Visual Description of Skin Lesions

The work of this dissertation was aimed at getting a better understanding about the way people evaluate visual similarity of skin lesions. Experiments testing the evaluation performance achieved following the ABCD rule were run at first. Results showed a substantial variability in the obtained evaluations which puts the usefulness of this qualitative guideline under questioning. According to additional analysis, the use of the ABCD rule in the development of automatic classifiers can be arguably discouraged. Experiments purely based on visual similarity, on the other hand, showed the emergence of homogeneous visual classes of Basal Cell Carcinomas. These classes delineate some visual criteria possibly followed by the observers during the assessment. A system is developed to learn these criteria from the experimental data and promising results are reported despite the limited availability of training and testing data.