The main goal of the aided diagnosis is to develop machines that will help clinicians in their daily practice. For this reason, the instrument must be easy to use, fast and not based on subjective evaluation. When a System-aided interpretation is based on clinician's assessments the results are obviously based on a poor engine. Moreover the hidden trap is the fact that a clinician himself can not be the "gold standard" for the diagnosis. A real false negative has not been seen by the dermatologist. For this reason many scientific studies are not very useful when reporting high accuracy with machines that depend on previous expert examination because he is a filter for the reality of facts. Plus we also know that Systems with poor quality only "see" trivial melanoma. For this reason, it is apparently easy to reach very high sensibility on such machines, but the results are false. Some studies report a sensitivity of 100%, forgetting that the histology itself, which is the "gold standard", does not reach such value. If a study is based on aprevious clinician's examination, we must consider his error and multiply the sensibility for a correction factor. Otherwise it would be necessary to employ skin cancer registries and multicentered validations, as was done during the development of the DB-Mips System.

DB-Mips actually employs ANN and Similarity classifiers. The results obtained during the last decade by independent clinicians who used the DB-Mips are reported on this page. Please note how the release version and the accuracy values have increased over the years. Subjective , non-reproducible algorithms have been replaced by objective and reliable variables. The experts use their common sense and machines do the rest.