the sensitivity and specificity of the ANN diagnosis was 95 and 88%. Our data indicate that artificial neural networks can be trained to diagnose PSL at a human expert level, based on patterns provided by ELM criteria. We suggest that this technique offers a new approach to the diagnosis of PSL.

No abstract

Tumor invasion is the most reliable prognostic factor for primary stage I melanoma. "Thick" melanomas, with a Breslow thickness of more than 4 mm, tend to have a poor prognosis. Exceptions occur: some patients have no further recurrence of tumor. In an attempt to determine prognostic markers for "thick" clinical stage I melanomas, we investigated the volume-weighted mean nuclear volume of primary melanomas with tumor invasions > or = 4.0 mm in 32 patients. Seventeen of these patients developed melanoma metastases within a follow-up period of 60 mo; 15 patients who did not developed metastases and were comparable with regard to clinical and histological criteria were selected as a comparison group. Volume-weighted mean nuclear volume (Vv) is determined by a technique that permits an unbiased, efficient, shape- and orientation-independent, 3-dimensional estimation of nuclear size in tissues. This technique has been employed successfully in the prognostic assessment of stage I and II melanomas and was recently proven to be a sensitive marker for thin, high-risk melanomas. In our patients, Vv was determined by computer-assisted image analysis on Feulgen-stained sections by stereologic estimation of the Vv. The mean Vv (+/-SD) of primary melanomas with subsequent metastatic course was 794.99 +/- 209.18 micron3 (range: 409.48-1161.9 micron3), whereas primary melanoma lesions without subsequent metastases exhibited a mean Vv 640.54 +/- 205.07 micron3 (range: 206.7-927.48 micron3). This difference was found to be statistically significant (p = 0.0439). "Thick" melanomas with subsequent metastases thus exhibited a significantly higher Vv than did melanomas that did not metastasize.